pastenow
pastenow

Tag: Learning

Mastering Design Principles for Machine Learning

Software design principles are general guides for developing clean, readable and maintainable code. Design principles are important because they provide best practices that help ensure that code can be easily understood, reused, scaled and tested. Writing code without incorporating at least some of ...

Updates on Hidden Markov Models in 2023 part7(Machine Learning)

Abstract : In the paper, we introduce the maximum entropy estimator based on 2-dimensional empirical distribution of the observation sequence of hidden Markov model , when the sample size is big: in that case computing the maximum likelihood estimator is too consuming in time by the classical Baum-W...

Dynamic Pricing with Multi-Armed Bandit: Learning by Doing

In the vast world of decision-making problems, one dilemma is particularly owned by Reinforcement Learning strategies: exploration versus exploitation. Imagine walking into a casino with rows of slot machines (also known as “one-armed bandits”) where each machine pays out a different, un...

When AI Goes Astray: High-Profile Machine Learning Mishaps in the Real World

The transformative potential of artificial intelligence (AI) and machine learning has often made headlines in the news, with plenty of reports on its positive impact in diverse fields ranging from healthcare to finance. Yet, no technology is immune to missteps. While the success stories paint a p...

TOP 3 MACHINE LEARNING CERTIFICATIONS FOR AN INCREASED SALARY IN 2023

Bring your dream AI career to reality with the most sought-after AI certifications around the world. Enrol with the best credentials providers and earn big with every passing year. Machine Learning Certifications | USAII Digging into some core statistics, to begin with;...

Leveraging Clustering for Document Layout Analysis in Machine Learning Projects

Introduction In machine learning / AI projects, dealing with diverse document layouts can pose a significant challenge. However, by leveraging clustering techniques, we can identify documents with similar layouts and selectively augment the training data to improve model performance. In this blog...

Machine Learning Tricks, Learning with ChatGPT, and Other Recent Must-Reads

As August comes to a close, many of our readers are heading back to school (be it at university, a boot camp, or online), while others are shaking off the last vestiges of slower summer schedules. What better time to prepare for the next chapter of your data science learning journey? If you&rsquo...

Boosting Model Accuracy: Techniques I Learned During My Machine Learning Thesis at Spotify (+Code Snippets)

In 2021, I spent 8 months building a predictive model to measure user satisfaction as part of my Thesis at Spotify. Image by Author My goal was to understand what made users satisfied with their music experience. To do so, I built a LightGBM classifier whose output was a binary r...

Parsnip: Where Machine Learning Models Snap Together Like LEGO Mindstorms

In the intricate landscape of machine learning, each algorithm and model is like a unique LEGO piece. They come in various shapes, sizes, and colors, each offering its own distinct function. Whether you’re working with the sturdy ‘brick’ of linear regression or the intricate &lsquo...

How I Deployed a Machine Learning Model for the First Time

Introduction For as long as I’ve started with machine learning, Jupyter Notebooks have been my most loyal sidekick. From data preprocessing to model training, fine-tuning, and testing, Jupyter Notebooks have been there at every step to support me. However, I always knew that there is an ent...

When AI Goes Astray: High-Profile Machine Learning Mishaps in the Real World

The transformative potential of artificial intelligence (AI) and machine learning has often made headlines in the news, with plenty of reports on its positive impact in diverse fields ranging from healthcare to finance. Yet, no technology is immune to missteps. While the success stories paint a p...

How far have we come with Wireless sensor networks part2(Machine Learning)

Abstract : Wireless sensor networks (WSNs) are self-organizing monitoring networks with a large number of randomly deployed microsensor nodes to collect various physical information to realize tasks such as intelligent perception, efficient control, and decision-making. However, WSN nodes are powere...

God-Level Data Science Machine Learning Full Stack Roadmap 2023

The‌ ‌Roadmap‌ ‌is‌ ‌divided‌ ‌into‌ ‌16 ‌Sections‌ Duration:‌ ‌256‌ ‌Hours‌ of Learning ‌(8 ‌Months)‌ ‌and many more hours for practice and project building. ‌ Month 1 — May ...

Machine Learning Engineers — What Do They Actually Do?

The title is a trick question, of course. Much like Data Scientist before it, the title Machine Learning Engineer is developing into a trend in the job market for people in our profession, but there is no consensus about the meaning of the title or the functions and skills it should encompass. I ima...

How far have we come with Wireless sensor networks part2(Machine Learning)

Abstract : Wireless sensor networks (WSNs) are self-organizing monitoring networks with a large number of randomly deployed microsensor nodes to collect various physical information to realize tasks such as intelligent perception, efficient control, and decision-making. However, WSN nodes are powere...

How Brunn-Minkowski inequality is used in Machine Learning part3

Brunn-Minkowski inequality for θ-convolution bodies via Ball’s bodies(arXiv) Author : Brunn-Minkowski inequality for θ-convolution bodies via Ball’s bodies Abstract : We consider the problem of finding the best function φn:[0,1]→R such that for any pair of...

Working with Mutual Information Estimation part8(Machine Learning)

Abstract : Channel capacity plays a crucial role in the development of modern communication systems as it represents the maximum rate at which information can be reliably transmitted over a communication channel. Nevertheless, for the majority of channels, finding a closed-form capacity expression r...

Mastering Monte Carlo: How to Simulate Your Way to Better Machine Learning Models

How a Scientist Playing Cards Forever Changed the Game of Statistics In the tumultuous year of 1945, as the world was gripped by what would be the final throes of World War II, a game of solitaire quietly sparked an advancement in the realm of computation. This was no ordinary game, mind you, but...

Working with Delaunay Complex part3(Machine Learning)

Abstract : We give sufficient conditions for a discrete set of points in any dimensional real hyperbolic space to have positive anchored expansion. The first condition is a bounded mean density property, ensuring not too many points can accumulate in large regions. The second is a bounded mean vacan...

Automated Feature Selection for Machine Learning in Python

Feature selection is the process of identifying the most important and informative features within a dataset. It is one of the most important steps of machine learning modeling pipeline, since it has significant impact on model performance and its predictive power. Simple Visualization of Fea...

Learning Python Pandas Library: A Comprehensive Guide with Code Examples

Python’s Pandas library is a powerful tool for data manipulation and analysis. It provides data structures and functions to efficiently manipulate large datasets and perform various tasks like cleaning, transforming, and analyzing data. Whether you’re a beginner or an experienced program...

Monitoring Machine Learning Models in Production: Why and How?

Machine Learning (ML) model development often takes time and requires technical expertise. As data science enthusiasts, when we acquire a dataset to explore and analyze, we eagerly train and validate it using diverse state-of-the-art models or employing data-centric strategies. It fee...

How I Deployed a Machine Learning Model for the First Time

Introduction For as long as I’ve started with machine learning, Jupyter Notebooks have been my most loyal sidekick. From data preprocessing to model training, fine-tuning, and testing, Jupyter Notebooks have been there at every step to support me. However, I always knew that there is an ent...

Dynamic Pricing with Reinforcement Learning from Scratch: Q-Learning

1. Introduction In this post, we introduce the core concepts of Reinforcement Learning and dive into Q-Learning, an approach that empowers intelligent agents to learn optimal policies by making informed decisions based on rewards and experiences. We also share a practical Python example built ...

Machine Learning in Your Browser

If you’re working in IT, you have said the magic seven letters ChatGPT at least once in the last few months and you’ll probably remember at least one news story revolving around AI. It’s probably the hype topic of the century. Today, I want to show you an often overlooked aspect. ...

Machine Learning Engineers — What Do They Actually Do?

The title is a trick question, of course. Much like Data Scientist before it, the title Machine Learning Engineer is developing into a trend in the job market for people in our profession, but there is no consensus about the meaning of the title or the functions and skills it should encompass. I ima...

Machine Learning Interview Questions 2023

As per my recent Interview experience I have created a list of questions on various Machine Learning Sections. This list will comprise of just questions, I am planning to write a separate blog post for all the answers. Machine Learning Interview Questions What is Regression? What are ...

Mastering Monte Carlo: How to Simulate Your Way to Better Machine Learning Models

How a Scientist Playing Cards Forever Changed the Game of Statistics In the tumultuous year of 1945, as the world was gripped by what would be the final throes of World War II, a game of solitaire quietly sparked an advancement in the realm of computation. This was no ordinary game, mind you, but...

Machine Learning with Expert Models: A Primer

Expert models are one of the most useful inventions in Machine Learning, yet they hardly receive as much attention as they deserve. In fact, expert modeling does not only allow us to train neural networks that are “outrageously large” (more on that later), they also allow us to build mod...

God-Level Data Science Machine Learning Full Stack Roadmap 2023

The‌ ‌Roadmap‌ ‌is‌ ‌divided‌ ‌into‌ ‌16 ‌Sections‌ Duration:‌ ‌256‌ ‌Hours‌ of Learning ‌(8 ‌Months)‌ ‌and many more hours for practice and project building. ‌ Month 1 — May ...

How You Should Validate Machine Learning Models

Large language models have already transformed the data science industry in a major way. One of the biggest advantages is the fact that for most applications, they can be used as is — we don’t have to train them ourselves. This requires us to reexamine some of the common assumptions abou...

Efficient Deep Learning: Unleashing the Power of Model Compression

Introduction When a Machine Learning model is deployed into production there are often requirements to be met that are not taken into account in a prototyping phase of the model. For example, the model in production will have to handle lots of requests from different users running the product. So...

Machine Learning in a Non-Euclidean Space

What you will learn in this article. 1. There are different examples of non-Euclidean geometry, among them spherical geometry and hyperbolic geometry. 2. A hyperbolic space is a space of negative constant curvature. 3. There are different models of hyperbolic geometry, t...

Operator Learning via Physics-Informed DeepONet: Let’s Implement It From Scratch

Ordinary and partial differential equations (ODEs/PDEs) are the backbone of many disciplines in science and engineering, from physics and biology to economics and climate science. They are fundamental tools used to describe physical systems and processes, capturing the continuous change of quantitie...

Machine Learning Made Intuitive

What is Machine Learning? Sure, the actual theory behind models like ChatGPT is admittedly very difficult, but the underlying intuition behind Machine Learning (ML) is, well, intuitive! So, what is ML? Machine Learning allows computers to learn using data. But what does this mean? How d...

10 Most Common Machine Learning Algorithms Explained -2023

1. Linear Regression Linear regression is a statistical method used to examine the relationship between two continuous variables: one independent variable and one dependent variable. The goal of linear regression is to find the best-fitting line through a set of data points, which can then be use...

Best Research of Arborescences part2(Machine Learning + Graph Theory)

Abstract : An arborescence, which is a directed analogue of a spanning tree in an undirected graph, is one of the most fundamental combinatorial objects in a digraph. In this paper, we study arborescences in digraphs from the viewpoint of combinatorial reconfiguration, which is the field where we st...

Building Real-time Machine Learning Foundations at Lyft

In early 2022, Lyft already had a comprehensive Machine Learning Platform called LyftLearn composed of model serving, training, CI/CD, feature serving, and model monitoring systems. On the real-time front, LyftLearn supported real-time inference and input feature validati...

Automatic Differentiation with Python and C++ for Deep Learning

This story explores automatic differentiation, a feature of modern Deep Learning frameworks that automatically calculates the parameter gradients during the training loop. The story introduces this technology in conjunction with practical examples using Python and C++. Figure 1: Coding A...

Mastering Design Principles for Machine Learning

Software design principles are general guides for developing clean, readable and maintainable code. Design principles are important because they provide best practices that help ensure that code can be easily understood, reused, scaled and tested. Writing code without incorporating at least some of ...

Building a Trading Strategy with Machine Learning Models and Yahoo Finance in Python.

Developing a successful trading strategy requires a combination of market knowledge, technical analysis, and the ability to leverage data effectively. Machine learning models, coupled with financial data from sources like Yahoo Finance, offer a powerful approach to building robust trading strategies...

How to Design a Roadmap for a Machine Learning Project

What is the first thing you do when starting a new machine learning project? I’ve posed this question to a variety of ML leaders in startups and have received a few different answers. In no particular order: Try out one of our existing models to see if it works for the new task. Sta...

Inside GPT — I : Understanding the text generation

Regularly engaging with colleagues across diverse domains, I enjoy the challenge of conveying machine learning concepts to people who have little to no background in data science. Here, I attempt to explain how GPT is wired in simple terms, only this time in written form. Behind ChatGPT’s p...

Machine Learning with Expert Models: A Primer

Expert models are one of the most useful inventions in Machine Learning, yet they hardly receive as much attention as they deserve. In fact, expert modeling does not only allow us to train neural networks that are “outrageously large” (more on that later), they also allow us to build mod...

Streamlining Machine Learning with the caret Package in R

In the rapidly evolving world of data science and machine learning, efficiency and simplicity are paramount. Developers and data scientists often seek tools that can streamline complex tasks, enabling them to focus on the core aspects of their projects. One such tool in the realm of R programming is...

A Roadmap to Become a Machine Learning Engineer

As a Machine Learning Engineer, I remember feeling uncertain about the path ahead when I first started out. Back then, I had no idea that the title “Machine Learning Engineer” even existed when I was working on my Text-to-Speech study for my Bachelor’s thesis. But it has become a p...

Machine Learning Engineers — what do they actually do?

The title is a trick question, of course. Much like Data Scientist before it, the title Machine Learning Engineer is developing into a trend in the job market for people in our profession, but there is no consensus about the meaning of the title or the functions and skills it should encompass. I ima...

Research based on Metric Measure Spaces in Machine Learning part4

Assume that (X,d,μ) is a metric space endowed with a non-negative Borel measure μ satisfying the doubling condition and the additional condition that μ(B(x,r))≳rn for any x∈X,r>0 and some n≥1. Let L be a non-negative self-adjoint operator on L2(X,μ). We assume that e−t...

Churn Prediction With Machine Learning

A complete work in data science, through exploratory analysis, feature engineering techniques, model selection and model creation of predictive machine learning and hyperparameter tuning. Photo by Markus Winkler on Unsplash Churn rate, also known as customer attrition or cus...

Mastering Monte Carlo: How To Simulate Your Way to Better Machine Learning Models

In the tumultuous year of 1945, as the world was gripped by what would be the final throes of World War II, a game of solitaire quietly sparked an advancement in the realm of computation. This was no ordinary game, mind you, but one that would lead to the birth of the Monte Carlo method(1). The play...

Quick Midjourney Update: 4 key highlights to know

There was no Office Hours event on 30th August 2023. Here’s a quick rundown of the most recent Midjourney Weekly Office Hours in the first week of September: (1) Upcoming web releases There will be two release phases to ensure stability before introducing several new features. Th...

Advanced AI Training — Deep Intro to Graph Neural Nets GNN

eXacognition AI has released on their Youtube channel the next session video in the Deep Intro to AI Bootcamp series of introductory AI training presentations on advanced Artificial Intelligence design that I created & presented earlier this year to their client base. I personally perceive Gr...

How Quasiconvexity works part7(Machine Learning)

We prove homogenization for a class of viscous Hamilton-Jacobi equations in the stationary and ergodic setting in one space dimension. Our assumptions include most notably the following: the Hamiltonian is of the form G(p)+βV(x,ω), the function G is coercive and strictly quasiconvex, minG...

Machine Learning in a Non-Euclidean Space

What you will learn in this article. 1. There are different examples of non-Euclidean geometry, among them spherical geometry and hyperbolic geometry. 2. A hyperbolic space is a space of negative constant curvature. 3. There are different models of hyperbolic geometry, t...

How Quasiconvexity works part8(Machine Learning)

We establish that for any non-empty, compact set K⊂R3×3sym the 1- and ∞-symmetric div-quasiconvex hulls K(1) and K(∞) coincide. This settles a conjecture in a recent work of Conti, Müller and Ortiz (Symmetric Div-Quasiconvexity and the Relaxation of Static Problems. Arch. ...

Why Does All AI Art Look Like That?

Way back in the 1990s, I went to Art School. It was challenging, fun, and informative and among many of the memories I have from the time, one stands out with regard to the ongoing discussion about AI-generated art. Life Drawing was one of the first classes all first-semester students had to ...

How Quasiconvexity works part3 Machine Learning

We introduce a notion of convexity with respect to a one-dimensional operator and with this notion find a one-parameter family of different convexities that interpolates between classical convexity and quasiconvexity. We show that, for this interpolation family, the convex envelope of a continuous b...

How Quasiconvexity works part4(Machine Learning)

for a new class of costs c(x,y) for which we introduce a tentative notion of twist condition. In particular we study the conditions under which the infinitely-motonone minimizers are induced by a transportation map. We also state a uniqueness result for infinitely cyclically monotone Monge minimizer...

How Quasiconvexity works part1(Machine Learning)

Let X be a metric space and BCl(X) the collection of its bounded closed subsets as a metric space with respect to Hausdorff distance (and call BCl(X) the bounded-subset space of X). The question of whether or not one can characterize (the existence of) a rectifiable path in some subspace J of BCl(X)...

How to Crack Machine learning Interviews at FAANG!

Cracking a machine learning interview at companies like Facebook, Google, Netflix, Snap etc. really comes down to nailing few patterns that these companies look for. In this article, I plan to share my experience interviewing with these companies and also how I went about preparing. About me: ...

Why you should start studying Quantum Machine Learning

In the last few months I have been thinking about career and future and that many tools that I currently work with nowadays did not exist 10 years ago, and then I thought: how things are going to be in 10 years from now? Well, the most honest answer is I don’t know, but I can try and make a gu...

A Guide to Real-World Data Collection for Machine Learning

Whether you’re brand new to data science or the Chief Data Scientist at a large organization, you’ve probably played with perfectly crafted data sets to solve toy machine learning problems. Maybe you’ve used K-Means clustering to predict flower species in the Iris data se...

Deep Learning Roadmap with Python

Machine learning is a good approach for small and medium datasets. But, when it comes to analyzing big data, this approach is unsuccessful. I learned machine learning techniques easily, but when performing deep learning projects, there are many challenges, especially for beginners. This blog will...

Monte Carlo Approximation Methods: Which one should you choose and when?

  Since deterministic inference is often intractable with probabilistic models as we saw just now, we now turn to approximation methods based on numerical sampling, which are known as Monte Carlo techniques. The key question we will look at with these methods is computing the expec...

Enhancing Machine Learning Projects: Strategies for Effective Data Handling and Model Performance

Machine learning has revolutionized numerous industries, from finance to healthcare, by enabling the development of intelligent systems capable of making predictions and decisions based on data. However, the success of machine learning projects relies heavily on the proper handling of data and the a...

MLOPS and Azure Machine Learning Service

As a data engineer on Azure who works closely with data scientists and in data science projects, it’s my job to find and deploy the best tools for machine learning projects. Data science happens in notebooks, starts with a small idea and over the years has become more easy to use than ever bef...

Predicting NBA Salaries with Machine Learning

The NBA stands out as one of the most lucrative and competitive leagues in sports. In the last few years, the salaries of NBA players have been on an ascending trend, but behind every awe-inspiring dunk and three-pointer lies a complex web of factors that determine thes...

The Golden Age of Open Source in AI Is Coming to an End

I joined the Google Brain team in 2015 right as TensorFlow was open sourced. Contrary to popular belief, TensorFlow was not the secret sauce behind Google’s success at that point in time. Only a handful of researchers had used it, and it took several years before it transformed ...

Using Minkowski functionals in Machine Learning research

The study of the angular power spectrum of Cosmic Microwave Background (CMB) anisotropies, both in intensity and in polarisation, has led to the tightest constraints on cosmological parameters. However, this statistical quantity is not sensitive to any deviation from Gaussianity and statistical isot...

How to Debug a Machine Learning Model: My Experience with LSTMs as an Example

In machine learning, building a model is just one part of the puzzle. Some basic models are pre-constructed, but the real challenge often arises when a model doesn’t perform as expected. There might be issues with accuracy, or perhaps the model doesn’t handle unseen data well. Debugging ...

Deep Learning and Stock Time Series Data

Time series data is extremely prevalent in modern data science practice. One of the most visible examples of this is stock data, a time series that drives a great deal of modern economic life. In this post, we’re going to attempt to train a univariate deep learning model on time series and see...

How Banach space-valued functions are used in Machine Learning part3

We present a generalization of the Radon-Riesz property to sequences of continuous functions with values in uniformly convex and uniformly smooth Banach spaces. 2. On p-Dunford integrable functions with values in Banach spaces(arXiv)   Abstract : Let (Ω,Σ,μ) be a complet...

Can you learn machine learning in a year?

This post is for anyone considering a career move into the field of machine learning. Of course, the answer to the titular question is “it depends”. But what does it depend on, exactly? Rather than try and give some generic answer to the question that suits no one in particular, I ...

Machine Learning for Fraud Detection in Streaming Services

Streaming services serve content to millions of users all over the world. These services allow users to stream or download content across a broad category of devices including mobile phones, laptops, and televisions. However, some restrictions are in place, such as the number of active devices, the ...

ML Concept Ensemble Learning I — Bagging & Random Forest

This article aims to examine the fundamental concepts of Ensemble Learning, a subset of machine learning methods that have gained widespread use worldwide. We will also introduce the common types of Ensemble Learning. However, due to the diverse nature of Ensemble Learning, we will break down the ...

A Keyframe-style Learning Rate Scheduler for PyTorch

It struck me one day that defining how a learning rate should change over the course of a training run is similar to defining an animation, with a combination of: Key frames: at timestep x the value should be y Transitions: how to interpolate values between timesteps So, I’ve crea...

Structuring Your Machine Learning Project with MLOps in Mind

If you’re looking to take your machine learning projects to the next level, MLOps is an essential part of the process. In this article, we’ll provide you with a practical tutorial on how to structure your projects for MLOps, using the classic handwritten digit classification problem as a...

Deploy Machine Learning Models Right From Your Jupyter Notebook

Amidst this AI revolution, building intelligent systems at scale has been of great interest lately to countless organizations. While plenty of time and energy is being actively spent in training large machine learning models, taking these models to production and maintaining them is a task of its...

Kaggle competition: Predicting Sale Price of Corporación Favorita using Machine Learning

Whether you are a beginner or a professional working in Data Science, do yourself a favor and take part occasionally in competitions that resonate with your interests. If you are interested in machine learning, text analysis, exploratory analysis and more, consider showcasing your skills, ideas. Thi...

Fake News Detector: Combating Misinformation with Machine Learning

In the age of the internet, information flows faster than ever before. News travels at the speed of light, transcending borders and barriers. Yet, amidst this whirlwind of connectivity, a troubling phenomenon has emerged — a shadowy underworld of fake news, misinformation, and sensationalism. ...

Unlocking the Power of Quantum Machine Learning: A Beginner’s Guide

Imagine a world where the limitations of classical physics do not bind computers. Instead, they harness the mind-bending properties of quantum mechanics. A world where machines can process information and solve complex problems unimaginably. This is the world of Quantum Machine Learning. From fin...

How Quasiconformal mapping is used in Machine Learning part5

We define Hardy spaces Hp, 0<p<∞, for quasiconformal mappings on the Korányi unit ball B in the first Heisenberg group H1. Our definition is stated in terms of the Heisenberg polar coordinates introduced by Korányi and Reimann, and Balogh and Tyson. First, we prove the exis...

GPT-4: 8 Models in One ; The Secret is Out

The GPT4 model has been THE groundbreaking model so far, available to the general public either for free or through their commercial portal (for public beta use). It has worked wonders in igniting new project ideas and use-cases for many entrepreneurs but the secrecy about the number of parameters a...

Simplify Your Machine Learning Projects

Many businesses are eager to adopt machine learning to improve their products and services. However, many data scientists get too caught up in creating the perfect model and using state of the art techniques. By doing this, they forget the most important thing: delivering a functional minimum viable...

Value Your Password

Ever have trouble remembering all your pin numbers and passwords? Well, imagine if you were the guy that forgot the password to an account that held $220m? That's what has happened to a San Fransisco man who wrote the password of his bitcoin account on a piece of paper. Oh yeah - you ...

Stop wasting times to learn Machine Learning! Read this instead!

Welcome to Machine Learning Tutorial. In this tutorial, we will do basic Machine Learning operations, starting with loading Python’s built-in data set to build svm with Iris Dataset. Machine Learning — First steps -Image by Author At the end of the article, you will see the qui...

The problem with anthropomorphizing algorithms

More and more people are using generative algorithms for a growing number of tasks, whether for text or image generation. OpenAI’s decision to apply the classic Silicon Valley philosophy of “move fast and break things” to machine learning and bring to market an unfinished prod...

All Languages Are NOT Created (Tokenized) Equal

Large language models such as ChatGPT process and generate text sequences by first splitting the text into smaller units called tokens. In the image below, each colored block represents a unique token. Short or common words such as “you”, “say”, “loud”, and &...

The Art of Prompt Design: Prompt Boundaries and Token Healing

This (written jointly with Marco Tulio Ribeiro) is part 2 of a series on the art of prompt design (part 1 here), where we talk about controlling large language models (LLMs) with guidance. In this post, we’ll discuss how the greedy tokenization methods used by langu...

Graph Machine Learning @ ICML 2023

We presented GraphGPS about a year ago and it is pleasing to see many ICML papers building upon our framework and expanding GT capabilities even further. Exphormer by Shirzad, Velingker, Venkatachalam et al adds a missing piece of graph-motivated sparse attention to ...

Let’s be clear about what Geoffrey Hinton is saying about deep learning

Geoffrey Hinton, considered by some the godfather of AI for his work in the field of deep learning, is leaving Google after ten years in order to warn about the dangers of the technology. His departure has strengthened the campaign, as did the open letter from a group of research...

Predicting Stock Prices with Machine Learning

In the world of finance, predicting stock prices has always been a challenge that captures the imagination of investors, researchers, and data scientists alike. The ability to anticipate future price movements could potentially lead to significant gains, but it’s no secret that the stock marke...

Dynamic Pricing using Machine Learning

Have you ever looked up a plane ticket, and decided to buy later, only to come back and see the price has gone up a few hundred dollars? Have you ever experienced the same with concerts, hotels, or games? Have you ever thought about why Uber ride costs vary day to day? All of the above i...

Machine Learning Introduction

Corpus is the collection of our whole data X based on which our model will calculate to give out some data Y. When our model gives out some output Y based on the data stored in corpus as X is called Machine Learning, where we generally teach our model to give some output based on a lot of data fe...

The AI Brillo Box: End of Art Redefined in the Machine Learning Era

Arthur C. Danto, the philosopher and art critic celebrated for his avant-garde thought, ushered in a new perspective on art, one that finds resonance in the era of generative AI art. His redefinition of art, centered on collective acceptance rather than intrinsic aesthetic qualities, set the stage f...

Dr. Andrew Ng’s Significant Contributions to Machine Learning

Dr. Andrew Ng is a name that resonates profoundly within the machine learning community. His work has been instrumental in shaping the trajectory of the field, and his influence is evident in both academic and industrial circles. Delving into the depth of his contributions, one can appreciate the ma...

How to create a transfer learning model

In convolutional neural networks, to reach the best accuracy and generalization ability, we need to test many experiments, adding layers or hidden units and so on. Sometimes it will take a lot of time and it can be just a random guess. But one thing is for sure, neural network&nbsp...

Building an End-to-End Machine Learning Pipeline

You know, anyone can build a machine learning model these days. We’ve seen them springing up like mushrooms after the rain — predicting everything from stock prices to the next hit song on the radio. But today, we’re diving into something different, something that’s like the ...

MLOps: Bridging the Gap Between Machine Learning and Operations

In an era defined on innovation with a trends for data driven technologies, machine learning deployment into production ready to use interface become a worldwide business concern. In this landscape MLOps bridge the gap between ML lifecycle and deployment on devices ( web, mobiles, etc ) offering ...

How Bayesian Estimation works in different domains part2(Machine Learning)

In an earlier work, we demonstrated the effectiveness of Bayesian neural networks in estimating the missing line-of-sight velocities of Gaia stars, and published an accompanying catalogue of blind predictions for the line-of-sight velocities of stars in Gaia DR3. These were not merely point predicti...

XGBoost Algorithm in Machine Learning

XGBoost is a versatile machine learning algorithm that finds applications in a wide range of domains. Some of its common uses and applications: Classification: XGBoost is often employed for classification tasks, such as spam detection, image recognition, fraud detection, and sentiment analysis...

Graph Machine Learning

We presented GraphGPS about a year ago and it is pleasing to see many ICML papers building upon our framework and expanding GT capabilities even further.  Exphormer by Shirzad, Velingker, Venkatachalam et al adds a missing piece of graph-motivated sparse attenti...

Machine Learning System Design: Ad click prediction

Develop a machine learning model to forecast the likelihood of an ad receiving clicks. Before progressing, it’s crucial to grasp the nuances of the ad serving backdrop. Initially, the ad request traverses a waterfall model, wherein publishers endeavor to dispose of their inventory throu...

What Does It Really Mean for an Algorithm to Learn?

When one first encounters machine learning, one often rushes through algorithm after algorithm, technique after technique, equation after equation. But it is afterwards that one can reflect on the general trends across the knowledge that they have acquired. What it means to ‘learn’ is...

One Secret to Happiness; Learning to Want What You Already Have

The one thought that scares me more than losing my own life is the thought of losing someone close to me. Yet, that is precisely the frightening reality I confronted when my wife of thirty years was diagnosed with a life-threatening heart condition. And it may be one of the best things that ever ...

Learning to play Mahjong: Lessons in Life, Loss, and Friendship

“You are playing what? Mahjong? Since when are you an old Jewish woman?” My best friend Elaine laughs when I call her three months after moving south to tell her I am learning to play mahjong. I tell Elaine I am just trying to meet people. I don’t tell Elaine how much I miss wal...

Learning to play Mahjong: Lessons in Life, Loss, and Friendship

“You are playing what? Mahjong? Since when are you an old Jewish woman?” My best friend Elaine laughs when I call her three months after moving south to tell her I am learning to play mahjong. I tell Elaine I am just trying to meet people. I don’t tell Elaine how much I miss wal...

Discover the Secrets to Lifelong Learning (Backed by Science)

Curiosity is an important aspect of learning. One piece of advice I hear too often is to question everything. But is the advice to always question things really all we need? To me, it feels like a common saying, similar to “don’t compare yourself with others,” which might sound ...

Learning Styles Are A Myth

I first encountered learning styles theory when I was taking a psychology class in college. We all took a quiz to determine our learning style; I was informed that, because I fidgeted a lot, liked to play sports, and favored learning through active participation, I was a kinesthetic learner. As s...

The Learning Curve

It’s raining outside. I am listening to a song in a language I can’t understand. The leaves look heavy because of the raindrops which look like pieces of stars. I am trying to calm my nerves by writing my other escape apart from painting. The shadow of September is still with me. Soon...

Three Of My Most Valuable Life Lessons, But I am Still Learning

Some Things Are Learned The Hard Way Some life lessons are priceless. They come with pain. Unfortunately, this is the school of life. We learn by making mistakes. The good news is we generally avoid repeating the painful mistakes. We learn and move forward with a bit more wisdom under our belt. ...

Learning and Creating

Which do you prefer — learning or creating? Many consider themselves lifelong learners, but how many consider themselves lifelong creators? Let’s examine the differences to find what’s best for us to live a great life. Learning and creating Like many of you, learning has b...

Time Management and Prioritization Strategies: A Path to Purposeful Learning

The Art of Time Management Time is a finite resource, and managing it effectively is essential for successful selective learning. Here are some strategies to help you make the most of every moment: 1. Set Clear Goals: Define your learning objectives and break them down into manageable chunk...

Personalized Learning at Scale: The Power of AI-Powered Employee Training

AI-powered employee training is a rapidly growing trend in the corporate world, and for good reason. This type of training uses artificial intelligence to personalize the learning experience for each employee, providing them with tailored content and feedback that is designed to meet their specific ...

Learning the basics of input actions (Godot 4/C#)

Video games are a unique form of art because, among other things, they are an interactive medium. This means that a core feature of any game is handling user inputs, and reacting to the press of keys and buttons to trigger various actions in the game. And, to do this, a very common technique is t...

Building a Tic-Tac-Toe Game with Reinforcement Learning in Python: A Step-by-Step Tutorial

Welcome to this step-by-step tutorial on how to build a Tic-Tac-Toe game using reinforcement learning in Python. In this tutorial, we will learn how to create an agent that learns to play the game by trial and error, taking actions and receiving rewards or penalties depending on whether the action l...

Machine Learning is Fun! Part 2

Update: This article is part of a series. Check out the full series: Part 1, Part 2, Part 3, Part 4, Part 5, Part 6, Part 7 and Part 8! You can also read this article in Italiano, Español, Français, Türk&cc...

“Shall we play a game?”: A guide to AI Reinforcement Learning

It’s the early 90s, and as a child of that time, I’m wandering my sacred place, my temple — the local video store. Long before the world of streaming and internet-delivered media content, the video store was the launchpad for a child’s imagination. Rows and rows of pure ma...

Azure Databricks A-Z Complete Guide | Azure Dp 203 Databricks Learning Material

This article will provide readers with a comprehensive understanding of Azure Databricks, its architecture, cluster management, notebook usage, data access, secrets management, and securing access to Delta Lake, empowering them to make the most of this powerful platform for their data-related tasks....

#1 Learning how to do “O11Y”

Hy everbody, how are you? I hope well! Sure, I’ll start my first post so excited at focusy my improve skills, try times to build and running diverses evironmentes. In that’s post, I’ll Showing how I doed resolved challenge O11Y of the course Observability Fundamentals by O2B ...

Kotlin and Jetpack Compose Learning Resources.

Someone asked me Where to learn Kotlin and Jetpack Compose. Here some good resource to learn about Kotlin and Jetpack Compose. For Kotlin Resources are: On YouTube, you can watch CodeTutor, Kotlin by JetBrains, Philipp Lackner, Cheezy Code videos CodeTutor: Kotlin...

Setting Up an Android Request-Response Capture Environment | My Learning Journey | Part 1

As a student learning cybersecurity, I spent a lot of time performing practicals on web applications and Hack The Box machines. I believed a change and a challenge was needed. So, I decided to setup an environment where I could use an android device and capture the requests and responses. Thus, b...

Learning Tango in Buenos Aires

Today is the 26th September of 2020 in Buenos Aires. The city is still under grip of laws imposed by politicians, supposedly elected to maintain and advance welfare in the nation. It was the beginning of spring and the temperature was very comfortable, the morning rain had released all sorts of plea...

Learning to Say “I Love You”

The last time I was at a gathering of Monica’s friends, I noticed they stood together in four little groups — colleagues, neighbors, members of her Southside Baptist church, and those from her North Shore church. I knew no one. There was no easy explanation for how we’d met. ...

Working & Learning at the University of Edinburgh — Student Ambassador, Geologist, Red Lichtie

Inprevious blogs I covered studying course by course, since I came to the end of my education at the University, I shall cover what I learnt, year by year. I had a great time with the University where I learnt a lot about myself, about the rich world of geology and seen many pretty landscapes. Th...

MBP | CREATIVE LEARNING

Between the MBP team, we’ve tried and tested a whole lot of ways to keep learning while staying in and working from home. With the help of our MBPeep, Katy, we have put together our favourite learning outlets while keeping our creativity intact. BOOKS Reading is always food f...

Learning the Language of My New Life*

Let’s face it. Portuguese is not a beautiful language. It’s harsh sounding and choppy. On the contrary, the Italian language is so melodic and beautiful. I loved learning Italian as it just rolls off the tongue and you can easily convey your current mood by your tone. Portuguese is not l...

Learning Another Language When You’re Anglophone

I’m always learning different languages. A few years ago, when I left the military, I decided to try my hand at French. It was an easy decision for me. French, after all, a global language, spoken on practically every continent. I felt it would be just as practical a language to learn as well ...

Learning the city through its design code: Paris

It’s been more than a year since I landed at Charles de Gaulle airport, a huge brutalist concrete jungle that hardly brings you an idea you’re in the city called “the city of love”. Paris’ reputation is an absolutely extraordinary case — is there any other...

Unveiling a World of Creativity: Kidizens and the Lego Learning Odyssey

In the dynamic landscape of education, after-school programs have emerged as a cornerstone for shaping the holistic development of young minds. Kidizens, a pioneering educational platform, has carved a niche for itself with its innovative approach to learning through Lego-centric activities. As we e...

The Role of Machine Learning in Wildlife Conservation

Wildlife conservation is an essential undertaking that aims to preserve the diverse range of species and ecosystems found in nature, ensuring the protection of our planet. Conservationists have encountered increasingly difficult challenges over the years, primarily due to human activities, climate c...

“Mastering” Construction Management: My Journey through 5 Learning Paths and Exams with LinkedIn Learning

Amid the pandemic, I completed 5 learning paths and exams in Construction Management. Each learning path comprised approximately 8–10 courses, with each course containing about *8–10 videos*. While working with NLNG, I recognized the need to deepen my knowledge in Construc...

Breaking the ‘False Beginner’ Cycle Learning Arabic — How to Start Making Progress Again

You are a false beginner if you have ever studied a language at any point in time, have some linguistic knowledge, but cannot use the language. I recently published a post detailing an ever increasing situation holding UK Muslims back from enriching their lives learning Arabic (I sugges...

Why Western Muslims Stop Learning Arabic

I am a professional ‘false beginner’. A decade long career of course-hopping to be exact. The Collins dictionary describes a false beginner as “a language student who has some knowledge of a language, but who needs to start again from the beginnin...

I Turned My Life Around Thanks to Allah, Learning to Read, and Dr. Booker

My name is Carlos Marcell Jackson. I was incarcerated when I was 21 years old for aiding and abetting a murder. I’m now 39; I’ve been in federal prison 18 years. A staff member in one of the prisons told me once that I could have done something with my life, and I often think about wh...

Disability in institutions of higher learning.

Running during the third week of May 2016 Disability week was established by the Disability Committee, through the Office of Equity and Institutional Culture, this initiative was designed to create a space within the university that promotes awareness about disability and the challenges that face th...

Learning Linode

We had just submitted Our resignation with Ring, refusing to work for Amazon who had just acquired the company. We have a deep commitment to making people’s lives truly better, being supportive of them living whole, authentic lives, improving the systems in which they are r...

Diversity, Equity, Inclusion, and Belonging (DEI&B) as an Emotional Experience for Designing Learning Strategies

In certain leadership practices, positive emotions such as calmness, cheerfulness, attention, or enthusiasm are discussed for the benefit of developing interpersonal relationships and increasing job satisfaction and performance outcomes. The studies centered around emotio...

AI & Law: Overinterpretation By Machine Learning Produces Legal Nonsense

Perhaps you’ve had an occasion to be speaking with someone about a matter of the law and at one point either or both of you exclaimed that the underlying logic makes absolutely no legal sense. We usually expect that any serious legal matter ought to ultimately be rooted in something legally...

What I Believe About Teaching and Learning

This school year has felt like an emotional roller coaster. Every school year does, but something about this year has made the highs and lows feel more extreme. I have felt more doubt and frustration about my teaching, and the educational system in general, than I can remember feeling before. I&r...

Do Certificate Programs Pay Off? Top SCM certifications. Free certificate programs for anyone who has access to LinkedIn Learning…

From Forbes: Do Certificate Programs Pay Off? Top SCM certifications: Free certificate programs for anyone who has access to LinkedIn Learning (thank you Mr. Dan Stanton): The WMU Supply Chain Graduate Certificate program is now up and accepting students. Information can be found here: ...

Possibilities of Machine Learning in Logistics

Inrecent years, machine learning (ML) has revolutionized various industries, and logistics is no exception. The integration of AI and ML technologies has unlocked a myriad of possibilities, reshaping the way goods are transported, managed, and delivered across the globe. This post aims to explore th...

A Beginner’s Guide to Reinforcement Learning and its Basic Implementation from Scratch

Let’s consider the analogy of teaching a dog new dog tricks. In this scenario, we emulate a situation and the dog tries to respond in different ways. If the dog’s response is a desired one, we reward it with dog food. Else, we convey in one way or the other that its response isn’t ...

Active Learning, Data Selection, Data Auto-Labeling, and Simulation in Autonomous Driving

Deep Learning is going to be in every module of the Self-Driving Car software stack. These deep learning models use data as their learning material, and the quality of the data they are trained on determines their performance. As a result, choosing the optimum training dataset is just as crucial as ...

Becoming a Self-Driving Car & Machine Learning Engineer

The past year has been quite a journey for me. A year ago I left my full-time job in computer chip design, to go “back to school” for a career change into machine learning. However, I didn’t go back to school in a traditional sense — I decided to pursue online education via U...

Simulating self-driving cars using Reinforcement learning

Despite the recent breakthroughs in AI and extraordinary efforts of many auto-making companies, fully autonomous cars are still out of reach except for some trial programs. Engineers and AI scientist have been developing prototypes to make self-driving more efficient and to outperform humans. Drivin...

Learning traditions

My experience as a Native American was shaped long before I was born. It began among the Cherokee and Kiowa tribes, into which my grandmother and grandfather were born, but it radically shifted when they were sent away from their families to government boarding schools. That is where they met. But i...

Unlearning My White Privilege Pt. 2 — “I want them to think I’m not ugly.”

As part of my ongoing learning experience I watched another fantastic documentary the other day. Where the documentarian allowed the students she interviewed to ask her and the crew questions before she asked them anything. It was quite telling and like the two “research experiments” ...

Machine Learning in Chemistry

the combination of machine learning and chemistry has made significant progress. Researchers are using advanced models like CNNs and RNNs for tasks such as creating new drugs, predicting toxicology, and modeling quantitative structure-activity relationships. The pursuit of models that are interpreta...

A Guide to Genetic ‘Learning’ Algorithms for Optimization

In a broader mathematical or computational perspective, an optimization problem is defined as a problem of finding the best solution from all feasible solutions. In terms of Machine Learning and Artificial Intelligence, two significant algorithms that perform these tasks are Reinforcement Learning a...

From Biological Learning to Artificial Neural Network: What’s Next?

Back in the beginning of the 21st century, when I studied for MBA at NYU Stern, one class I took was called Data Mining, which introduced many algorithms to “mine” the data, meaning to automatically find the meaning of the data for forecasts and decision making. The neural network was on...

Brain-Based Learning Strategies to Try in Your Classroom Today

Time has never been a particularly plentiful resource for educators — there’s so much content to cover, so many learners with such a variety of needs, and countless interruptions — that the oh-so-valuable deeply engaged learning time is always inevitably limited. In the face of lea...

Using Multi-Task and Ensemble Learning to Predict Alzheimer’s Cognitive Functioning

In this article, I’ll share a concrete example of when my cognitive science background enabled me to 1) develop innovative modeling approaches for a disorder that holds personal significance for me in the field of neuroscience and 2) forge unique connections that are often overlooked in conven...

How should we enable playful learning?

There’s an old wooden computer desk on our terrace at Comini. We had square holes cut out to put in two Ikea trays — I forget why. Those trays are no longer in, so what we have is a table with two large holes at the top and a small rectangular one at the back, the one used to pass wires ...

Use The Post-Processing Principle To Revolutionize Learning

The Essence of the Post-Processing Principle The Post-Processing Principle is straightforward yet profound. Millionaires globally have embraced it. They credit it with saving the brightest minds 10 hours of reading each week. Yet, these individuals learn more than 99% of people. This approach doe...

Calculus that every Machine Learning Engineer should know

Inthe world of Data Science, there is an important concept that make Machine Learning Model training with efficient and optimized way that will provide with high accuracy in making prediction or guess correct output by model. Yes, it is none other than Calculus. The ...

Understanding Backpropagation: The Engine Behind Neural Network Learning

In the realm of artificial intelligence and machine learning, neural networks have emerged as a dominant paradigm for solving complex tasks, from image recognition to natural language processing. At the heart of their success lies a fundamental algorithm known as backpropagation. Backpropagation is ...

Deep Learning in Geometry: Arclength Learning

In this current work, we address a fundamental question in the field of geometry where we aim to reconstruct a basic property using DNN. The simplest geometric object is a curve, and a simple metric to evaluate a curve is the length. There are many close form expressions for calculation of the lengt...

Why is statistics important in Data Science, Machine learning, and Analytics

In this article, I will attempt to explain why I believe it is essential for data science and machine learning enthusiasts to possess a deeper understanding of statistics. Looking deeper statistics is a form of mathematical analysis that employs multiple quantitative models to produce experimental d...

Gaussian Discriminant Analysis an example of Generative Learning Algorithms

Algorithms that model p(y|x) directly from the training set are called discriminative algorithms. There can be a different approach to the same problem, consider the same binary classification problem where we want learn to distinguish between two classes, class A (y=1) and class B (y=0) based...

Deep Learning Illustrated, Part 2: How Does a Neural Network Learn?

Let’s say we want to create a neural network that predicts the daily revenue of ice cream sales using the features temperature and day of the week. This is the training dataset we’re using: To build a neural network, as we learned in the previous article, we need to first decid...

Statistics you need to know to become a Data Analyst/Scientist

Confused about where to start when it comes to learning statistics for becoming a data scientist? I was too. Grabbing an old Math books to read topics like probability , statistics might help but how much? And what all topics do we need to go through? Here is a checklist for all the statistics topic...

About Train, Validation and Test Sets in Machine Learning

This is aimed to be a short primer for anyone who needs to know the difference between the various dataset splits while training Machine Learning models. For this article, I would quote the base definitions from Jason Brownlee’s excellent article on the same topic, it is quite com...

A Guide to Education and Learning in Fashion Design

Fashion design is more than just creating stylish clothing — it’s an art form that combines creativity, innovation, and technical skill to bring visions to life. Whether you’re an aspiring designer with a passion for style or someone looking to delve into the dynamic world of fashi...

How to Start Learning English

On the other hand, if you start by enrolling in an English school to learn English with a teacher, structure = disciplined learning, but the lack of flexibility may frustrate you. It is also not always effective to learn English in a classroom. I had “formally” studied Engli...

The Comprehensive Guide to Learning English in 2023

The number of English learners around the world is exploding. English is currently spoken by 1.75 billion people worldwide, one out of every four people on the planet, according to the British Council. The group estimates that by 2025, 2.2 billion people will use English daily. This growth is p...

How to Hack Learning French

“Why isn’t our French better?” a high school classmate of mine incredulously complained at a recent reunion. And another friend finds it frustrating that, “I got high marks in French all through school. Nothing less an A minus. But when I got out in the workforce...

A guide to learning French

Table of contents Who am I, and why am I authoring this article? Reason — why do you want to learn it? Important things to know about language learning. Important things to know about the French language. All-important resources when it comes to learning French. Learn More

Language Learning Tips to Speak Like a Native

I speak, read, and write four languages. Although two of them are pretty similar, their scripts are completely different. I learned all of those scripts in school. It is kind of a part of our culture. Today, I’m going to help you with your language-learning journey. The best tip I can give ...

The German Learning App That Changed My Learning Routine

Like many of you, I scrolled through app stores, looking for that perfect tool to make German less intimidating and more accessible. That’s when I stumbled upon Metkagram, and honestly, it’s been a game-changer in my language learning process. Let me share why Metkagram has become my go-...

A fantastic tip to make learning Chinese easy & fun!

Have you tried learning Mandarin from any other language besides English? While pinyin is the defacto phonetic system for foreigners to start speaking Mandarin fast, Hindi and other native Indian languages ranging from Tamil, Bengali, Malayalam and Marathi all make learning Mandarin pronunciations e...

Learning Telugu —interesting observations by a Hindi speaker

Recently, I developed interest in learning Telugu owing to my Telugu friend. I know Hindi and Punjabi (Punjabi is my mother tongue).While learning, I observed some interesting features of the Telugu language. Some of these features might be confusing for a Hindi speaking person. While learning a ...

Cantonese & Mandarin Learning — Jan

My first goal was simple and attainable so that I wouldn’t get overwhelmed and eventually do a bunch of nothing. I also mixed ways to incorporate Cantonese into my life, similar to the way English is, like news, media, and daily life. I was starting to get concerned at how empty my ticks lo...

Three Things You Should Know Before Learning Mandarin Chinese(English Ver.)

I met some students who just arrived in Taiwan. They had a specific purpose, which was to learn basic conversation in Chinese, for example, using Mandarin to buy food and have small talk to their Taiwanese friends. Some of my students told me s/he wants to get a job in the future so s/he made the ef...

Why I am learning Mandarin in 2024

In Malaysia, language is often politicised, and among the Chinese diaspora, it is no different. Malaysian Chinese folks are divided into “English-educated*” and “Chinese-educated” groups. (* English-educated can also mean that you went to a Malaysian national school, where...

The N Stages of Learning Chinese

Learning a language is a long and daunting task, no matter which language you choose to learn. They all have their own unique quirks, and their own unique stumbling blocks, that make the learning experience that little bit different for each. Chinese is, at the end of the day, just another langua...

What learning Mandarin taught me about not giving up

Learning Mandarin is difficult. After 90 hours worth of classes and nearly 2000 flashcards, I’m still struggling to even understand everyday real-life conversations. According to the Defense Language Institute (DLI), Mandarin ranks as a Level 4 foreign language, which means t...

What is Subliminal Learning?

In the world of personal development and self-improvement, subliminal learning has garnered significant attention. It is a technique that claims to harness the power of the subconscious mind to facilitate learning and behavior change. But what exactly is subliminal learning, and does it truly ...

5 Instagram accounts to follow if you’re learning Spanish

If you’re actively trying to improve your Spanish, getting a little bit of practice every day is an extremely effective way of doing that. For anyone who’s already in the habit of checking Instagram at least once a day, it’s a great place to get that regular Spanish fix, without ev...

The 9 Pillars of Learning Spanish on Your Own [Complete Guide]

Let’s be clear about one thing: I suck at languages. I am your typical 27-year-old American white dude: grew up in a single language household, didn’t try at Spanish AT ALL in school, went to college, got a job, and life went on in my monolingual world. Somewhere in there I fell in love ...