How to Design a Roadmap for a Machine Learning Project
<p>What is the first thing you do when starting a new machine learning project?</p>
<p>I’ve posed this question to a variety of ML leaders in startups and have received a few different answers. In no particular order:</p>
<ol>
<li>Try out one of our existing models to see if it works for the new task.</li>
<li>Start exploring and understanding the data.</li>
<li>Dig into the research literature to see what’s been done before.</li>
</ol>
<p>Notice that none of these first steps is to code and train a new model. And none is to design a data preprocessing pipeline.</p>
<p>Each of the three approaches has its merits. If the new project is quite similar to something that has previously been modeled (both the data and the task), trying out modeling approaches that have already been implemented can be a very quick way to establish a baseline for the task. In doing so, you may also discover new challenges that must be accommodated in data preprocessing or modeling.</p>
<p><strong>Visit Now</strong></p>