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

In one of my previous <a href="https://medium.com/towards-data-science/why-my-cognitive-science-degree-was-a-great-foundation-for-data-science-and-machine-learning-f5838b527d40" rel="noopener">articles</a>, I detailed my experience of transitioning into machine learning from cognitive science and the imposter syndrome that taunted me. In that article, I mentioned: <blockquote> “An idea began to slowly unravel — perhaps, my background [in cognitive science] provided a much more solid foundation than I had initially anticipated”. </blockquote> 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 conventional discussions. Through this experience, it became evident to me that the field of deep learning, with all its potential, is still in its formative stages, serving as a reminder of the inclusive opportunities it offers to individuals from both traditional and non-traditional backgrounds. <h1>The Brain Networks Laboratory</h1> A lingering feeling that haunted me after completing my undergraduate degree was a sense of having a decent theoretical foundation but lacking the practical understanding to apply those tools effectively. I envisioned the ideal scenario where I could apply these tools within the space of neuroscience or mental health. <a href="https://towardsdatascience.com/using-multi-task-and-ensemble-learning-to-predict-alzheimers-cognitive-functioning-7b46fe09f9ff">Website</a>