Meghan Heintz

Understanding AI applications in bio for machine learning engineers Meghan Heintz · Follow Published in Towards Data Science · 9 min read · 13 hours ago — Photo by Ousa Chea on Unsplash Anyone who has tried teaching a dog new tricks knows the basics of reinforcement learning. We can modify the dog’s behavior by repeatedly offering rewards for obedience and punishments for misbehavior. In reinforcement learning (RL), the dog would be an agent, exploring

Understanding AI applications in bio for machine learning engineers Meghan Heintz · Follow Published in Towards Data Science · 7 min read · 6 hours ago — Photo by Conny Schneider on Unsplash What do a network of financial transactions and a protein structure have in common? They’re both poorly modeled in Euclidean (x, y) space and require encoding complex, large, and heterogeneous graphs to truly grok. Left: image in Euclidean Space. Right: graph in

Exploring RAG techniques to improve retrieval accuracy Meghan Heintz · Follow Published in Towards Data Science · 5 min read · 2 days ago — Visualising AI project launched by Google DeepMind. From Unsplash image. First of all, do we still care about RAG (Retrieval Augmented Generation)? Gemini Pro can handle an astonishing 2M token context compared to the paltry 15k we were amazed by when GPT-3.5 landed. Does that mean we no longer care