#representation-learning
4 posts · all tags
-
· What is Neural Collapse? A Simpler Look
Imagine you're training a very powerful neural network to recognize different classes of images, like cats, dogs, and cars. In the beginning, the network struggles, but eventually, it gets a perfect score on your training data.
-
· Scarf: Self Supervised Learning for Tabular Data
Machine learning often struggles with the scarcity of labeled data. While unlabeled datasets are abundant, obtaining high-quality labeled data remains expensive and time-consuming. SCARF emerges as a breakthrough methodology that transforms how we extract meaningful representations from raw, untagged information.
-
· The Platonic Representation Hypothesis: Are AI Models Converging on Universal Representations?
This blog post is based on The Platonic Representation Hypothesis by Huh et al. (2024), MIT. AI models are becoming increasingly similar in how they represent the world, regardless of how they're trained or what kind of data they process. This fascinating trend suggests we may be approaching a universal way of representing reality.
-
· Self Supervised Learning
This post is based on this blog post by meta Link to post.