Are all scalable objectives alike?
Published:
Tolstoy begins Anna Karenina with the claim that all happy families are alike. I propose an answer to the analogous question for learning objectives: are all scalable objectives somehow alike?
Posts by Category
blog
Constructive Self-Supervised Learning (Part 1): Designing generalisable deep self-supervision, and predicting lower-level abstractions for better semantics.
Published:
Contents
Thinking About a Bias for Better Semantic Coherence and Reuse
Published: