Benign Overfitting: A New Era for Linear Classifiers
Deep learning's peculiar ability to overfit yet generalize well is stirring up the world of linear classifiers. There's more than meets the eye.
Read the full articleYou might also wanna read
Proposal: Overparameterized Neural Networks with High Learning Rates Could Bridge AI-Human Intelligence Gap
Speculative proposal to create artificial neural nets with human-like performance by high-learning-rate/regularization training of overparam
gwern.net·1mo agoProposal: Overparameterized Neural Networks with High Learning Rates Could Bridge AI-Human Intelligence Gap
Speculative proposal to create artificial neural nets with human-like performance by high-learning-rate/regularization training of overparam
gwern.net·1mo agoThe Significance of Generalization in AI Systems and the Quest for Consciousness
This blog post outlines a key engineering principle I’ve come to believe strongly in for building general AI systems with deep learning. Thi
Theoretical Foundations of Deep Learning
Theoretical Foundations of Deep Learning
clcoding.com·25d agoHow Hyperscalers Are Hooked Into Generative AI
The recent OpenAI debacle highlighted the gamble cloud providers are making on key AI startups -- and how dependent they are on those compan
Visualizing piecewise linear neural networks
Neural networks are often thought of as opaque, black-box function approximators, but theoretical tools let us describe and visualize their
Deep Neural Networks Converge to Universal Low-Dimensional Subspaces Across Diverse Tasks
We show that deep neural networks trained across diverse tasks exhibit remarkably similar low-dimensional parametric subspaces. We provide t
arxiv.org·7mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.