curius graph

all pages

showing 80151-80200 of 203081 pages (sorted by popularity)
The Inside View
https://ruthcfong.github.io/projects/interactive_overlay/
Beyond interpretability: developing a language to shape our relationships with AI | by Been Kim | Medium | Medium
Puzzles of modern machine learning – Windows On Theory
COCO Attribute Dataset
BERT-base forward pass - Ana Marasović
A Tutorial on Structural Optimization
Legibility | Owen Lynch
Studying Growth with Cellular Automata
Differentiable Finite State Machines
Privacy and machine learning: two unexpected allies? | cleverhans-blog
AI-Written Critiques Help Humans Notice Flaws
leonidk/new_website: a fork of https://jonbarron.info/ for use in jekyll builds with markdown page updates
Causal confusion as an argument against the scaling hypothesis - AI Alignment Forum
Interpretability Creationism | Objective Funk
Personal Rules of Productive Research
Rethinking SGD’s noise – Machine Learning Research Blog
Epsilon-Nets and Computational Geometry - Springer-1993_1010079783642580437_4
Rewriting Geometric Rules of a GAN
[2206.10999] Neural Networks as Paths through the Space of Representations
On the Link Between Optimization and Polynomials, Part 5
[2205.15763] Exact Feature Collisions in Neural Networks
[2208.08831] Discovering Bugs in Vision Models using Off-the-shelf Image Generation and Captioning
CLIP Enrichment Circuits
Optimization Nuggets: Implicit Bias of Gradient-based Methods
[2206.13498] Auditing Visualizations: Transparency Methods Struggle to Detect Anomalous Behavior
Psychoceramics
Precision Loss in Transformers | aslvrstn.com
Five aphorisms on infinity – Axiom of Chance
Mechanistic Mode Connectivity | OpenReview
Linear Mode Connectivity of Deep Neural Networks via Permutation Invariance and Renormalization | OpenReview
Collective Intelligence for Deep Learning: A Survey of Recent Developments | 大トロ
Deep learning theory lecture notes
The sum of a geometric series is all you need! – Machine Learning Research Blog
Co-Founding Considered Harmful
Tidiane Thiam’s Spare and Beautiful ‘Siftorde’ Never Wastes a Sound | PopMatters
LLM.int8() and Emergent Features — Tim Dettmers
Seven Sins of Numerical Linear Algebra – Nick Higham
Programming by poking: why MIT stopped teaching SICP | posterior science
GD’s Implicit Bias on Separable Data
An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers — Neel Nanda
Landscape Connectivity of Low Cost Solutions for Multilayer Nets – Off the convex path
Sharing texts better, part 1: Austrian Newspapers
PhotoGuard: Defending Against Diffusion-based Image Manipulation – gradient science
Interpretability Creationism | Objective Funk
Tutorial #17: Transformers III Training - Borealis AI
The Use Case for Relative Position Embeddings – Ofir Press
Catherine Aiken's Testimony before the National Artificial Intelligence Advisory Committee - Center for Security and Emerging Technology
Announcing a New Course on the Science and Philosophy of Intelligence – Axiom of Chance
MagicMix: Semantic Mixing with Diffusion Models