aks2203 / deep-thinkingLinks
A centralized place for deep thinking code and experiments
☆86Updated 2 years ago
Alternatives and similar repositories for deep-thinking
Users that are interested in deep-thinking are comparing it to the libraries listed below
Sorting:
- Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"☆59Updated 3 years ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated last year
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆37Updated 2 years ago
- Sparse and discrete interpretability tool for neural networks☆63Updated last year
- Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)☆62Updated 4 years ago
- ☆51Updated last year
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 2 years ago
- Data for "Datamodels: Predicting Predictions with Training Data"☆97Updated 2 years ago
- Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair☆48Updated last year
- Latest Weight Averaging (NeurIPS HITY 2022)☆31Updated 2 years ago
- ModelDiff: A Framework for Comparing Learning Algorithms☆59Updated 2 years ago
- ☆51Updated last year
- ☆55Updated last year
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆81Updated last year
- ☆60Updated 3 years ago
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆78Updated 3 years ago
- ☆95Updated 2 years ago
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated last year
- ☆70Updated 8 months ago
- ☆36Updated 3 years ago
- ☆56Updated 10 months ago
- ☆19Updated 3 years ago
- Meta-learning inductive biases in the form of useful conserved quantities.☆37Updated 2 years ago
- ☆26Updated 2 years ago
- ☆68Updated 2 years ago
- The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We s…☆67Updated 2 years ago
- ZeroC is a neuro-symbolic method that trained with elementary visual concepts and relations, can zero-shot recognize and acquire more com…☆32Updated 2 years ago
- ☆133Updated 4 years ago
- Understanding how features learned by neural networks evolve throughout training☆36Updated 10 months ago
- ☆45Updated last year