generalization

Everything about Transfer Learning and Domain Adaptation--迁移学习

Release of CIFAR-10.1, a new test set for CIFAR-10.

A Compositional Object-Based Approach to Learning Physical Dynamics

[ICML 2020] PyTorch Code for "One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control"

Generalized 3D Surface Descriptor (CVPR 2021)

A new test set for ImageNet

Javascript Generalized Parser Combinators

CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning

Official implementation of the NeurIPS'2020 paper 'Self-Adaptive Training: beyond Empirical Risk Minimization'

Interpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal Lifting

Implementation of the paper Recurrent Independent Mechanisms (https://arxiv.org/pdf/1909.10893.pdf)

PGDrive: an open-ended driving simulator with infinite scenes from procedural generation

Code for 3D Reconstruction of Novel Object Shapes from Single Images paper

Computing various norms/measures on over-parametrized neural networks

This repository contains code to replicate the experiments given in NeurIPS 2019 paper "One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers"

On the decision boundary of deep neural networks

Improving generalization by controlling label-noise information in neural network weights.

Awesome list for Neural Network Optimization methods.

Implements sharpness-aware minimization (https://arxiv.org/abs/2010.01412) in TensorFlow 2.

Winning Solution of the NeurIPS 2020 Competition on Predicting Generalization in Deep Learning

The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We significantly improve the systematic generalization of transformer models on a variety of datasets using simple tricks and careful considerations.

ML/DL/RL paper notes

Awesome Domain Adaptation Package Toolbox

Source code and dataset for the paper "On Robustness and Bias Analysis of BERT-based Relation Extraction"

CartAGen is a plugin for GeOxygene dedicated to cartographic generalisation

The official repository for our paper "Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks". We develop a method for analyzing emerging functional modularity in neural networks based on differentiable weight masks and use it to point out important issues in current-day neural networks.

generalize counter-examples of property-based testing

A study about the following problems: what is the memorization problem in meta-learning; why does memorization problem happen; and how to prevent it. (ICLR 2020)

Path-SGD: Path-Normalized Optimization in Deep Neural Networks

"Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics" by Wuyang Chen, Xinyu Gong, Yunchao Wei, Humphrey Shi, Zhicheng Yan, Yi Yang, and Zhangyang Wang