Highlights
- Pro
Stars
Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning
A PyTorch Library for Multi-Task Learning
Official PyTorch Implementation for Conflict-Averse Gradient Descent (CAGrad)
Code for "Gradient Surgery for Multi-Task Learning"
Awesome Multitask Learning Resources
Fast and flexible AutoML with learning guarantees.
Official PyTorch implementation for the paper "CARD: Classification and Regression Diffusion Models"
《Pytorch实用教程》(第二版)无论是零基础入门,还是CV、NLP、LLM项目应用,或是进阶工程化部署落地,在这里都有。相信在本书的帮助下,读者将能够轻松掌握 PyTorch 的使用,成为一名优秀的深度学习工程师。
Source code for Neural Information Processing Systems (NeurIPS) 2018 paper "Multi-Task Learning as Multi-Objective Optimization"
Learning Confidence for Out-of-Distribution Detection in Neural Networks
Experiments used in "Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning"
Demos demonstrating the difference between homoscedastic and heteroscedastic regression with dropout uncertainty.
Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more
[ICML 2020] Neural Architecture Distribution Search for Uncertainty Awareness
Uncertainty Quantification Neural Network from Similarity and Sensitivity
Reproduction of the paper: Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
Code for Mondrian Forests (for classification and regression)
DualAQD: Dual Accuracy-quality-driven Prediction Intervals
AM207 project: dissect aleatoric and epistemic uncertainty
Uncertainty estimation for anchor-based deep object detectors.