45 Open source projects that are alternatives of or similar to Remembering-for-the-Right-Reasons

Continual learning baselines and strategies from popular papers, using Avalanche. We include EWC, SI, GEM, AGEM, LwF, iCarl, GDumb, and other strategies.

PyTorch implementation of our Adam-NSCL algorithm from our CVPR2021 (oral) paper "Training Networks in Null Space for Continual Learning"

No description or website provided.

Class Normalization for Continual Zero-Shot Learning

Framework for Analysis of Class-Incremental Learning with 12 state-of-the-art methods and 3 baselines.

One Person, One Model, One World: Learning Continual User Representation without Forgetting

A pytorch compatible data loader to create sequence of tasks for Continual Learning

Steven C. Y. Hung, Cheng-Hao Tu, Cheng-En Wu, Chien-Hung Chen, Yi-Ming Chan, and Chu-Song Chen, "Compacting, Picking and Growing for Unforgetting Continual Learning," Thirty-third Conference on Neural Information Processing Systems, NeurIPS 2019

Repository containing code for the paper "Meta-Learning with Sparse Experience Replay for Lifelong Language Learning".

CVPR 2020 Continual Learning Challenge - Submit your CL algorithm today!

PyTorch implementation of our CVPR2021 (oral) paper "Prototype Augmentation and Self-Supervision for Incremental Learning"

Open-source code for our paper: Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition

In this work, we propose a deterministic version of Local Interpretable Model Agnostic Explanations (LIME) and the experimental results on three different medical datasets shows the superiority for Deterministic Local Interpretable Model-Agnostic Explanations (DLIME).

(RecSys 2020) Adaptively Distilled Exemplar Replay towards Continual Learning for Session-based Recommendation [Best Short Paper]

Data generator for Arena - interactive XAI dashboard

PyTorch code for NeurIPSW 2020 paper (4th Workshop on Meta-Learning) "Few-Shot Unsupervised Continual Learning through Meta-Examples"

Library implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AI

Life-Disciplines-Projects (LDP) is a life-management framework built within Obsidian. Feel free to transform it for your own personal needs.

Interesting resources related to Explainable Artificial Intelligence, Interpretable Machine Learning, Interactive Machine Learning, Human in Loop and Visual Analytics.

ExpMRC: Explainability Evaluation for Machine Reading Comprehension

Visualization tool for Graph Neural Networks

Adaptive, interpretable wavelets across domains (NeurIPS 2021)

Machine Learning in one line of code

What I consider the best practices for web and software development.

MindsDB server allows you to consume and expose MindsDB workflows, through http.

[ICLR 2022] Towards Continual Knowledge Learning of Language Models

AI Physicist, a paradigm with algorithms for learning theories from data, by Wu and Tegmark (2019)

lifelong learning: record and analysis of my knowledge structure

Meta-Learning through Hebbian Plasticity in Random Networks: https://arxiv.org/abs/2007.02686

AirLoop: Lifelong Loop Closure Detection

A curated list of awesome machine learning interpretability resources.

Fit interpretable models. Explain blackbox machine learning.

Sample use case for Xavier AI in Healthcare conference: https://www.xavierhealth.org/ai-summit-day2/

FairPut - Machine Learning Fairness Framework with LightGBM — Explainability, Robustness, Fairness (by @firmai)

Fast approximate Shapley values in R

Papers about explainability of GNNs

Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.

Model verification, validation, and error analysis

Techniques & resources for training interpretable ML models, explaining ML models, and debugging ML models.

The code of AAAI 2020 paper "Transparent Classification with Multilayer Logical Perceptrons and Random Binarization".

PyTorch implementation of a VAE-based generative classifier, as well as other class-incremental learning methods that do not store data (DGR, BI-R, EWC, SI, CWR, CWR+, AR1, the "labels trick", SLDA).

NMA deep learning course

Official Code Repository for "Gradient Projection Memory for Continual Learning"

Official code of CVPR 2021's PLOP: Learning without Forgetting for Continual Semantic Segmentation

Official Implementation of CVPR2021 paper: Continual Learning via Bit-Level Information Preserving