199 Open source projects that are alternatives of or similar to knowledge-neurons

Pytorch code for ICRA'21 paper: "Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation"

Pytorch Implementation of GoEmotions 😍😢😱

Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" https://arxiv.org/abs/1909.13584

🏎️ Accelerate training and inference of 🤗 Transformers with easy to use hardware optimization tools

A Python multilingual toolkit for Sentiment Analysis and Social NLP tasks

Load What You Need: Smaller Multilingual Transformers for Pytorch and TensorFlow 2.0.

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.

Chef Transformer 🍲 .

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

Transformers Pipeline with KoELECTRA

Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.

This is the official implementation of TransCenter. The code and pretrained models are now available here: https://gitlab.inria.fr/yixu/TransCenter_official.

CINO: Pre-trained Language Models for Chinese Minority (少数民族语言预训练模型)

classy is a simple-to-use library for building high-performance Machine Learning models in NLP.

Bottleneck Transformers for Visual Recognition

An NLP-suite powered by deep learning

Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)

🏔️ Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations

A collection of Models, Datasets, DataModules, Callbacks, Metrics, Losses and Loggers to better integrate pytorch-lightning with transformers.

Official Code for "Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents"

A Framework for Textual Entailment based Zero Shot text classification

Multi-class text categorization using state-of-the-art pre-trained contextualized language models, e.g. BERT

Code snippets and solutions for the Introduction to Deep Learning and Neural Networks Course hosted in educative.io

ProtoTrees: Neural Prototype Trees for Interpretable Fine-grained Image Recognition, published at CVPR2021

This repository contains code for the O'Reilly Live Online Training for BERT

Contextualised Embeddings and Language Modelling using BERT and Friends using R

Global-Local Capsule Network (GLCapsNet) is a capsule-based architecture able to provide context-based eye fixation prediction for several autonomous driving scenarios, while offering interpretability both globally and locally.

Conversational text Analysis using various NLP techniques

[ICCV 2021] Official implementation of "Scalable Vision Transformers with Hierarchical Pooling"

Implementation of Uniformer, a simple attention and 3d convolutional net that achieved SOTA in a number of video classification tasks, debuted in ICLR 2022

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.

CLIP (Contrastive Language–Image Pre-training) for Italian

Active Learning for Text Classification in Python

Code for AAAI 2018 accepted paper: "Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients"

Source code for GNN-LSPE (Graph Neural Networks with Learnable Structural and Positional Representations), ICLR 2022

Code for "Distributed, Egocentric Representations of Graphs for Detecting Critical Structures" (ICML 2019)

Utility for analyzing Transformer based representations of language.

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

Compare neural networks by their feature similarity

Unofficial JAX implementations of deep learning research papers

Persian Bert For Long-Range Sequences

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

Universal 1d/2d data containers with Transformers functionality for data analysis.

Implementation of STAM (Space Time Attention Model), a pure and simple attention model that reaches SOTA for video classification

Implementation of N-Grammer, augmenting Transformers with latent n-grams, in Pytorch

NeurIPS 2018. Linear-time model comparison tests.

🛠️ Tools for Transformers compression using PyTorch Lightning ⚡

[AAAI 2022] This is the official PyTorch implementation of "Less is More: Pay Less Attention in Vision Transformers"

A collection of state-of-the-art algorithms for the training, serving and interpretation of Decision Forest models.

Abstractive and Extractive Text summarization using Transformers.

Implementation of Long-Short Transformer, combining local and global inductive biases for attention over long sequences, in Pytorch

Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval" https://arxiv.org/abs/2112.07577

Implementation of NÜWA, state of the art attention network for text to video synthesis, in Pytorch

DeepConsensus uses gap-aware sequence transformers to correct errors in Pacific Biosciences (PacBio) Circular Consensus Sequencing (CCS) data.

🌏 A zero-dependency networking solution for building modern and secure iOS, watchOS, macOS and tvOS applications.

An Open-Source Package for Chinese Open-domain Conversational Chatbot (中文闲聊对话系统，一键部署微信闲聊机器人)

Text2Text: Cross-lingual natural language processing and generation toolkit

[ECCV 2018] code for Choose Your Neuron: Incorporating Domain Knowledge Through Neuron Importance

Using pre-trained BERT models for Chinese and English NER with 🤗Transformers

Anonymization of legal cases (Fr) based on Flair embeddings