huawei-noah/noah-research

Stars
855
Rank 52,898 (Top 2 %)
Language
Python
Created over 4 years ago
Updated 18 days ago

huawei-noah/noah-research

huawei-noah

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Noah Research

Noah Research

This repository contains some research related code released by Huawei Noah's Ark Lab.

About issue and PR

Because the repo contains many subprojects (each subproject corresponds to a directory), in order to clarify which subproject the issue or PR pionts to, please add the subproject name before its title.

Please refer to the following format:

'[' + subproject name + ']' + ' ' + title

An example is as follows:

[mRNN-mLSTM] This is the title of an issue of mRNN-mLSTM

Efficient-AI-Backbones

Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

HEBO

Bayesian optimisation & Reinforcement Learning library developped by Huawei Noah's Ark Lab

Jupyter Notebook

Pretrained-Language-Model

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

Efficient-Computing

Efficient computing methods developed by Huawei Noah's Ark Lab

Jupyter Notebook

AdderNet

Code for paper " AdderNet: Do We Really Need Multiplications in Deep Learning?"

trustworthyAI

Trustworthy AI related projects

SMARTS

Scalable Multi-Agent RL Training School for Autonomous Driving

bolt

Bolt is a deep learning library with high performance and heterogeneous flexibility.

vega

AutoML tools chain

VanillaNet

Speech-Backbones

This is the main repository of open-sourced speech technology by Huawei Noah's Ark Lab.

Jupyter Notebook

streamDM

Stream Data Mining Library for Spark Streaming

Pretrained-IPT

xingtian

xingtian is a componentized library for the development and verification of reinforcement learning algorithms

benchmark

Disout

Code for AAAI 2020 paper, Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks (Disout).

BGCN

A Tensorflow implementation of "Bayesian Graph Convolutional Neural Networks" (AAAI 2019).

BHT-ARIMA

Code for paper: Block Hankel Tensor ARIMA for Multiple Short Time Series Forecasting (AAAI-20)

multi_hyp_cc

[CVPR2020] A Multi-Hypothesis Approach to Color Constancy

Efficient-NLP

streamDM-Cpp

stream Machine Learning in C++

Federated-Learning