Name: Liang Ding
Type: User
Company: JD Explore Academy, JD.com Inc.
Bio: NLP/ML researcher (developing LLM and exploring its way to human-centric AGI).
Twitter: liangdingNLP
Location: Shanghai(CN) & Sydney(AU)
Blog: liamding.cc
Liang Ding's Projects
Machine Learning Algorithms (Julia)
lstm based model for kaggle pronunciation prediction
Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on Theano or TensorFlow.
NPI(Neural Programmer-Interpreters) implementation with Keras
A Neural Machine Translation implementation in Chainer
Transfer knowledge from a large DNN or an ensemble of DNNs into a small DNN
Language-agnostic BERT Sentence Embedding (LaBSE)
LAnguage Model Analysis
lamtram: A toolkit for neural language and translation modeling
Learning to Execute
Transparent deep learning in hundreds of lines of code.
《统计学习方法》的代码实现
致力于将李航博士《统计学习方法》一书中所有算法实现一遍
Papers & Works for large languange models (ChatGPT, GPT-3, Codex etc.).
lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch
Summary of Machine Learning: A Probabilistic Perspective book
coding for book 《ML》by lian
Fast Neural Machine Translation in C++
A masked language modeling objective to train a model to predict any subset of the target words, conditioned on both the input text and a partially masked target translation.
MASS: Masked Sequence to Sequence Pre-training for Language Generation
our team work,this model analysing wechat's moments' emotion and then caculating a value between [-50,50]
End-To-End Memory Networks in PyTorch
Meta Learning / Learning to Learn / One Shot Learning / Few Shot Learning
An open-source implementation of the AlphaGoZero algorithm
A Chinese Words Segmentation Tool Based on Bayes Model
Minimal and clean examples of machine learning algorithms
personal taste mobi books for kindle, mainly in Chinese version. welcome rp/ fork/ star ...