Pinned Repositories
Active-Passive-Losses
[ICML2020] Normalized Loss Functions for Deep Learning with Noisy Labels
Attention-Advice
Transformers with learned advice vectors
awd-lstm-lm
LSTM and QRNN Language Model Toolkit for PyTorch
blockchain_video
COM 217 video presentation code for an explainer on how blockchain works using Manim
Citadel-Central-Datathon-Fall21
2nd place winning analysis of smoking data for the Citatdel Central Datathon of Fall 2021 (final report included)
DNI-RNN
Decoupled Neural Interfaces (Jaderberg et al. 2017) mini-package for easy integration with pytorch RNNs
LEAP
LEAP: Linear Explainable Attention in Parallel for causal language modeling with O(1) path length, and O(1) inference
Rethinking-Neural-Computation
Draft & experiments for an alternative approach to neuro-symbolic AI that allows for "thinking fast and slow"
Transformer-Trader
Investigation into whether Transformers and self-supervised learning could be used to trade currency markets
mtanghu's Repositories
mtanghu/LEAP
LEAP: Linear Explainable Attention in Parallel for causal language modeling with O(1) path length, and O(1) inference
mtanghu/Transformer-Trader
Investigation into whether Transformers and self-supervised learning could be used to trade currency markets
mtanghu/DNI-RNN
Decoupled Neural Interfaces (Jaderberg et al. 2017) mini-package for easy integration with pytorch RNNs
mtanghu/Active-Passive-Losses
[ICML2020] Normalized Loss Functions for Deep Learning with Noisy Labels
mtanghu/Attention-Advice
Transformers with learned advice vectors
mtanghu/awd-lstm-lm
LSTM and QRNN Language Model Toolkit for PyTorch
mtanghu/blockchain_video
COM 217 video presentation code for an explainer on how blockchain works using Manim
mtanghu/Citadel-Central-Datathon-Fall21
2nd place winning analysis of smoking data for the Citatdel Central Datathon of Fall 2021 (final report included)
mtanghu/datasets
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
mtanghu/Rethinking-Neural-Computation
Draft & experiments for an alternative approach to neuro-symbolic AI that allows for "thinking fast and slow"
mtanghu/URF
URF: Unsupervised Random Forest fork that uses scikit learn instead of pycluster for ~100x speed up
mtanghu/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
mtanghu/dni-pytorch
Decoupled Neural Interfaces using Synthetic Gradients for PyTorch
mtanghu/EconML
ALICE (Automated Learning and Intelligence for Causation and Economics) is a Microsoft Research project aimed at applying Artificial Intelligence concepts to economic decision making. One of its goals is to build a toolkit that combines state-of-the-art machine learning techniques with econometrics in order to bring automation to complex causal inference problems. To date, the ALICE Python SDK (econml) implements orthogonal machine learning algorithms such as the double machine learning work of Chernozhukov et al. This toolkit is designed to measure the causal effect of some treatment variable(s) t on an outcome variable y, controlling for a set of features x.
mtanghu/Fastformer
A pytorch &keras implementation and demo of Fastformer.
mtanghu/flash-attention
Fast and memory-efficient exact attention
mtanghu/flops-profiler
pytorch-profiler
mtanghu/hccpy
A Python implementation of Hierarchical Condition Categories
mtanghu/martingale
quick simulation to see how martingale betting would work with realistic conditions (i.e. finite but large money), as well as removing finite stopping condition
mtanghu/Mega-pytorch
Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena
mtanghu/parallelizing_linear_rnns
mtanghu/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
mtanghu/RWKV-CUDA
The CUDA version of the RWKV language model ( https://github.com/BlinkDL/RWKV-LM )
mtanghu/RWKV-LM
RWKV is a RNN with transformer-level performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
mtanghu/SGConv
mtanghu/smart-on-fhir-tutorial
SMART on FHIR developer tutorial
mtanghu/sru
Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)
mtanghu/tinygrad
You like pytorch? You like micrograd? You love tinygrad! ❤️