Beast code in Giters

xiaozhuang's repositories

MTG-Net

Efficient and Effective Multi-task Grouping via Meta Learning on Task Combinations part of Advances in Neural Information Processing Systems (NeurIPS) 2022.

Language:Jupyter Notebook10 10

alphafold

Open source code for AlphaFold.

Language:PythonApache-2.0000

BayesianLSTM_torch

This repository implements a custom Bayes Backprob LSTM cell with Pytorch(v1.3.1).

Language:Python010

BIG-bench

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

Language:PythonApache-2.0000

chemprop

Message Passing Neural Networks for Molecule Property Prediction

Language:PythonMIT000

deep-ensembles-uncertainty

My implementation of the paper "Simple and Scalable Predictive Uncertainty estimation using Deep Ensembles"

Language:PythonGPL-3.0000

Deep-Semi-Supervised-GPS-Transport-Mode

Language:Python000

FOST is a general forecasting tool, which demonstrate our experience and advanced technology in practical forecasting domains, including temporal, spatial-temporal and hierarchical forecasting. Current general forecasting tools (Gluon-TS by amazon, Prophet by facebook etc.) can not process and model structural graph data, especially in spatial domains, also those tools suffer from tradeoff between usability and accuracy. To address these challenges, we design and develop FOST and aims to empower engineers and data scientists to build high-accuracy and easy-usability forecasting tools.

Language:PythonMIT000