Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

A Library for Advanced Deep Time Series Models.

PGPortfolio: Policy Gradient Portfolio, the source code of "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem"(https://arxiv.org/pdf/1706.10059.pdf).

A pytorch port of google-research/google-research/robust_loss/

Code for Neural Arithmetic Units (ICLR) and Measuring Arithmetic Extrapolation Performance (SEDL|NeurIPS)

Ca3DPose：Canonical 3D Pose estimation via object-level classification method