Stars
Code for Neural Arithmetic Units (ICLR) and Measuring Arithmetic Extrapolation Performance (SEDL|NeurIPS)
A pytorch port of google-research/google-research/robust_loss/
A Library for Advanced Deep Time Series Models.
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
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).
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
colinzhenli / Ca3DPose
Forked from 3dlg-hcvc/minsu3dCa3DPose:Canonical 3D Pose estimation via object-level classification method