Implementation of the Deep Deterministic Policy Gradient (DDPG) using PyTorch
Multi-talker Speech Separation with LSTM/BLSTM by Permutation Invariant Training method.
Optimization algorithms for hybrid precoding in mmWave MIMO systems: Version 1.1.0
T. R. Halford and K. M. Chugg Matlab implementation for LDPC codes cycles of girth, girth+2, girth+4 counting
Rethinking the Value of Network Pruning (Pytorch) (ICLR 2019)
Variational Bayesian Monte Carlo (VBMC) algorithm for posterior and model inference in MATLAB
Neural network graphs and training metrics for PyTorch, Tensorflow, and Keras.
PyTorch0.4 implementation of: actor critic / proximal policy optimization / acer / ddpg / twin dueling ddpg / soft actor critic / generative adversarial imitation learning / hindsight experience replay