Mohammad Pezeshki

pytorch_forward_forward. Implementation of Hinton's forward-forward (FF) algorithm - an alternative to back-propagation

Associative_LSTM. LSTM with associative memory cells (http://arxiv.org/abs/1602.03032)

Recurrent-Neural-Networks. Recurrent Neural Network for modeling sequential data implemented using Python and Theano.

CTC-Connectionist-Temporal-Classification. Theano implementation of CTC.

Gradient_Starvation. Gradient Starvation: A Learning Proclivity in Neural Networks

Epoch_wise_Double_Descent. Official implementation of "Multi-scale Feature Learning Dynamics: Insights for Double Descent".

RNN_Experiments. General experiments on Vanilla RNN and LSTM in Theano.

LSTM_Dropout. Python

Theano_Tile_Coding. A tile coder in theano for Reinforcement Learning tasks

LSTM-Attention. LSTM-Attention

DeepLearningTutorials. Deep Learning Tutorial notes and code. See the wiki for more info.

CatsVSDogs. Kaggle Cats vs Dogs challenge for IFT6266

ladder_network. Implementation of "Ladder Network" using Blocks and Theano.

theano_alexnet. Theano-based Alexnet

Identity_RNN. RNN on MNIST (one pixel at a time) with Identity initialization

DAR. Deep Action Recognition

ofxTSNE. t-SNE dimensionality reduction technique for openFrameworks

mpezeshki.github.io. JavaScript

GAN-Nesterov-Training.

A-_Guide_-to_Data_Sciecne_from_mathematics. It is a blueprint to data science from the mathematics to algorithms. It is not completed.

draw. Reimplementation of DRAW

keras-GAN. Generative Adversarial Networks with Keras

ladder. Ladder network is a deep learning algorithm that combines supervised and unsupervised learning