Soroush Mehri (soroushmehr)

soroushmehr

Geek Repo

Company:Microsoft Research Montreal (prev. MILA)

Location:Montreal

Github PK Tool:Github PK Tool


Organizations
Maluuba
mila-iqia
ezoic increase your site revenue

Soroush Mehri's repositories

sampleRNN_ICLR2017

SampleRNN: An Unconditional End-to-End Neural Audio Generation Model

Language:PythonLicense:MITStargazers:515Issues:25Issues:26
Language:PythonLicense:MITStargazers:0Issues:0Issues:0

ARS

An implementation of the Augmented Random Search algorithm

Language:PythonLicense:NOASSERTIONStargazers:0Issues:1Issues:0

awesome-research

:seedling: a curated list of tools to help you with research/life

Stargazers:0Issues:1Issues:0

bayou

System for synthesizing Java API idioms, powered by Neural Sketch Learning

Language:JavaLicense:Apache-2.0Stargazers:0Issues:2Issues:0

beta-tcvae

code for "Isolating Sources of Disentanglement in Variational Autoencoders".

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

coding-interview-university

A complete computer science study plan to become a software engineer.

License:CC-BY-SA-4.0Stargazers:0Issues:0Issues:0

cond-shift-neurons

Implementation of Conditionally Shifted Neurons by Munkhdalai et al. (https://arxiv.org/pdf/1712.09926.pdf)

Language:PythonStargazers:0Issues:3Issues:0

conll-2012

Reader for CoNLL-2012 using Ontonotes-5.0 documents

Stargazers:0Issues:0Issues:0

deep-subsets

Learning deep functions on sets for set2subset transformations

Language:PythonStargazers:0Issues:0Issues:0

Deep4Cast

Probabilistic Multivariate Time Series Forecast using Deep Learning

Language:PythonLicense:BSD-3-ClauseStargazers:0Issues:0Issues:0

diora

Deep Inside-Outside Recursive Autoencoder

Language:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0

DIP-VAE

An implementation of DIP-VAE from the paper "Variational Inference of Disentangled Latent Concepts from Unlabelled Observations" by Kumar et al. (Published at ICLR 2018) https://arxiv.org/abs/1711.00848

Language:PythonStargazers:0Issues:0Issues:0

fourier

An Interactive Introduction to Fourier Transforms

Language:Jupyter NotebookLicense:MITStargazers:0Issues:1Issues:0

Fractal-Megacollection

Wholesome collection of fractal types and coloring methods all in pixel shaders.

Language:ShaderLabLicense:MITStargazers:0Issues:1Issues:0

generating-neural-networks-with-neural-networks

Code that goes along with paper http://arxiv.org/abs/1801.01952

Language:PythonStargazers:0Issues:2Issues:0

generative-compression

TensorFlow Implementation of Generative Adversarial Networks for Extreme Learned Image Compression

Language:PythonLicense:MITStargazers:0Issues:2Issues:0

gym-sokoban

Sokoban environment for OpenAI Gym

Language:PythonLicense:MITStargazers:0Issues:0Issues:0
Language:ShellLicense:BSD-3-ClauseStargazers:0Issues:1Issues:0

imitation-learning

Imitation learning algorithms

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

jaxrl

JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.

License:MITStargazers:0Issues:0Issues:0

PIDOptimizer

Code for this CVPR 2018 paper: "A PID Controller Approach for Stochastic Optimization of Deep Networks", Wangpeng An, Haoqian Wang, Qingyun Sun, Jun Xu, Qionghai Dai, Lei Zhang.

Language:PythonStargazers:0Issues:0Issues:0

plant-art

Guid to help you make generative art using the electrical activity in plants 🎨🌱

Language:ProcessingLicense:MITStargazers:0Issues:2Issues:0

Reinforcement_learning_tutorial_with_demo

Reinforcement Learning Tutorial with Demo: DP (Policy and Value Iteration), Monte Carlo, TD Learning (SARSA, QLearning), Function Approximation, Policy Gradient, DQN, Imitation, Meta Learning, Papers, Courses, etc..

Language:Jupyter NotebookStargazers:0Issues:2Issues:0

RL-Adventure-2

PyTorch0.4 implementation of: actor critic / proximal policy optimization / acer / ddpg / twin dueling ddpg / soft actor critic / generative adversarial imitation learning / hindsight experience replay

Stargazers:0Issues:0Issues:0

self-driving-car-sim

A self-driving car simulator built with Unity

Language:C#License:MITStargazers:0Issues:0Issues:0

TCL

Time-Contrastive Learning

Language:PythonStargazers:0Issues:1Issues:0

TextWorld

​TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.

Language:PythonLicense:NOASSERTIONStargazers:0Issues:1Issues:0

Verilog-Generator-of-Neural-Net-Digit-Detector-for-FPGA

Verilog Generator of Neural Net Digit Detector for FPGA

Language:VerilogLicense:Apache-2.0Stargazers:0Issues:1Issues:0

zeroshot-imitation

[ICLR 2018] TensorFlow code for zero-shot visual imitation by self-supervised exploration

Language:PythonLicense:BSD-2-ClauseStargazers:0Issues:1Issues:0