Stars
Latex code for making neural networks diagrams
This repository contains a simple implementation of Interval Bound Propagation (IBP) using TensorFlow: https://arxiv.org/abs/1810.12715
The released code of ReluVal in USENIX Security 2018
CLEVER (Cross-Lipschitz Extreme Value for nEtwork Robustness) is a robustness metric for deep neural networks
Efficient Robustness Verification for ReLU networks (this repository is outdated, don't use; checkout our new implementation at https://github.com/Verified-Intelligence/auto_LiRPA instead)
PLANET: a Piece-wise LineAr feed-forward NEural network verification Tool
Ultra-fast Boost.Python interface for ORBSLAM2
Microsoft Program Synthesis using Examples SDK is a framework of technologies for the automatic generation of programs from input-output examples. This repo includes samples and sample data for the…
Macro to draw architecture of convolutional neural nets in tikz.
a lightweight and simple logger for Machine Learning
Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit
A layer-wise algorithm for learning Convolutional Neural Networks
Tensors and Dynamic neural networks in Python with strong GPU acceleration
An implementation of the RL-NTM from http://arxiv.org/abs/1505.00521
A terminal for your browser, using node/express/socket.io
A graphics backend for the browser (with a Torch7 client).
A simple module for <Torch7> and the <nn> package
Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch
BING Objectness proposal estimator linux/mac/windows version implementation, runs at 1000 FPS. More in http://mmcheng.net/bing/ and also http://www.robots.ox.ac.uk/~szheng/DepthProposals.html
Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.
Automatically collect and visualize usage statistics in Ubuntu/OSX environments.
Recurrent Deep Learning Tutorials and examples: RNN, GRU, LSTM
Threads for Lua and LuaJIT. Transparent exchange of data between threads is allowed thanks to torch serialization.