Hadi Salman

smoothing-adversarial. Code for our NeurIPS 2019 *spotlight* "Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers"

robust-verify-benchmark. Benchmark for LP-relaxed robustness verification of ReLU-networks

ICAPS2017-code. Repository containing the codes that were used in the paper "Multi-agent Ergodic Coverage with Obstacle Avoidance"

trajectory-optimized-active-search. Code for the ICRA2018 paper "Trajectory-Optimized Sensing for Active Search of Tissue Abnormalities in Robotic Surgery"

AirSim-robustness. C++

gym-gazebo-hadi. Modified version of gym-gazebo. Includes new Gazebo models and new deep RL architectures

snakeMonsterGazebo. A package containing URDF model for a six legged robot (snake Monster) with a central pattern generator controller for quick integration with Gazebo

search-coverage. CMake

UE-vulkan-debug. Dockerfile

DeepRL-Agents. A set of Deep Reinforcement Learning Agents implemented in Tensorflow.

chexrobfer. Jupyter Notebook

stoec. This repository contains codes for the IROS2017 paper "Ergodic Coverage In Constrained Environments Using Stochastic Trajectory Optimization"

PSRule. Validate objects using PowerShell rules.

realsense_samples_ros. Sample code illustrating how to develop ROS applications using the Intel® RealSense™ ZR300 camera for Object Library (OR), Person Library (PT), and Simultaneous Localization And Mapping (SLAM).

robustness. A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.

maskrcnn-benchmark. Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

Sphinx-RTD-Tutorial. A tutorial on how to use Sphinx

L0Learn. Efficient Algorithms for L0 Regularized Learning

EfficientNet-PyTorch. A PyTorch implementation of EfficientNet

chainer. A flexible framework of neural networks for deep learning

convex_adversarial. A method for training neural networks that are provably robust to adversarial attacks.