Name: Souradeep Dutta
Type: User
Company: University of Colorado, Boulder
Bio: Hi, Souradeep here.
I am currently a Postdoctoral Scholar, at UPenn. Current interests include- Formal Methods, AI, RL, and general learning
Location: Boulder, CO, USA
Blog: https://sites.google.com/site/duttasouradeep39/
Souradeep Dutta's Projects
A poor man's version of a python to x86 compiler
Code for the book Deep Learning with PyTorch by Eli Stevens, Luca Antiga, and Thomas Viehmann.
The Haar wavelet-based perceptual similarity index (HaarPSI) is a similarity measure for images that aims to correctly assess the perceptual similarity between two images with respect to a human viewer.
Handwritten digit recognition using neural network trained on 60000 images from MNIST dataset
This repository contains the benchmarks for neural network controller verification project using reach set computation.
Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
Reinforcement Learning examples implementation and explanation
Sherlock is a tool for output range anaylsis of Deep Neural Networks with ReLU activation units.
Sherlock without rule inference and other fancy stuff
An Open Source Machine Learning Framework for Everyone
The code here implements verification guided training scheme for neural network plant models. The verification scheme uses SHERLOCK to implement range propagation idea, and Tensorflow to train the Neural Network.