Name: Vishal Keshav
Type: User
Company: University of Massachusetts, Amherst
Bio: Grad @ UMass | Software Eng. @ Amazon.com | Machine Learning @ Samsung Research | IIT Guwahati
Twitter: keshav_vishal
Location: Massachusetts, USA
Blog: vishal-keshav.github.io
Vishal Keshav's Projects
Hosts the server code for Poe Bot that introduces you to an amazing world of dogs.
A simple programme utilizing the power of artificial neural networks
Curated list of Machine Learning, NLP, Vision Project Ideas
A decentralized game that can be played on private or public blockchain network
Boltzmann Machines in TensorFlow with examples
Contains matlab codes used in project
Caffe2 is a lightweight, modular, and scalable deep learning framework.
A game developed in UNITY
A Tensorflow implementation of CapsNet(Capsules Net) in Hinton's paper Dynamic Routing Between Capsules
Essential Cheat Sheets for deep learning and machine learning researchers
Solutions to "Introduction to Algorithm, 3rd Edition"
CLTune: An automatic OpenCL & CUDA kernel tuner
Exploring novel strategy to solve color constancy problem with deep learning ideas.
The ARM Computer Vision and Machine Learning library is a set of functions optimised for both ARM CPUs and GPUs using SIMD technologies.
An application of convolutional neural network algorithms with caffee library and python interface for image and speech detection
Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.
This repository hosts the source code used for the project "Cost aware inference with early exits".
Changed
Introduction to Parallel Programming class code
Contains algorithm intended to run on GPU.
These are my quick implementation of various data structures and important algorithms
For testing SQLite database in android system
DeepVis Toolbox
My tensorflow implementation of "A neural conversational model", a Deep learning based chatbot
A deeplearning framework developed in C++ for on device training and light weight inference.
A web-based tool to parse through bills, lanch split web interface and compute the expense.