suyashh94 Goto Github PK
Name: Suyash Harlalka
Type: User
Company: Washington University in St. Louis
Bio: Interested in understanding how things are learned - both computationally and experimentally.
Location: St. Louis
Name: Suyash Harlalka
Type: User
Company: Washington University in St. Louis
Bio: Interested in understanding how things are learned - both computationally and experimentally.
Location: St. Louis
This repository shows how using spatial dropout in convolution layers can help the training process using CNN models
This has assignment solutions from data structures class that requires implementation of min heap, hash table, avl trees and Djikstra's shortest path algorithm
Materials for Bayesian Methods in Machine Learning Course
This is an implementation of fully connected neural network from scratch. Batch normalization, regularization using dropout , and momentum, SGD, and adam optimization techniques have been implemented.
This repository contains an implementation of CNNs from scratch. It has dropout regularization, both for convolution and fully connected layers. It also has batch normalization implemented - both for fully connected and convolution layers. It takes the model characteristics as input from the user. This, currently has implementation for Conv + relu and Max pool layers in the convolution segment of the network. Also, final layer before fully connected segment is a max pool layer. This implementation makes use of functions from generalized-neural-network repository for the fully connected layer's computation.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
This is an implementation of neural style transfer, which I wrote to generate a Van Gogh styled portrait of my friend, Eric, to give him as his "going away" present. This is motivated by post " Neural Style Transfer: Creating Art with Deep Learning using tf.keras and eager execution" . Theoretical basics were covered from Coursera lectures and Gatys et al.(2015) paper. Application using tensorflow and keras was done by referring to the referred post.
Software for processing, recording, and visualizing multichannel electrophysiology data
This has a detailed implementation of ResNet50 architecture from scratch in keras to identify signs of numbers
This is a vanilla implementation to generate dinosaur names. Dataset was taken from Coursera's sequence model course. We can train it on any other data set of names to generate alike names.
Open Ephys plugins for tracking experiments
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.