Name: Rajat Kanti Bhattacharjee
Type: User
Company: @ShareChat
Bio: Engineer @ShareChat , performance fanatic and loves work with a.i problems . Dabble in decentralized systems, spends leisure time with cosmos.
Location: Guwahati, Assam ,India
Blog: https://medium.com/csmadeeasy
Rajat Kanti Bhattacharjee's Projects
This is notebook where I just create random idenitity and Autoencoder networks to actually see what the convolution layers are learning. Mostly I visualise the internal layers activation and conclusions can be drawn about what the hidden layers are learning. For anyone who is trying to build CNN. This can also help them guide them into thinking and creating proper hidden representation.
This is a fast neural style transfer implement with Keras 2.
This is a personnel repo where i keep every small module that i have created and reuse when making projects .
It contains my own variant of Neural Network implementation which is generic. So ya anyone who have used keras should be able to understand how it works. It allows you to add layers and then run the test
Hobby Operating System
Create a standard set of issue labels for a GitHub project
Go Promise aims to be a Promise/Future alternative of bluebird in golang. It will give all the various functionalities provided by any standard promise library along with something more.
Skip List implementation in Golang,
Looking for a guide? You came to the right place. Here you can find documentation for a variety of topics I research to make complex computing easier. For comments go to the IRC channel #nfo at the Rizon network.
This is our 7th sem 4th year Engineering final year project. It aims to use techniques like Conditional GAN , Image to Image translation , Texture and content transfer for aiding as a design tool for handloom weavers and also designers and industry as a whole.
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in python using Scikit-Learn and TensorFlow.
How to systematically secure anything: a repository about security engineering
Intuition net is a neural network + experiment which is built upon the idea of Object Permanance in humans which also leads us to understand physics and inertia of objects intuitively. The network in question will be able to predict segmentation mask for vehicles on road which are not part of the visual field from previous time step data.
It's a Scala Json parser. It parses JSON, and create Map , Arrays and String and Numbers and Booleans embedded in them. It' supposed to be functional in nature, so no mutation. Also it's to support streaming which is work in progress, getting immutability and streaming is a tough nut to work out together
Books, Presentations, Workshops, Notebook Labs, and Model Zoo for Software Engineers and Data Scientists wanting to learn the TF.Keras Machine Learning framework
Keras Temporal Convolutional Network.
A lazy evaluation liobrary with concurrency and task scheduling baked in, for frontend evaluation of large data arrays and task qeueus
200+ Youtube Videos on Programming, Design and Architecture. 20+ Courses on Programming and Full Stack Development.
:sunglasses: A quick Travis CI (Continuous Integration) Tutorial for Node.js developers
Becoming better at data science every day
Linux kernel source tree
Machine Learning Pipelining With Spark & Tensorflow , workshop for Developer Students Club Assam Engineering College
A list of research papers in the domain of machine learning, deep learning and related fields.
Machine_learning_Scripts will be a collection of all small time analytics that i do with datasets. The repo includes simple mathematical methods implementations or sklearn based one analysis.
Dispatches mail by getting information from the excell sheet provided. Necessary to have in xlsx format
This is a markov chain implementation that does not generates text on random. It finds the most likely path after creating a tree from subgraph of the entire fully connected graph
This is grid system that i have designed for general responsive of a webpage. Yes there are other alternatives but a home brewn one never hurts.
MIT Deep Learning Book in PDF format (complete and parts) by Ian Goodfellow, Yoshua Bengio and Aaron Courville