Bhavana Jain's repositories
research-paper-summaries
A directory with some interesting research paper summaries in the field of Deep Learning
spatial-transformer-networks
Tensorflow models for Spatial Transformer Networks
concurrent-priority-queues
Implemented Concurrent Priority Queues using fine grained locking over sequential heap and lockfree skiplist-based
optimistic-concurreny-control
C++ implementation of two Optimistic Concurrency Control (OCC) protocols - dynamic adjustment (OCC-DA) and TicToc (Time Traveling OCC)
graph-visualisation-with-sigma.js
Graph visualisation using Javascript library (sigma.js) and using No-SQL graph database Neo4j - A demo movie database with movies, actors, directors and other crew persons related to each movie (from neo4j sample databases ). Along with graph visualisation, we added interaction with it. So, a person could create an account, mark movies as watched, follow people and rate movies.
algorithms
Implementation of common data structures and algorithms in C++
diversionary_comments
Built a python pipeline to preprocess blog posts (lemmatization, coreference resolution, identify collocations, etc) and built an LDA topic model to flag irrelevant comments under those posts.
maplejuice
A fault-tolerant parallel cloud computing framework
show-and-tell
cs547 project on implementing image captioning (show and tell approach)
stackoverflow-tag-suggestion
Tag Suggestion for StackOverflow: We built two models - a deep neural network trained on the tf-idf vector embeddings of the post and a supervised LDA topic model.
autonomous-vehicles
Assignments and projects for CS598 MAAV: Autonomous Vehicles course at UIUC
clustering-algorithms
Clustering algorithms of K-Means and DBScan. Use them to classify documents topic-wise and compare performance
cs101_grader
Grader code for cs101. Please make changes accordingly
gitignore
A collection of useful .gitignore templates
infinitam
An extended infinitam version with a ROS node
ml-tools
Python implementations of Machine Learning tools
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
RBMs
In summer 2017, I was an intern at the Purdue University working under Prof Bruno Ribeiro on improving the training of Restricted Boltzmann Machines. We used the Las Vegas transformation of Markov Chain Monte Carlo method to obtain better samples to estimate the negative phase of the gradient. The model trained via this method achieved a significantly higher likelihood on the MNIST data as compared to the conventional model trained via Contrastive Divergence. This repository contains a brief report on my work.