rahul-dhavalikar Goto Github PK

activity-recognition

Predicting the Human Activity from the sensor readings of smartwatch

bay-area-traffic-flow-analysis

Analyzing Uber geodata using traveling salesman & network flow algorithms

collaborative-filtering-for-movie-recommendation

coursera-machine-learning

Programming assignments of Coursera-machine learning course

dqn-predator-prey-dynamics

Simulation of Predator Prey Dynamics using Deep Reinforcement Learning (CS 275: Artificial Life for Computer Graphics and Vision - Course Project)

event-detection-using-sentiment-analysis-on-twitter-data

Using sentiment analysis on SuperBowl 2015 data to detect key events during the SuperBowl. The analysis is also further extended to extract the key people involved.

imdb-mining

We explore various properties of the IMDb dataset by systematically analyzing actor/actress, movie data by constructing networks helping uncover trends and other interesting information

introduction-to-graph-networks

In this project, we study various random graph networks and their properties. Along with this, we implement random walks and PageRank on these networks.

network-analysis-using-regression

product-recommendation-system

Product recommendation system on Amazon product dataset using Apache Spark framework

product-title-analysis

Determining the clarity and conciseness of product titles using deep learning, XGBoost

quora-duplicate-question-pair-detection

Determining whether two questions are asking the same thing can be challenging, as word choice and sentence structure can vary significantly. Traditional natural language processing techniques been found to have limited success in separating related question from duplicate questions. In this paper, we explore methods of determining semantic equivalence between pairs of questions using a dataset released by Quora. We explore different approaches involving using different classifiers with a rich feature set, a Siamese Neural Network which uses an LSTM, and an ensemble of the multiple approaches. Our ensemble model outperforms the classifier and Siamese models.

reinforcement-learning-and-inverse-reinforcement-learning

In this project, we implement reinforcement learning concepts using the Value Iteration Algorithm to learn optimal policy. In the second part, we apply inverse reinforcement learning for apprenticeship learning.

social-network-mining-using-google--and-facebook-data

In this project, we study various properties of social networks. In the first part of the project, we study an undirected social network (Facebook). In the second part of the project, we study a directed social network (Google +).

test