Scaling Compute Intensive Tasks using Apache Spark
A study evaluating the performance for different compute intensive tasks on Apache Spark, analyzing the scalability and optimal parameter selection.
Portfolio
Distributed Training using PyTorch
Training a multiclass classifier on MNIST across multiple GCP instances using PyTorch’s DistributedDataParallel module
Implementing Viola Jones Algorithm using Python and Numba
Python and Numba-based open source implementation of Viola Jones Cascade Classifier training procedure
Statistical Exploration of Happiness
A look at impact of Covid-19 on reported happiness scores
Google Foobar Challenge
My solutions to Google’s coding challenge
Logarithmic Binning for Improved Histogram Plots
Enhancing histogram visualization by applying log transformation for better binning
Interactive Machine Learning
Implementing and comparing the different Contextual Bandit Algorithms on MNIST dataset