Technical Skills

This page will not be actively maintained. Please check my Github for latest activity. Last updated 2017.

• Languages: Python, C, C++, Java, MySQL, PL-SQL, PHP
• Softwares & Pkgs: Spark, Python (sklearn, nltk, pandas, numpy, plotly, bs4), R (dplyr, H2O, shiny, caret, ggplot2, reshape2), MATLAB, Neo4j
• Data Mining Tools: WEKA, Orange
• Deep Learning: PyTorch, Keras, Tensorflow, Caffe, H2O, DIGITS (NVIDIA)
• Experience in SparkSQL,MLLib,PySpark and Scala.
• Good understanding of core AWS services, uses, and basic architecture. (Amazon EC2 and Amazon S3)
  
  For some time I have been using PyTorch for Deep Learning.
  

Courses

• Deep Learning: Advanced Learning Models, Machine Learning and Object Recognition , Information Retrieval
• Machine Learning: Advanced Algorithms for ML & Data Mining, Machine Learning Fundamentals, Fundamentals of probabilistic data mining, Neuro Computing, Soft Computing
• Big Data & Parallel programming: Convex & Distributed Optimization, High Performance Computing, Data Management in Large-scale distributed systems, Distributed Systems

Projects

Some of the projects as part of my courses and pursued independently.

• Classification using Deep Learning
  M.Tech. Thesis, Department of Mathematics, IIT Delhi
• Independent Deep Learning Projects
  * Daily News for Stock Market Prediction (See Code section)
  * Multi-layer RNN (Keras) for binary addition & character language models
  * Sentiment Analysis using character based and word based language models (both RNNs and CNNs)
  * LeNet model (Keras) for MNIST handwritten digit classification
• Movie Recommendation System (PySpark)
• Binary Classification with Logistic Regression (PySpark)
• Naive Bayes Classifier for Newsgroup Classification
• Support Vector Machines (SVMs) for Spam Classification