Efficient n-gram predictions

Hi! I am Kaustubh Sable - a highly motivated, passionate and experienced software developer.
I enjoy solving problems and to make a positive impact on people's lives.
I am currently pursuing my Master's degree from Stony Brook University, NY. I have extensive experience of software
development in Java, C++ and Python. I have also worked on machine learning and data science projects during my
internship experience and in college coursework.
I am passionate and sincere towards my goals and I strive to improve with every opportunity. Grasping new skills quickly,
teamwork, and time management are some qualities that I'm proud of.
My areas of interest include Backend Development, Machine Learning, Data Engineering, Artificial Intelligence and Cloud
Computing.
Outside the cubicle, I am an avid reader, joyful hiker and an experimental cook.
Nutanix, Inc.
Member of Technical Staff Intern - -
Team: Files Infrastructure
eQ Technologic, Inc.
Data Engineer - -
Team: Platform – Plugins and Adapters
Developed modules on the Data Virtualization layer that connect and interact with various enterprise systems, like SAP ERP and TCRA4S, to insert, update and read data efficiently.
NVIDIA Graphics Pvt Ltd
System Software Intern ( Deep Learning ) - -
Team: GPU Video-Windows
Project: Deep Learning based Error Concealment.
Here is a more detailed blog created by me about the project: Image Completion using Tensorflow
Efficient n-gram predictions
Recommender Systems
Pac-Man Searching
Retail Data Analysis
Spam Classifier
Online Pizza Delivery System
Datapoint extraction (NLP)
State University of New York at Stony Brook
Master of Science in Computer Science - -
Pune Institute of Computer Technology
Bachelor of Engineering in Computer Engineering - -
I love being socially and culturally active. Few of my hobbies include:
Efficient n-gram predictions
Task: Analyze different approaches used for n-gram word predictions and optimize them for resource-constrained settings.
Models analyzed: Analyzed the Hidden Markov model, the Back-off model, character-based LSTM model, and word-based LSTM model.
Inference: word-level LSTM is optimum in terms of complexity and space-efficiency compared to others.
Github link for the code and more details here.
Recommender Systems
The study mainly consisted of the following three topics:
Github link for the code and more details here.
Pac-Man Searching
These projects were implemented in Python under the course lecture of Artificial Intelligence (AI):
Github link for the code and more details here.
Retail Data Analysis
Analyzed the data of Costello’s ACE hardware retail store chain with the primary goal of providing the store with insights that will help them grow their business. It also included performing the following techniques:
Github link for the code and more details here.
Spam Classifier
Implemented the Naive Bayes algorithm from scratch for spam filtering.
The dataset used is a subset of 2005 TREC Public Spam Corpus. It contains a training set and a test set.
Github link for the code and more details here.
Online Pizza Delivery System
Spring MVC Restful application for Pizza Delivery System: This project was created during my initial days at eQ Technologic in a group of four.
It was continuously reviewed with respect to Database Design, sequence & class diagram, UML Design, OOP, Flexibility and Scalability.
Due to NDA, code and other details regarding the project cannot be made public.
Datapoint extraction (NLP)
Performed information extraction based on multiple datapoints from html and PDF documents for Broadridge Financial Solutions as part of advance project.