Tweet Geocoder

Python application that trains and executes queries on recurrent neural network classifier solely on the foundation text of tweets. Uses RNN with multilayer bidirectional LSTM and GloVe embeddings. Trained on dataset from here.

Algorithms

C++ and Python Implementations of several common sorting, graph, root finding and differentiation algorithms.

News Analyzer

Parse news article and create inverted index for face recognition and association with text queries. Facial recognition performed using OpenCV Cascade Classifiers and OCR performed with Tesseract. OpenCV, Computer Vision, Python

Portfolio Website

Generated scalable, serverless personal portfolio (client & server-side dynamic) website to further develop skill base with jQuery, React, Flask, and Bootstrap and gain experience with AWS Lambda, S3, APIGateway and CloudFormation as well as PostgreSQL.

Dog Breed Classifier

Trained and developed convolutional neural network for identifying dog breeds using PyTorch. Contact for details.

Amazon Review Classifier

Developed and optimized gaussian-kerneled multi-label SVM for textual analysis of Amazon reviews using NLP techniques including analysis of optimal tokenization methods, stemming/lemmatization, tf-idf vectorization etc. Contact for details.

Wound Healing Research

Researched, published, and presented on findings regarding impact of VEGF on wound healing and scar tissue development. Presented at MIT UV Convention. Published abstract, manuscript pending publication.

E.K.G.A.R. (Every Kid Gets a Robot)

Founded robotics program and product to create opportunities for students in socio-economically challenged education systems to participate and engage with developments in the field of robotics. Designed and produced $50 (now $20) robot kits for distribution with proceeds going toward funding development and redistribution in additional kits. Rebranded under the STEAM connection.

Data Structures and Algorithms

Institution: University of Michigan ≎̸ Grade: A

Topics include introduction to algorithm analysis and O-notation, fundamental data structures including lists, stacks, queues, priority queues, hash tables, binary trees, search trees, balanced trees and graphs, searching and sorting algorithms, recursive algorithms, basic graph algorithms, greedy algorithms and divide and conquer strategy.

Introduction to Computer Organization

Institution: University of Michigan ≎̸ Grade: A+

Basic concepts of computer organization and hardware. Instructions executed by a processor and how to use these instructions in simple assembly-language programs. Stored-program concept. Datapath and control for multiple implementations of a processor. Performance evaluation, pipelining, caches, virtual memory, input/output.

Foundations of Computer Science

Introduction to theory of computation. Models of computation: finite state machines, Turing machines. Decidable and undecidable problems. Polynomial time computability and paradigms of algorithm design. computational complexity emphasizing NP-hardness. Coping with intractability. Exploiting intractability: cryptography.

Introduction to Machine Learning

Institution: University of Michigan ≎̸ Grade: A

Theory and implementation of state-of-the-art machine learning algorithms for large-scale real-world applications. Topics include supervised learning (regression, classification, kernel methods, neural networks, and regularization) and unsupervised learning (clustering, density estimation, and dimensionality reduction).

Database Management Systems

Institution: University of Michigan ≎̸ Grade: A

Concepts and methods for the design, creation, query and management of large enterprise databases. Functions and characteristics of the leading database management systems. Query languages such as SQL, forms, embedded SQL, and application development tools. Database design, integrity, normalization, access methods, query optimization, transaction management and concurrency control and recovery.

Web Systems

Institution: University of Michigan ≎̸ Grade: A+

Concepts surrounding web systems, applications, and internet scale distributed systems. Topics covered include client/server protocols, security, information retrieval and search engines, scalable data processing, and fault tolerant systems. The course has substantial projects involving development of web applications and web systems.

Information Retrieval and Web Search

Institution: University of Michigan ≎̸ Grade: A

Covers background and recent advances in information retrieval (IR): indexing, processing, querying, classifying data. Basic retrieval models, algorithms, and IR system implementations. Focuses on textual data, but also looks at images/videos, music/audio, and geospatial information. Web search, including Web crawling, link analysis, search engine development, social media, and crowdsourcing.

Computer Science Pragmatics

Institution: University of Michigan ≎̸ Grade: A+

Essential tools for computer programming: Shells, environments, scripting, Makefiles, compilers, debugging tools, and version control.

Applied Linear Algebra

Institution: University of Michigan ≎̸ Grade: A

An introduction to the main concepts of linear algebra… matrix operations, echelon form, solution of systems of linear equations, Euclidean vector spaces, linear combinations, independence and spans of sets of vectors in Euclidean space, eigenvectors and eigenvalues, similarity theory. There are applications to discrete Markov processes, linear programming, and solutions of linear differential equations with constant coefficients.

Introduction to Operating Systems

Institution: University of Michigan ≎̸ Grade: A+

Operating system design and implementation: multi-tasking; concurrency and synchronization; inter-process communication; deadlock; scheduling; resource allocation; memory and storage management; input-output; file systems; protection and security. Students write several substantial programs dealing with concurrency and synchronization in a multi-task environment, with file systems and with memory management.

Compiler Construction

Institution: University of Michigan ≎̸ Grade: A

Introduction to compiler construction. Topics covered will include the following: lexical scanning, parsing (top-down and bottom-up), abstract syntax trees, semantic analysis, code generation and optimization. Students build a working compiler for a high-level programming language.

Introduction to Computer Security

Institution: University of Michigan ≎̸ Grade: A

This course introduces the principles and practices of computer security as applied to software, host systems, and networks. It covers the foundations of building, using and managing secure systems. Topics include standard cryptographic functions and protocols, threats and defenses for real-world systems, incident response and computer forensics.

Distributed Systems

Institution: University of Michigan ≎̸ Grade: A

Distributed systems offer higher performance, greater fault-tolerance, and better scalability than single-computer systems, but are challenging to develop. Topics covered: abstractions for simplifying development of distributed systems, techniques used to implement these abstractions, and case studies on the use of these techniques in real-world systems.