Angel Vilchis

Relevant Coursework

Machine Learning & Data Mining

Introduction to principles of machine learning and data-mining applied to real-world datasets.

Introduction to Artificial Intelligence

Different means of representing knowledge and uses of representations in heuristic problem solving such as predicate logic, semantic nets, procedural representations, natural language grammars, and search trees.

Neural Networks & Deep Learning

Theory of parallel distributed processing systems, algorithmic approaches for learning from data in various manners, applications to difficult problems in AI from computer vision, to natural language understanding, to bioinformatics and chemoinformatics.

Introduction to Deep Learning for Medical Imaging

Aimed to provide the skillset needed to design, train and validate convolutional neural networks for various imaging applications in the healthcare setting.

Graph Algorithms

Algorithms for solving fundamental problems in graph theory: graph representations, graph traversal, network flow, connectivity, graph layout, matching problems.

Introduction to Optimization

A broad introduction to optimization: unconstrained and constrained optimization, equality and inequality constraints, linear and integer programming, stochastic dynamic programming.

Software Testing, Analysis, & Quality Assurance

Preparation for developing high-quality software: fundamental principles of software testing, implementing software testing practices, ensuring the thoroughness of testing to gain confidence in the correctness of the software.

Project in Artifical Intelligence

Worked with team to create a Minecraft agent that accomplished tasks given natural language text as input.

Applications of Probability in Computer Science

Analysis of algorithms and graphs, probabilistic language models, network traffic modeling, data compression, and reliability modeling.

Algorithms for Probabilistic and Deterministic Graphical Models

Graphical model techniques dealing with probabilistic and deterministic knowledge representations with focus on graphical models such as constraint networks, Bayesian networks, and Markov networks.