Tyler Wallett

M.S. Data Science - George Washington University

I am from Venezuela 🇻🇪 and Canada 🇨🇦. I am deeply passionate 💖 about computers 💻, specifically teaching computers how to learn 📚 from lots and lots of data 📊. My areas of interest 🤔 are Deep Learning 🧠, Natural Language Processing 💬, Graph-Neural Networks 🔗 and Reinforcement Learning 🤖.

Courses Developed

Reinforcement Learning

This course introduces reinforcement learning through classical and deep architectures. Key algorithms covered include Monte Carlo (MC), Temporal Difference (TD), Value Function Approximation (VFA), Deep Q-Networks (DQN), Vanilla Policy Gradient (VPG), Proximal Policy Optimization (PPO), and Monte Carlo Tree Search (MCTS), with hands-on projects and real-world applications.

GitHub

Projects

Neural Networks with NumPy

This project implements neural networks using NumPy to solve regression and classification problems. Key algorithms covered include Perceptron, ADALINE and Multi-Layered Perceptron (MLP).

GitHub

Optimization with NumPy

This project applies optimization techniques using NumPy to optimize multidimensional functions. Key algorithms covered include Gradient Descent, Linear Minimization, Newton's Method and Conjugate Gradient.

GitHub

Research

A Benchmark for Graph-Based Dynamic Recommendation Systems

This paper aims to provide a comprehensive benchmarking framework for evaluating the performance of graph-based dynamic recommendation systems. Key algorithms covered SAGE (GraphSAGE), GAT (Graph Attention Networks), GIN (Graph Isomorphism Networks), and additional state of the art Graph Neural Network architectures.

GitHub Springer Link