Teaching

👨‍🏫 Current Courses

Deep Learning

Universidad Panamericana Master’s in Data Science

A comprehensive journey through the foundations and state-of-the-art of Deep Neural Networks. We start from the mathematical basics of the single Perceptron and the Universal Approximation Theorem, moving through:

• Optimization: Stochastic Gradient Descent, Adam, and backpropagation mechanics.
• Architectures: CNNs for vision, RNNs/LSTMs for sequences.
• Modern Era: Attention mechanisms and the Transformer architecture (BERT, GPT).
• Generative Models: VAEs and GANs.

Deep Reinforcement Learning

Colegio de Matemáticas Bourbaki Specialized Advanced Track

An advanced course focusing on agents that learn from interaction. We cover the full spectrum of RL, balancing mathematical rigor with implementation:

• Foundations: Markov Decision Processes (MDPs), Bellman Equations, and Q-Learning.
• Policy Gradients: REINFORCE, Actor-Critic methods, and PPO (Proximal Policy Optimization).
• Deep RL: DQN refinements, Double Q-Learning, and Offline RL strategies.
• Application: Solving custom environments and optimization problems in finance and robotics.

---

📚 Course Archive & Resources

Material from my previous courses, including slides, notebooks, and syllabi.

• [DS01] Introduction to Data Science (2018)
  • Focus: Python stack (Pandas/Numpy), exploratory analysis, and data visualization.
• [DB01] Introduction to Databases (2018)
  • Focus: SQL, NoSQL, and data modeling for analytics.
• [ML01] Machine Learning (2017)
  • Focus: Supervised vs. Unsupervised learning, Scikit-learn, and model validation.

Guest Lecturing

• Machine Learning for Planetary Sciences (University of Arizona, 2016)
  • Guest lecturer on applying CNNs to HiRISE imagery for geological feature detection.