COURSE SCHEDULE
Daily Breakdown
Day 1: Model Development and Neural Network Foundations
Framing a problem, validating a model honestly, choosing the right metric and preparing data without leakage; then neurons, layers, backpropagation and optimizers, and training networks reliably in PyTorch.
Day 2: Deep Learning Architectures
CNNs for images, RNNs, LSTMs and GRUs for sequences, and the attention mechanism behind transformers.
Day 3: Reinforcement Learning Foundations
Agents, environments and rewards, Markov decision processes, value functions and the Bellman equation, and Q-learning.
Day 4: Policy Gradients and RL in the Real World
Learning the policy directly, from REINFORCE to PPO and GRPO, then where RL runs in the real world: RLHF for language models, multi-agent RL and robotics.
Day 5: Responsible AI and MLOps Foundations
Bias, fairness, interpretability and AI governance, then tracking, deploying, compressing and monitoring a model in production.