Content:

Artificial Intelligence I 

• An introductory course to programming
• Array/tensor processing and vectorization
• Basics of parallel programming:
  • Sequential flow of control vs concurrency vs. parallelism
  • Parallel programming models
  • Hardware acceleration: GPUs/TPUs

Artificial Intelligence II

• Introduction to Artificial Intelligence:
  • Learning from examples
  • Types of learning
  • Evaluation metrics
  • Train/val/test splits
  • Cross-validation
  • Data preprocessing
• Linear Models:
  • Loss functions
  • Gradient Descent
  • Regularization
  • Hyperparameter optimization
• Neural Networks:
  • Layered architectures
  • Activation functions
  • Backpropagation
  • Weight initialization
  • Dropout
  • Enhanced optimization algorithms: (Nesterov) Momentum, Adagrad, RMSprop, Adam
• Intro to Convolutional Neural Networks:
  • Common layer types
  • Patterns and popular architectures
  • Transfer Learning / Fine-tuning
• Intro to Reinforcement Learning:
  • Markov Decision Processes
  • Value Functions
  • Value Iteration / Policy Iteration
  • Q-Learning
  • Deep Q-Learning