Day 1

  • Introduction
    • Machine learning vs. statistical approaches
  • Types of learning: supervised, unsupervised and reinforcement learning
  • Good practices in experimental design
  • Introduction to Python, Keras, Pytorch.
  • Some illustrative examples:
    • Classification problem
    • Clustering problem
    • Modern approaches: Embeddings
  • Ethics, privacy and governance considerations about AI deployments in industry
    • Mini-workshop: how to prepare an elevator pitch

Day 2

  • Introduction: Deep Learning
  • Artificial Neural Networks
    • Multilayered Perceptron
    • Recurrent neural networks (RNN)
    • Convolutional neural networks (CNN)
  • Good practices and experiment design

Day 3

  • Applications of Neural Networks
  • Text processing and Sentiment analysis
  • Anomaly detection
  • Generative models
  • Forecasting models
  • Introduction: learning by reinforcement
    • Q-learning
  • Case study: Reinforcement learning in finance