Syllabus (tentative)

• Introduction: What is machine learning, supervised, reinforcement and unsupervised learning
• Types of predictors, bias-variance tradeoff, overfitting, curse of dimensionality
• Families of predictors for regression and classification: linear and logistic regression, nearest neighbor classifiers, regression and decision trees, neural networks, boosted predictors
• Training predictors; gradient descent and stochastic gradient descent and smoothness
• Regularization: Lasso and sparsity, Support Vector Machines and the kernel trick, overparametrization and double descent
• Neural networks: two layer, multi-layer, convolutional,
• Deep neural networks, autoencoders, generative models, flow models and theoretical views: the neuro-tangent kernel, NN's as Gaussian processes
• Attention, transformers, large language models
• Elements of unsupervised learning: Clustering, mixtures distributions, K-means and EM algorithms, density estimation, Principal Components Analysis
• Combining predictors
• Adversarial learning
• Privacy, fairness, explanability and interpretability
  Topics in [] are optional, time permitting; new topics are highlighted in blue.