Introduction to Machine Learning (Fall 2020) (M-I-T)

Neural networks – regularization by early stopping and dropout (M-I-T)

Regression – beauty of the closed form OLS solution (M-I-T)

Neural networks – regularization by weight decay (M-I-T)

Regression – OLS analytical solution setup (M-I-T)

Neural networks – training and back-propagation (M-I-T)

Regression – OLS analytical solution using gradients (M-I-T)

Neural networks – weight initialization (M-I-T)

Regression – OLS and gradient descent demo example (M-I-T)

Neural networks and Q-learning (M-I-T)

Regression – ordinary least squares solution using optimization (M-I-T)

Objectives of the reinforcement learning problem (M-I-T)

Regression – regularization by ridge regression (M-I-T)

One-dimensional linear regression – demo (M-I-T)

Regression – ridge regression using gradient descent (M-I-T)

Perceptron – overview of plan (M-I-T)

Regression – stochastic gradient descent (M-I-T)

Perceptron convergence theorem (M-I-T)

Regression – structural error and estimation error (M-I-T)

Regression and the ordinary least squares problem (M-I-T)

Regression trees – problem statement (M-I-T)

Reinforcement learning demos (M-I-T)

RNNs – gating mechanisms and LSTM (M-I-T)

RNNs – training a language model (M-I-T)

Sequence-to-sequence RNN (M-I-T)

SM – Markov decision processes – states and actions (M-I-T)