MIT

Gradient descent optimization – parameters and demo (M-I-T)

CNNs – two-dimensional filters (M-I-T)

Introduction to ML – estimation and generalization (M-I-T)

CNNs – typical architecture (M-I-T)

Introduction to ML – perspective and history (M-I-T)

Collaborative filtering – alternating least squares algorithm (M-I-T)

Introduction to non-parametric models (M-I-T)

Collaborative filtering – alternating least squares idea (M-I-T)

Introduction to reinforcement learning (M-I-T)

Collaborative filtering – framework (M-I-T)

K-armed bandits (M-I-T)

Collaborative filtering – hypothesis space (M-I-T)

Learning algorithms (M-I-T)

Collaborative filtering – objective function (M-I-T)

Linear classifiers (M-I-T)

Collaborative filtering – stochastic gradient descent (M-I-T)

Linear logistic classifier – a few comments about regularization (M-I-T)

Collaborative filtering – strategy (M-I-T)

Linear logistic classifier – hypothesis class (M-I-T)

Decision trees (M-I-T)

Linear logistic classifier – negative log likelihood loss function (M-I-T)

Logistic regression – setting and sigmoid function (M-I-T)

Machine learning as optimization – framework (M-I-T)

Machine learning as optimization – gradient descent in multiple dimensions (M-I-T)

Machine learning as optimization – gradient descent in one dimension (M-I-T)