Decision theory, continuous features, discriminant features and surfaces, Models with gaussian density, Parameter estimation, ML/Bayesian estimation, Examples, Linear regression of one variable, cost function and solution, gradient descent, Multivariate regression, non linear features, underfitting, overfitting, regularization, Logistic regression, cost function, Regularization, Extension of linear models to non linear models, single layer neural network, artificial neural networks, loss functions, back propagation, examples of regression and classification tasks. Alternate Classification systems - Support vector machines, Decision trees, Random forests and Gradient Boosting, Deep learning, vanishing gradient descent problem – solutions, Special architectures, convolutional and recurrent neural networks, Imagenet data, Unsupervised learning algorithms - K means clustering, applications, imensionality reduction, Recommender systems, NN embeddings as features, Introduction to generative models - Autoencoder, Variational Autoencoder

Generative Adversarial Networks (GAN)