Explores neural networks' ability to learn features and make linear predictions, emphasizing the importance of data quantity for effective performance.
Introduces feed-forward networks, covering neural network structure, training, activation functions, and optimization, with applications in forecasting and finance.
Covers the fundamentals of deep learning, including data representations, bag of words, data pre-processing, artificial neural networks, and convolutional neural networks.
Provides a review of linear algebra concepts crucial for convex optimization, covering topics such as vector norms, eigenvalues, and positive semidefinite matrices.
Explores Convolutional Neural Networks for semantic segmentation, discussing models for pixel classification, learned decoding, and the importance of skip connections.