Introduces feed-forward networks, covering neural network structure, training, activation functions, and optimization, with applications in forecasting and finance.
Explores the design of flexible guidances, emphasizing the analysis of structures with orthogonal flexible joints and the optimization using flexible columns.
Covers the fundamentals of deep learning, including data representations, bag of words, data pre-processing, artificial neural networks, and convolutional neural networks.
Introduces Lasso regularization and its application to the MNIST dataset, emphasizing feature selection and practical exercises on gradient descent implementation.
