Covers the fundamentals of deep learning, including data representations, bag of words, data pre-processing, artificial neural networks, and convolutional neural networks.
By Meenakshi Khosla explores data-driven modeling in large-scale naturalistic neuroscience, focusing on brain activity representation and computational models.
Introduces feed-forward networks, covering neural network structure, training, activation functions, and optimization, with applications in forecasting and finance.
Delves into the geometric insights of deep learning models, exploring their vulnerability to perturbations and the importance of robustness and interpretability.