Explores the learning dynamics of deep neural networks using linear networks for analysis, covering two-layer and multi-layer networks, self-supervised learning, and benefits of decoupled initialization.
Covers Convolutional Neural Networks, including layers, training strategies, standard architectures, tasks like semantic segmentation, and deep learning tricks.
Explores recent advances in magnetic materials and spintronics, including manipulating magnetization with light pulses and essentials for high-density magnetic random-access memory.
Introduces feed-forward networks, covering neural network structure, training, activation functions, and optimization, with applications in forecasting and finance.
