Covers Convolutional Neural Networks, including layers, training strategies, standard architectures, tasks like semantic segmentation, and deep learning tricks.
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.
Delves into training and applications of Vision-Language-Action models, emphasizing large language models' role in robotic control and the transfer of web knowledge. Results from experiments and future research directions are highlighted.
Explores the provable benefits of overparameterization in model compression, emphasizing the efficiency of deep neural networks and the importance of retraining for improved performance.
Explores the mathematics of language models, covering architecture design, pre-training, and fine-tuning, emphasizing the importance of pre-training and fine-tuning for various tasks.
Covers the fundamentals of deep learning, including data representations, bag of words, data pre-processing, artificial neural networks, and convolutional neural networks.
