Part a - Introduction to deep learning. Perceptrons, deep networks, convolutional neural networks, transformers. Optimization techniques: stochastic gradient descent, ADAM. Data wrangling: public datasets, sourcing datasets, crowdsourcing dataset annotation, dataset cleanup and curation. Performance evaluation and benchmarking. Training and inference using Numpy and PyTorch. Applications to computer vision, sound processing and natural language processing. The class will emphasize hands-on experience and good experimental practices. Part b - (Prerequisite: 148a or equivalent) The class will focus on large language models (LLMs) and language-and-vision models, as well as on generative methods for artificial intelligence (AI). Topics include deep neural networks,transformers, large language models, generative adversarial networks, diffusion models, state-space models, and applications of such architectures and methods to image analysis, image synthesis, and text-to-image translation.