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.