| Deep Learning - 29171 - CS 69000 - DPL |
||||
|---|---|---|---|---|
|
Associated Term: Spring 2021
Levels: Graduate, Professional, Undergraduate West Lafayette Campus Lecture Schedule Type Learning Outcomes: This is an in-depth course on deep learning. Please consider other offers on campus if you are only interested in deep learning as a tool. A lot of our coding will be in pytorch as a numpy library for GPU. Upon completing the course, students should be able to: Understand the mathematical foundations of deep learning, including: Statistical Foundations of Deep Learning Extrapolations and Causal Mechanisms in Deep Learning Feedforward Networks, Recurrent Networks, Transformers, Set Representations, Convolutional Networks Markov chains and Sequence learning Graph Neural Networks and Graph Embeddings (e.g. word2vec, Glove) Backpropagation and Backpropagation-Throuh-Time Stochastic optimization of neural network models Invariant Representations Variational Auto-Encoders Multi-task Learning, Transfer Learning, and Meta Learning Generative Adversarial Networks Understand how to evaluate the performance of neural networks, as well as formulate and test hypotheses Understand how algorithmic elements interact to impact performance Required Materials: (Required, online) Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, MIT Press, FREE online copy (required, online) Thrun, Sebastian, Pratt, Lorien (Eds.), Learning to Learn, Springer. (free with your Purdue account) (recommended, online) Aston Zhang, Zachary C. Lipton, Mu Li, and Alexander J. Smola. "Dive into Deep Learning." Unpublished v0.7 draft (2019). https://d2l.ai/ Technical Requirements: View Catalog Entry
| ||||
