Dec 01, 2022
CS 6890 - Deep Learning
This course will introduce the multi-layer perceptron, a common deep learning architecture, and its gradient-based training through the backpropagation algorithm. Fully connected neural networks will be followed by more specialized neural network architectures such as convolutional neural networks (for images), recurrent neural networks (for sequences), and memory-augmented neural networks. The later part of the course will explore more advanced topics, such as generative adversarial networks and deep reinforcement learning. The lectures will cover theoretical aspects of deep learning models, whereas homework assignments will give students the opportunity to build and experiment with shallow and deep learning models, for which skeleton code will be provided.
Requisites: CS 6830 or permission
Credit Hours: 3
Repeat/Retake Information: May not be retaken.
Lecture/Lab Hours: 3.0 lecture
Grades: Eligible Grades: A-F,WP,WF,WN,FN,AU,I
- Students will be able to derive the gradients of a number of standard objective functions in machine learning, such as sum-of-square errors or cross-entropy.
- Students will be able to implement the backpropagation algorithm for feedforward neural networks.
- Students will be able to explain the advantages of deep learning architectures over shallow architectures.
- Students will be able to list the difficulties one may encounter when training deep architectures and outline solutions to alleviate them.
- Students will be able to use regularization techniques for deep architectures.
- Students will be able to summarize and evaluate recent state-of-the-art deep learning techniques.
- Students will be able to employ deep learning packages to complete a month-long machine learning project.
- Students will be able to design neural architectures appropriate for a given machine learning problem.
- Students will be able to evaluate the impact of hyper-parameters on the performance of neural models.
Add to Portfolio (opens a new window)