| |
Nov 22, 2024
|
|
|
|
|
AI 5010 - Foundations of Deep Learning
This course introduces multi-layer neural networks, a common deep learning architecture, and gradient-based training through the backpropagation algorithm. Fully connected neural networks are followed by more specialized neural network architectures such as convolutional neural networks, recurrent neural networks with attention, and deep generative models.
Requisites:
Credit Hours: 3
Repeat/Retake Information: May be repeated for a maximum of 6.0 hours.
Lecture/Lab Hours: 3.0 lecture
Grades: Eligible Grades: A-F,WP,WF,WN,FN,AU,I
Learning Outcomes:
- Students will be able to summarize the history of neural network models.
- Students will be able to apply linear learning models including linear regression and perceptron.
- Students will be able to apply neurons, logistical regression and multi-layer perceptron.
- Students will be able to apply backpropagation algorithms.
- Students will be able to apply convolutional neural networks (CNNs) and their applications in image recognition.
- Students will be able to apply recurrent neural networks (RNNs) and their application as language models.
- Students will be able to apply generative models including variational autoencoders (VAEs) and generative adversarial networks (GANs)
- Students will be able to apply deep learning models in applications areas, including computer vision and natural language processing
- Students will be able to utilize certain state-of-the-art deep learning models for computer vision and natural language processing.
Add to Portfolio (opens a new window)
|
|
