|
|
|
Oct 14, 2024
|
|
CS 687 - Fundamentals of Deep Learning (3 units)
Principles, design and implementation of deep learning systems. Topics include statistical machine learning, multi-layer perceptron (MLP) and neural networks, deep neural networks, optimization and learning, convolutional neural networks (CNN), CNN architectures, CNN applications in classification, detection, segmentation, and advanced topics in recurrent networks and generative adversarial networks (GAN).
Maximum units a student may earn: 3
Recommended Preparation: Machine Learning, solid mathematical background and good programming skills.
Grading Basis: Graded
Units of Lecture: 3
Offered: Every Spring
Student Learning Outcomes
Upon completion of this course, students will be able to:
1. identify, formulate, and solve complex engineering problems by applying principles of engineering, science, and mathematics.
2. develop and conduct appropriate experimentation, analyze and interpret data, and use engineering judgment to draw conclusions.
3. apply engineering and computer science research and theory to advance the art, science, and practice of the discipline.
Click here for course scheduling information. | Check course textbook information
Add to Portfolio (opens a new window)
|
|
|