| CS 515 Deep Learning |
3 Credits |
|
This course covers the theory and foundations of
Artificial Neural Networks (ANN) and various
ANN architectures, such as the single and multi-
layer perceptrons, Hopfield and Kohonen networks,
and deep learning architectures (convolutional
neural networks, autoencoders, restricted Boltzman
machines, recurrent networks and LSTMs, and
generative adversarial networks). Students will be
expected to develop systems for machine learning
problems from the computer vision and natural
language understanding areas.
|
| Last Offered Terms |
Course Name |
SU Credit |
| Spring 2026-2027 |
Deep Learning |
3 |
| Spring 2025-2026 |
Deep Learning |
3 |
| Spring 2024-2025 |
Deep Learning |
3 |
| Spring 2023-2024 |
Deep Learning |
3 |
| Spring 2022-2023 |
Deep Learning |
3 |
| Spring 2021-2022 |
Deep Learning |
3 |
| Spring 2020-2021 |
Deep Learning |
3 |
| Spring 2019-2020 |
Deep Learning |
3 |
| Spring 2018-2019 |
Deep Learning |
3 |
| Spring 2002-2003 |
Neural Networks |
3 |
| Spring 2000-2001 |
Neural Networks |
3 |
|
| Prerequisite: (CS 512 - Masters - Min Grade D |
| or CS 512 - Doctorate - Min Grade D |
| or EE 566 - Masters - Min Grade D |
| or EE 566 - Doctorate - Min Grade D) |
| Corequisite: __ |
| ECTS Credit: 10 ECTS
(ENGINEERING: / BASIC:)
|
| General Requirements: |
|
|
| |
