CS 557 - Computational Intelligence and Machine Learning

Description:
Introducing intelligent systems: artificial neural networks, deep learning, evolutionary computation, fuzzy systems, swarm intelligence, and hybridizations of the above techniques. We will look at these techniques from a machine learning perspective. CS 457 and CS 557 are layered courses; students may not receive credit for both.

Prerequisites:
Prerequisite: CS 528.

Credits:
(4)

Learner Outcomes:
Upon successful completion of this course, the student will be able to:

Compare the development and history of computational and artificial intelligence as compared to the Turing Machine and conventional computing.
Describe the basic concepts of artificial neural networks: learning, classification, pattern recognition, memory, logical operations.
Build neural classifiers and pattern recognition models.
Describe the use of feedback in neural networks for optimization.
Describe associative memories and, their use in clustering, classification and visualization of very large data sets.
Define genetic algorithms and their use in optimization.
Discuss the basic features of swarm intelligence and ant colony optimization.
Compare fuzzy logic to binary logic and analyze the use of fuzzy rules for expert systems and the architecture of fuzzy neural systems.
Describe radial function neural networks.
Analyze the computational power of neural networks and determine the limits of neural computing.
Lead group discussions pertaining to building neural classifiers and pattern recognition models. [graduate level]
Prepare presentation for demonstrating basic concepts of learning, classification, pattern recognition, memory, and logical operations. [graduate level]
Research and present information pertaining to associative memories and their use in clustering, classification, and visualization of very large data sets. [graduate level]

Learner Outcomes Approval Date:
4/5/18

Anticipated Course Offering Terms and Locations:
Winter Locations Ellensburg