ICS 485: Machine Learning

​

ICS 485: Machine Learning

 
Course Information
Class/Laboratory Schedule: 

Three 50-minutes lectures per week (3-0-3)

Designation: 
 Elective Course
Course Level: 
 Undergraduate
Prerequisites
Prerequisite(s) by Topic: 
  • Basics of logic and counting
  • Discrete probability
  • Fundamental programming constructs
  • Algorithms and problem-solving
  • Fundamental data structures
  • Recursion
  • Basic algorithmic analysis
  • Fundamental issues in intelligent systems
  • Search and constraint satisfaction
  • Knowledge representation and reasoning
Prerequisite Courses: 
Senior Standing
Catalog Description: 

Introduction to machine learning; Concept learning; Supervised learning - decision tree learning; Unsupervised learning - clustering. Artificial neural networks. Evaluating hypotheses; Bayesian learning; Computational learning theory; Instance based learning. Genetic algorithms; Learning sets of rules - Inductive Logic Programming; Reinforcement learning; Analytical learning;

Textbook(s): 

Machine Learning, Tom Mitchell, McGraw Hill, 1997.

Reference(s) and Other Material: 
  • Pattern Recognition and Machine Learning, Christopher Bishop, Springer, 2006.
  • Element of Machine Learning, Pat Langley, Morgan Kaufmann Publishers, 1995.
Course Outcomes: 

After completion of this course, the student shall be able to:

  • Understand the definition, theory and methodology of inductive learning.
  • Understand the definition and some techniques of clustering.
  • Understand the basics and some learning aspect of neural networks.
  • Understand the basics and some learning aspect of genetic algorithms.
  • Understand the basics of reinforcement learning.
  • Understand the basics of explanation based learning.
  • Practice the application of existing, as well as more recent machine learning approaches to real-world data, and evaluate/compare these approached.
Topics Covered: 
  • Concept Learning
  • Decision Tree Learning
  • Clustering
  • Artificial Neural Networks
  • Evaluating Hypotheses, Over fitting
  • Bayesian Learning
  • Instance Based Learning
  • Computational Learning Theory
  • Bayesian (Belief) Networks
  • Genetic Algorithms
  • Learning Sets of Rules
  • Reinforcement Learning
  • Analytical Learning​