Computers are becoming smarter, as artificial intelligence and machine learning, a subset of AI, make tremendous strides in simulating human thinking. Creating computer systems that automatically improve with experience has many applications including robotic control, data mining, autonomous navigation, and bioinformatics.
This course provides a broad introduction to machine learning and statistical pattern recognition. Learn about both supervised and unsupervised learning as well as learning theory and adaptive control. Explore recent applications of machine learning and design and develop algorithms for machines.
Machine Learning
CS229
Description
Instructors
Andrew Ng, Associate Professor, Computer Science
Topics Include
- Basics concepts of machine learning
- Generative learning algorithms
- Evaluating and debugging learning algorithms
- Learning theory
- Clustering, dimensionality reduction, and kernel methods
- Reinforcement learning and control
Assignments
There will be 4 assigments and a term project.
Resources
Units
This course is offered for 3-4 units. Students enrolling under the non-degree option are required to take the course for 4 units.
Certificates and Degrees
Prerequisites
Linear algebra, basic probability and statistics.
Course Preview
We highly recommend watching the course preview to ensure you have the requisite background and understand the scope of material covered.
Tuition & Fees
For course tuition, reduced tuition (SCPD member companies and United States Armed forces), and fees, please click Tuition & Fees.
Please complete a
Course Inquiry
so that we may notify you when enrollment opens.
