"Artificial Intelligence is the new electricity."
- Andrew Ng, Stanford Adjunct Professor
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, reinforcement learning and control. Explore recent applications of machine learning and design and develop algorithms for machines.
This course is now FULL, but you can enroll in the waitlist. In the case that a spot becomes available, Student Services will contact you. Make sure you have submitted your NDO application and required documents to be considered.
- Basics concepts of machine learning
- Generative learning algorithms
- Evaluating and debugging learning algorithms
- Bias/variance tradeoff and VC dimension
- Value and policy iteration
- Q-learning and value function approximation
Note on Course Availability
This course is typically offered Autumn, Spring and Summer quarters.
The course schedule is displayed for planning purposes – courses can be modified, changed, or cancelled. Course availability will be considered finalized on the first day of open enrollment. For quarterly enrollment dates, please refer to our graduate certificate homepage.
3.0 - 4.0
Students enrolling under the non degree option are required to take the course for 4.0 units.
Linear algebra, basic probability and statistics.
We strongly recommend that you review the first problem set before enrolling. If this material looks unfamiliar or too challenging, you may find this course too difficult.