Cluster 11
Brain-Inspired Machine Learning*
Instructors:
Jason Eshraghian, PhD
UCSC Electrical and Computer Engineering
Binh Nguyen
UCSC Electrical and Computer Engineering
Prerequisites: Algebra II, Computer Science
Preferred: Pre-Calculus
This is a FIRST CHOICE cluster option only
Summary: This course explores how to make machine learning algorithms as efficient as the brain. Topics to be covered include logistic and linear regression, neural networks, deep learning, computer vision with convolutional neural networks, sequence-based models, transformers, low-power machine learning techniques, low-precision and compressed models, and spiking neural networks.
Brain-inspired Machine Learning
Machine learning is rapidly changing how we interact with the world. Training large-scale machine learning models is incredibly expensive. For example, the power bill of training ChatGPT exceeded millions of dollars, whereas our brains can operate within a power budget of 10-20 watts. There are many applications where this amount of energy is not available, such as in mobile phones, portable robotics and in autonomous vehicles. This course will introduce the basics of machine learning, neural networks, and how these can be enhanced using principles from the brain. Emphasis will be placed on low-power machine learning techniques. The lectures will focus on training and using neural networks in Python. At the completion of this course, students will be able to define and apply fundamental concepts in machine learning to processing images and language.
