Units:

12

Description:

This course focuses on the investigation of biologically plausible neural networks, with the objective of engineering silicon-based implementations possessing brain-like capabilities. This course will bring students up-to-date with neuroscientific progress toward “reverse-engineering the brain”, as interpreted by a computer architect. After this course, students will: 1) better understand the nature of the problem, 2) view it as a computer architecture research problem, 3) have a firm foundation for initiating study of the problem, and 4) participate in an effort to address this grand challenge!

This course introduces the foundational concepts of neuromorphic computing based on Spiking Neural Networks (SNN) and introduces leading research topics in this field. We cover a brief overview of neuroanatomy to introduce the reference design of the human brain. Discuss the relationship of artificial intelligence, artificial neural networks, and neuromorphic computing. Review some of the most noteworthy early neuromorphic computing projects going all the way back to von Neumann and Turing. The course will survey the leading research on neuromorphic computing, including neuromorphic analog circuits, memristors, and digital versions of spike-time-dependent plasticity (STDP). Also covered will be two recent experimental neuromorphic chips, specifically IBM’s TrueNorth and Intel’s Loihi. Students will work together as a team to perform a research project during the semester and present their findings at the end of semester.

In Spring 2019 this course is broadcast from the Silicon Valley campus. ECE Pittsburgh students attend classes synchronously with students in Silicon Valley.

Last Modified: 2020-12-01 1:21PM

Semesters offered:

• Spring 2021
• Spring 2020
• Spring 2019