Syllabus for Brain-inspired Computing
Open online course, Fall 2021 (PDF version)
Responsible: Dr. Zhibin Zhang, Division of Solid-State Electronics, Department of Electrical Engineering, The Ångström Laboratory. 070 4250 820. firstname.lastname@example.org
Dates and time: 1st Nov. - 30th Dec. 2021, 4 weeks.
Virtual classroom: online with Zoom, https://uu-se.zoom.us/j/ 658 758 7424
Main fields of study: Electronics, engineering sciences, physics, computer science, neuroscience.
Participants: The course will target participants with a Bachelor degree in engineering, electronics, natural sciences, mathematics or a similar subject field.
Course materials: presentation, assignments, a limited amount of articles
Maximal number of participants: 80
Aim and scope
The general aim of this course is to provide the participants basic knowledge of how the brain, as a natural powerful analogue computer, performs cognitive processes such as associative memory and recognition. This course concerns the emerging neuromorphic computing for potential applications in digitalization and connection in industry, Industry 4.0, AI, Big Data, self-driving vehicles, etc.
Through the completion of the course, the participants should be able to understand how the human brain performs cognitive processes and how the working principles are applied to spiking neural network (SNN). In detail, the participants shall be able to
- understand the electrical behaviors of a single neuron and synaptic connections,
- be familiar with the characteristic features of neuronal populations,
- describe how the brain performs cognitive processes, e.g., learning, memory and recognition,
- explain how the basic working principles of the brain are applied in SNN.
The contents include a series of lectures and assignments in (1) the introduction of the brain-inspired neuromorphic computing, (2) the biological facts and characteristic electrical behaviors of individual neurons, (3) the biological facts and characteristic electrical behaviors of synaptic connections, (4) the fundamentals of neuronal population and perceptions, (6) the learning process with synapses, (7) the models of cognitive processes, e.g., associative memory and recognition, (9)the concepts of spiking neural network, the third generation of artificial neural network model. Assignments follow all lectures.
|Lecture-1||Recorded video||Background, and mathematical preliminaries||Zhibin Zhang|
|Lecture-2||Recorded video||A glance from the brain to the cell||Zhibin Zhang|
|Lecture-3||Recorded video||The neuron and the physical models||Libo Chen|
|Lecture-4||Recorded video||The synaptic connections between neurons||Chenyu Wen|
|Lecture-5||Recorded video||Learning with synaptic plasticity||Chenyu Wen|
|Lecture-6||Recorded video||The spiking neural network - a bio-plausible computation model||Viktor Mattsson|
|Lecture-7||Recorded video||Population of neurons||Zhibin Zhang|
|Lecture-8||Recorded video||Memory and recognition||Zhibin Zhang|
|Tutorial||10-12 am, 30th, Nov. 2021||Tutorial and Q&A (ZOOM https://uu-se.zoom.us/j/ 658 758 7424)||Zhibin Zhang, Libo Chen|
All course materials will be open on Studium (UU) from 1st Nov., 2021
The course is mainly based on the following literatures:
- An Introductory Course in Computational Neuroscience, Miller, Paul, 2018, ISBN 9780262038256
- Neuronal Dynamics, Gerstner, Wulfram, 2014, ISBN 9781107635197
- B. Rajendran, etc. “Low-power neuromorphic hardware for signal processing applications”, IEEE Signal Processing Magzine, Nov 2019
- Tavanaei, M. Ghodrati, S. R. Kheradpisheh, T. Masquelier, and A. Maida, “Deep learning in spiking neural networks,” Neural Networks, vol. 111, pp. 47–63, 2019, doi: 10.1016/j.neunet.2018.12.002.
- J. H. Lee, T. Delbruck, and M. Pfeiffer, “Training deep spiking neural networks using backpropagation,” Front. Neurosci., vol. 10, no. NOV, 2016, doi: 10.3389/fnins.2016.00508.