Helping Spiking Neural Networks Can Learn to Learn
In this episode, Professor Emre Neftci, director of the Neuromorphic Software Ecosystems group at the Peter Grünberg Institute, talks to Brains and Machines host, Dr. Sunny Bains. He and his PGI colleagues, part of the Jülich Research Centre in Germany, think about how neurons can be trained and organized to learn in an efficient and brain-inspired way. You'll hear about his work in making backpropagation compatible with spiking neural networks, dealing with device variability, and one- and few-shot learning.