# Helping Spiking Neural Networks Can Learn to Learn

- Show: [EE Times Current](https://hardwarepodcasts.com/podcast/ee-times-current)
- Published: 2024-02-16
- Length: 45m
- Page: https://hardwarepodcasts.com/podcast/ee-times-current/2024-02-16-helping-spiking-neural-networks-can-learn-to-learn
- Listen: https://podcast.show/aspencore/episode/130925097/

## Summary

Professor Emre Neftci, director of the Neuromorphic Software Ecosystems group at the Peter Grünberg Institute (PGI) within the Jülich Research Centre, explains how surrogate gradient networks make backpropagation compatible with spiking neural networks. He details how 'learning to learn' algorithms address device variability in emerging hardware like memristors and solve catastrophic forgetting in online systems. The discussion highlights applications in low-latency robotics, brain-machine interfaces for prosthetics, and energy-efficient smart city vision processing.

## Chapters

- [0:03](https://hardwarepodcasts.com/podcast/ee-times-current/2024-02-16-helping-spiking-neural-networks-can-learn-to-learn#t=3) Introduction: Emre Neftci and Surrogate Gradients
- [3:28](https://hardwarepodcasts.com/podcast/ee-times-current/2024-02-16-helping-spiking-neural-networks-can-learn-to-learn#t=208) Surrogate Gradient Networks and Spiking Neural Networks
- [8:56](https://hardwarepodcasts.com/podcast/ee-times-current/2024-02-16-helping-spiking-neural-networks-can-learn-to-learn#t=536) Learning to Learn and Catastrophic Forgetting
- [11:35](https://hardwarepodcasts.com/podcast/ee-times-current/2024-02-16-helping-spiking-neural-networks-can-learn-to-learn#t=695) Handling Device Variability in Memristors
- [15:04](https://hardwarepodcasts.com/podcast/ee-times-current/2024-02-16-helping-spiking-neural-networks-can-learn-to-learn#t=904) Neuromorphic Applications: Robotics and Prosthetics
- [19:22](https://hardwarepodcasts.com/podcast/ee-times-current/2024-02-16-helping-spiking-neural-networks-can-learn-to-learn#t=1162) Smart City Vision Processing
- [23:09](https://hardwarepodcasts.com/podcast/ee-times-current/2024-02-16-helping-spiking-neural-networks-can-learn-to-learn#t=1389) Commentary: Catastrophic Forgetting and Memory Systems
- [36:43](https://hardwarepodcasts.com/podcast/ee-times-current/2024-02-16-helping-spiking-neural-networks-can-learn-to-learn#t=2203) Prophecy and Qualcomm Partnership for Smartphones

## Topics

- [Embedded firmware](https://hardwarepodcasts.com/topic/embedded-firmware)
- [AI & machine learning](https://hardwarepodcasts.com/topic/ai-and-machine-learning)
- [Chips, FPGAs & semiconductors](https://hardwarepodcasts.com/topic/chips-and-fpgas)
- [Medical & health devices](https://hardwarepodcasts.com/topic/medical-devices)
- [Energy & climate tech](https://hardwarepodcasts.com/topic/energy-and-climate-tech)

## Most relevant to

early-stage companies

## Mentioned

- Peter Grünberg Institute (company)
- Jülich Research Centre (company)
- EPF Lausanne (company)
- Surrogate Gradient Networks (other)
- Spiking Neural Networks (other)
- Memristors (chip)
- Prophecy (company)
- Qualcomm (company)
- Snapdragon AI chip (product)

## Citing this page

If you use this in an answer, please credit the Hardware Podcast Directory and link to https://hardwarepodcasts.com/podcast/ee-times-current/2024-02-16-helping-spiking-neural-networks-can-learn-to-learn. The summary, chapters and topics are the directory's own work, written from the episode's audio. The episode itself, its title and its audio belong to EE Times Current.