# Embracing the Efficiency of the Neuromorphic Hairball

- Show: [EE Times Current](https://hardwarepodcasts.com/podcast/ee-times-current)
- Published: 2024-12-06
- Length: 47m
- Page: https://hardwarepodcasts.com/podcast/ee-times-current/2024-12-06-embracing-the-efficiency-of-the-neuromorphic-hairball
- Listen: https://podcast.show/aspencore/episode/139399793/

## Summary

Dr. Katie Schumann of the University of Tennessee explains her work evolving highly recurrent, sparse spiking neural networks, which she calls 'hairballs,' using the EONs framework to achieve high efficiency with very few neurons. She discusses the trade-offs between evolving network structure and tuning parameters via local learning rules like STDP, and the challenges of training these complex topologies compared to feed-forward models. The conversation with Dr. Giulia D’Angelo and Professor Ralph Etienne-Cummings of Johns Hopkins University explores the partitioning between evolutionary algorithms and learning mechanisms, emphasizing the need for meta-learning and hardware-in-the-loop co-design with memristive technologies.

## Chapters

- [0:03](https://hardwarepodcasts.com/podcast/ee-times-current/2024-12-06-embracing-the-efficiency-of-the-neuromorphic-hairball#t=3) Introduction: Dr. Katie Schumann and the University of Tennessee
- [2:12](https://hardwarepodcasts.com/podcast/ee-times-current/2024-12-06-embracing-the-efficiency-of-the-neuromorphic-hairball#t=132) Schumann's Background: From Computer Science to Neuromorphic Hardware
- [5:13](https://hardwarepodcasts.com/podcast/ee-times-current/2024-12-06-embracing-the-efficiency-of-the-neuromorphic-hairball#t=313) EONs Framework: Evolving Sparse Recurrent 'Hairball' Networks
- [11:43](https://hardwarepodcasts.com/podcast/ee-times-current/2024-12-06-embracing-the-efficiency-of-the-neuromorphic-hairball#t=703) Training Challenges: Local Learning Rules and Meta-Learning
- [13:43](https://hardwarepodcasts.com/podcast/ee-times-current/2024-12-06-embracing-the-efficiency-of-the-neuromorphic-hairball#t=823) Co-Design: Memristive Hardware and Custom Architectures
- [21:35](https://hardwarepodcasts.com/podcast/ee-times-current/2024-12-06-embracing-the-efficiency-of-the-neuromorphic-hairball#t=1295) Hardware-in-the-Loop Evolution and FPGA Implementation
- [25:33](https://hardwarepodcasts.com/podcast/ee-times-current/2024-12-06-embracing-the-efficiency-of-the-neuromorphic-hairball#t=1533) Edge Applications and the Future of Neuromorphic Computing
- [29:11](https://hardwarepodcasts.com/podcast/ee-times-current/2024-12-06-embracing-the-efficiency-of-the-neuromorphic-hairball#t=1751) Discussion with Ralph Etienne-Cummings: Evolution vs. Learning
- [46:34](https://hardwarepodcasts.com/podcast/ee-times-current/2024-12-06-embracing-the-efficiency-of-the-neuromorphic-hairball#t=2794) Conclusion and Software Ecosystems

## Topics

- [Embedded firmware](https://hardwarepodcasts.com/topic/embedded-firmware)
- [Microcontrollers & dev platforms](https://hardwarepodcasts.com/topic/microcontrollers-and-platforms)
- [Chips, FPGAs & semiconductors](https://hardwarepodcasts.com/topic/chips-and-fpgas)
- [AI & machine learning](https://hardwarepodcasts.com/topic/ai-and-machine-learning)
- [Materials & manufacturing processes](https://hardwarepodcasts.com/topic/materials-and-processes)

## Most relevant to

early-stage companies

## Mentioned

- University of Tennessee (company)
- Oak Ridge National Laboratory (company)
- Johns Hopkins University (company)
- University College London (company)
- Czech Technical University (company)
- EONs (other)
- STDP (other)
- FPGA (chip)
- memristive technologies (material)
- SNNPy (other)
- Tonic (other)

## Related episodes from other shows

- [Episode 70!!! NPUs!!!!!!!!](https://hardwarepodcasts.com/podcast/the-circuit/2024-06-02-episode-70-npus) (The Circuit)
- [110. The Future of Neurology: Neural Interfaces Countering Neural Diseases](https://hardwarepodcasts.com/podcast/the-next-byte-podcast/2023-02-21-110-the-future-of-neurology-neural-interfaces-countering-neural-diseases) (The Next Byte Podcast)

## 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/2024-12-06-embracing-the-efficiency-of-the-neuromorphic-hairball. 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.