Spike-based dynamic computing with asynchronous sensing-computing neuromorphic chip
- PMID: 38796464
- PMCID: PMC11127998
- DOI: 10.1038/s41467-024-47811-6
Spike-based dynamic computing with asynchronous sensing-computing neuromorphic chip
Abstract
By mimicking the neurons and synapses of the human brain and employing spiking neural networks on neuromorphic chips, neuromorphic computing offers a promising energy-efficient machine intelligence. How to borrow high-level brain dynamic mechanisms to help neuromorphic computing achieve energy advantages is a fundamental issue. This work presents an application-oriented algorithm-software-hardware co-designed neuromorphic system for this issue. First, we design and fabricate an asynchronous chip called "Speck", a sensing-computing neuromorphic system on chip. With the low processor resting power of 0.42mW, Speck can satisfy the hardware requirements of dynamic computing: no-input consumes no energy. Second, we uncover the "dynamic imbalance" in spiking neural networks and develop an attention-based framework for achieving the algorithmic requirements of dynamic computing: varied inputs consume energy with large variance. Together, we demonstrate a neuromorphic system with real-time power as low as 0.70mW. This work exhibits the promising potentials of neuromorphic computing with its asynchronous event-driven, sparse, and dynamic nature.
© 2024. The Author(s).
Conflict of interest statement
The authors declare no competing interests.
Figures
![Fig. 1](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/11127998/bin/41467_2024_47811_Fig1_HTML.gif)
![Fig. 2](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/11127998/bin/41467_2024_47811_Fig2_HTML.gif)
![Fig. 3](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/11127998/bin/41467_2024_47811_Fig3_HTML.gif)
![Fig. 4](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/11127998/bin/41467_2024_47811_Fig4_HTML.gif)
![Fig. 5](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/11127998/bin/41467_2024_47811_Fig5_HTML.gif)
Similar articles
-
Neuromorphic Sentiment Analysis Using Spiking Neural Networks.Sensors (Basel). 2023 Sep 6;23(18):7701. doi: 10.3390/s23187701. Sensors (Basel). 2023. PMID: 37765758 Free PMC article.
-
Surrogate gradients for analog neuromorphic computing.Proc Natl Acad Sci U S A. 2022 Jan 25;119(4):e2109194119. doi: 10.1073/pnas.2109194119. Proc Natl Acad Sci U S A. 2022. PMID: 35042792 Free PMC article.
-
Neuromorphic Engineering: From Biological to Spike-Based Hardware Nervous Systems.Adv Mater. 2020 Dec;32(52):e2003610. doi: 10.1002/adma.202003610. Epub 2020 Nov 9. Adv Mater. 2020. PMID: 33165986 Review.
-
Towards spike-based machine intelligence with neuromorphic computing.Nature. 2019 Nov;575(7784):607-617. doi: 10.1038/s41586-019-1677-2. Epub 2019 Nov 27. Nature. 2019. PMID: 31776490 Review.
-
Design Space Exploration of Hardware Spiking Neurons for Embedded Artificial Intelligence.Neural Netw. 2020 Jan;121:366-386. doi: 10.1016/j.neunet.2019.09.024. Epub 2019 Sep 26. Neural Netw. 2020. PMID: 31593842
References
-
- Schemmel, J. et al. A wafer-scale neuromorphic hardware system for large-scale neural modeling. In 2010 IEEE International Symposium on Circuits and Systems (ISCAS) 1947–1950 (IEEE, 2010).
MeSH terms
LinkOut - more resources
Full Text Sources