short-paper

Neko: a Library for Exploring Neuromorphic Learning Rules

Authors:

Fangfang XiaAuthors Info & Claims

ICONS 2021: International Conference on Neuromorphic Systems 2021

Article No.: 9, Pages 1 - 5

https://doi.org/10.1145/3477145.3477155

Published: 13 October 2021 Publication History

Abstract

The field of neuromorphic computing is in a period of active exploration. While many tools have been developed to simulate neuronal dynamics or convert deep networks to spiking models, general software libraries for learning rules remain underexplored. This is partly due to the diverse, challenging nature of efforts to design new learning rules, which range from encoding methods to gradient approximations, from population approaches that mimic the Bayesian brain to constrained learning algorithms deployed on memristor crossbars. To address this gap, we present Neko, a modular, extensible library with a focus on aiding the design of new learning algorithms. We demonstrate the utility of Neko in three exemplar cases: online local learning, probabilistic learning, and analog on-device learning. Our results show that Neko can replicate the state-of-the-art algorithms and, in one case, lead to significant outperformance in accuracy and speed. Further, it offers tools including gradient comparison that can help develop new algorithmic variants. Neko is an open source Python library that supports PyTorch and TensorFlow backends.

References

[1]

Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, 2016. Tensorflow: A system for large-scale machine learning. In 12th {USENIX} symposium on operating systems design and implementation ({OSDI} 16). 265–283.

[2]

Laurence Aitchison, Jannes Jegminat, Jorge Aurelio Menendez, Jean-Pascal Pfister, Alexandre Pouget, and Peter E Latham. 2021. Synaptic plasticity as Bayesian inference. Nature Neuroscience 24, 4 (2021), 565–571.

[3]

Mohamed Akrout, Collin Wilson, Peter C Humphreys, Timothy Lillicrap, and Douglas Tweed. 2019. Deep learning without weight transport. arXiv preprint arXiv:1904.05391(2019).

[4]

Fabien Alibart, Ligang Gao, Brian D Hoskins, and Dmitri B Strukov. 2012. High precision tuning of state for memristive devices by adaptable variation-tolerant algorithm. Nanotechnology 23, 7 (Jan 2012), 075201. https://doi.org/10.1088/0957-4484/23/7/075201

[5]

Christophe Andrieu and Johannes Thoms. 2008. A tutorial on adaptive MCMC. Statistics and Computing 18, 4 (01 Dec 2008), 343–373. https://doi.org/10.1007/s11222-008-9110-y

[6]

Trevor Bekolay, James Bergstra, Eric Hunsberger, Travis DeWolf, Terrence C Stewart, Daniel Rasmussen, Xuan Choo, Aaron Voelker, and Chris Eliasmith. 2014. Nengo: a Python tool for building large-scale functional brain models. Frontiers in Neuroinformatics 7 (2014), 48.

[7]

Guillaume Bellec, Franz Scherr, Anand Subramoney, Elias Hajek, Darjan Salaj, Robert Legenstein, and Wolfgang Maass. 2020. A solution to the learning dilemma for recurrent networks of spiking neurons. Nature Communications 11, 1 (2020), 1–15.

[8]

Nicholas T Carnevale and Michael L Hines. 2006. The NEURON book. Cambridge University Press.

[9]

François Chollet 2015. Keras. https://keras.io.

[10]

Will Dabney, Zeb Kurth-Nelson, Naoshige Uchida, Clara Kwon Starkweather, Demis Hassabis, Rémi Munos, and Matthew Botvinick. 2020. A distributional code for value in dopamine-based reinforcement learning. Nature 577, 7792 (2020), 671–675.

[11]

Andrew P Davison, Daniel Brüderle, Jochen M Eppler, Jens Kremkow, Eilif Muller, Dejan Pecevski, Laurent Perrinet, and Pierre Yger. 2009. PyNN: a common interface for neuronal network simulators. Frontiers in Neuroinformatics 2 (2009), 11.

[12]

Julien Dupeyroux. 2021. A toolbox for neuromorphic sensing in robotics. arxiv:2103.02751 [cs.RO]

[13]

Elliot J Fuller, Scott T Keene, Armantas Melianas, Zhongrui Wang, Sapan Agarwal, Yiyang Li, Yaakov Tuchman, Conrad D James, Matthew J Marinella, J Joshua Yang, 2019. Parallel programming of an ionic floating-gate memory array for scalable neuromorphic computing. Science 364, 6440 (2019), 570–574.

[14]

Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. In Proceedings of The 33rd International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 48), Maria Florina Balcan and Kilian Q. Weinberger (Eds.). PMLR, New York, New York, USA, 1050–1059. http://proceedings.mlr.press/v48/gal16.html

[15]

J. Garofolo, Lori Lamel, W. Fisher, Jonathan Fiscus, D. Pallett, N. Dahlgren, and V. Zue. 1992. TIMIT Acoustic-phonetic Continuous Speech Corpus. Linguistic Data Consortium (11 1992).

[16]

Marc-Oliver Gewaltig and Markus Diesmann. 2007. Nest (neural simulation tool). Scholarpedia 2, 4 (2007), 1430.

[17]

Alex Graves. 2011. Practical Variational Inference for Neural Networks. In Proceedings of the 24th International Conference on Neural Information Processing Systems (Granada, Spain) (NIPS’11). Curran Associates Inc., Red Hook, NY, USA, 2348–2356.

Digital Library

[18]

Sam Greydanus. 2020. Scaling down Deep Learning. arxiv:2011.14439 [cs.LG]

[19]

Peter D. Hoff. 2009. A First Course in Bayesian Statistical Methods (1st ed.). Springer Publishing Company, Incorporated.

[20]

Miao Hu, Hai Li, Yiran Chen, Qing Wu, Garrett S Rose, and Richard W Linderman. 2014. Memristor crossbar-based neuromorphic computing system: A case study. IEEE Transactions on Neural Networks and Learning Systems 25, 10(2014), 1864–1878.

[21]

Mohammad Kachuee, Shayan Fazeli, and Majid Sarrafzadeh. 2018. Ecg heartbeat classification: A deep transferable representation. In 2018 IEEE International Conference on Healthcare Informatics (ICHI). IEEE, 443–444.

[22]

David C. Knill and Alexandre Pouget. 2004. The Bayesian brain: the role of uncertainty in neural coding and computation. Trends in Neurosciences 27, 12 (01 Dec 2004), 712–719. https://doi.org/10.1016/j.tins.2004.10.007

[23]

Yann LeCun. 1998. The MNIST database of handwritten digits. http://yann. lecun. com/exdb/mnist/(1998).

[24]

Jun Haeng Lee, Tobi Delbruck, and Michael Pfeiffer. 2016. Training deep spiking neural networks using backpropagation. Frontiers in Neuroscience 10 (2016), 508.

[25]

Can Li, Daniel Belkin, Yunning Li, Peng Yan, Miao Hu, Ning Ge, Hao Jiang, Eric Montgomery, Peng Lin, Zhongrui Wang, 2018. Efficient and self-adaptive in-situ learning in multilayer memristor neural networks. Nature communications 9, 1 (2018), 1–8.

[26]

Timothy P Lillicrap, Daniel Cownden, Douglas B Tweed, and Colin J Akerman. 2016. Random synaptic feedback weights support error backpropagation for deep learning. Nature communications 7, 1 (2016), 1–10.

[27]

Timothy P Lillicrap, Adam Santoro, Luke Marris, Colin J Akerman, and Geoffrey Hinton. 2020. Backpropagation and the brain. Nature Reviews Neuroscience 21, 6 (2020), 335–346.

[28]

Chit-Kwan Lin, Andreas Wild, Gautham N Chinya, Yongqiang Cao, Mike Davies, Daniel M Lavery, and Hong Wang. 2018. Programming spiking neural networks on Intel’s Loihi. Computer 51, 3 (2018), 52–61.

[29]

Owen Marschall, Kyunghyun Cho, and Cristina Savin. 2020. A unified framework of online learning algorithms for training recurrent neural networks. Journal of Machine Learning Research 21, 135 (2020), 1–34.

[30]

Radford M. Neal. 2011. MCMC Using Hamiltonian Dynamics. CRC Press. https://doi.org/10.1201/b10905-7

[31]

Emre O Neftci, Hesham Mostafa, and Friedemann Zenke. 2019. Surrogate gradient learning in spiking neural networks: Bringing the power of gradient-based optimization to spiking neural networks. IEEE Signal Processing Magazine 36, 6 (2019), 51–63.

[32]

Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, [n.d.]. PyTorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703([n. d.]).

[33]

Balint Petro, Nikola Kasabov, and Rita M. Kiss. 2020. Selection and Optimization of Temporal Spike Encoding Methods for Spiking Neural Networks. IEEE Transactions on Neural Networks and Learning Systems 31, 2 (Feb. 2020), 358–370. https://doi.org/10.1109/tnnls.2019.2906158

[34]

P. J. Rossky, J. D. Doll, and H. L. Friedman. 1978. Brownian dynamics as smart Monte Carlo simulation. The Journal of Chemical Physics 69, 10 (1978), 4628–4633. https://doi.org/10.1063/1.436415 arXiv:https://doi.org/10.1063/1.436415

[35]

Bodo Rueckauer, Connor Bybee, Ralf Goettsche, Yashwardhan Singh, Joyesh Mishra, and Andreas Wild. 2021. NxTF: An API and Compiler for Deep Spiking Neural Networks on Intel Loihi. arXiv preprint arXiv:2101.04261(2021).

[36]

Bodo Rueckauer and Shih-Chii Liu. 2018. Conversion of analog to spiking neural networks using sparse temporal coding. In 2018 IEEE International Symposium on Circuits and Systems (ISCAS). IEEE, 1–5.

[37]

Bodo Rueckauer, Iulia-Alexandra Lungu, Yuhuang Hu, Michael Pfeiffer, and Shih-Chii Liu. 2017. Conversion of continuous-valued deep networks to efficient event-driven networks for image classification. Frontiers in Neuroscience 11 (2017), 682.

[38]

João Sacramento, Rui Ponte Costa, Yoshua Bengio, and Walter Senn. 2018. Dendritic cortical microcircuits approximate the backpropagation algorithm. arXiv preprint arXiv:1810.11393(2018).

[39]

Jun Sawada, Filipp Akopyan, Andrew S Cassidy, Brian Taba, Michael V Debole, Pallab Datta, Rodrigo Alvarez-Icaza, Arnon Amir, John V Arthur, Alexander Andreopoulos, 2016. Truenorth ecosystem for brain-inspired computing: scalable systems, software, and applications. In SC’16: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE, 130–141.

[40]

Andrew Sornborger, Louis Tao, Jordan Snyder, and Anatoly Zlotnik. 2019. A pulse-gated, neural implementation of the backpropagation algorithm. In Proceedings of the 7th Annual Neuro-inspired Computational Elements Workshop. 1–9.

Digital Library

[41]

Marcel Stimberg, Romain Brette, and Dan FM Goodman. 2019. Brian 2, an intuitive and efficient neural simulator. eLife 8(2019), e47314.

[42]

Andy Thomas. 2013. Memristor-based neural networks. Journal of Physics D: Applied Physics 46, 9 (2013), 093001.

[43]

Peng Yao, Huaqiang Wu, Bin Gao, Jianshi Tang, Qingtian Zhang, Wenqiang Zhang, J Joshua Yang, and He Qian. 2020. Fully hardware-implemented memristor convolutional neural network. Nature 577, 7792 (2020), 641–646.

[44]

Elham Zamanidoost, Farnood M. Bayat, Dmitri Strukov, and Irina Kataeva. 2015. Manhattan rule training for memristive crossbar circuit pattern classifiers. In 2015 IEEE 9th International Symposium on Intelligent Signal Processing (WISP) Proceedings. 1–6. https://doi.org/10.1109/WISP.2015.7139171

[45]

Friedemann Zenke and Surya Ganguli. 2018. Superspike: Supervised learning in multilayer spiking neural networks. Neural computation 30, 6 (2018), 1514–1541.

Digital Library

Cited By

Ganguly CBezugam SAbs EPayvand MDey SSuri M(2024)Spike frequency adaptation: bridging neural models and neuromorphic applicationsCommunications Engineering10.1038/s44172-024-00165-93:1Online publication date: 1-Feb-2024
https://doi.org/10.1038/s44172-024-00165-9
Knight JNowotny T(2023)Easy and efficient spike-based Machine Learning with mlGeNNNeuro-Inspired Computational Elements Conference10.1145/3584954.3585001(115-120)Online publication date: 12-Apr-2023
https://doi.org/10.1145/3584954.3585001

Neko: a Library for Exploring Neuromorphic Learning Rules
1. Computer systems organization
  1. Architectures
    1. Other architectures
2. Computing methodologies
  1. Machine learning
    1. Machine learning approaches

Recommendations

Learning rules in spiking neural networks: A survey
Abstract
Spiking neural networks (SNNs) are a promising energy-efficient alternative to artificial neural networks (ANNs) due to their rich dynamics, capability to process spatiotemporal patterns, and low-power consumption. The complex ...
Effects of Noise on Leaky Integrate-and-Fire Neuron Models for Neuromorphic Computing Applications
Computational Science and Its Applications – ICCSA 2022
Abstract
Artificial neural networks (ANNs) have been extensively used for the description of problems arising from biological systems and for constructing neuromorphic computing models. The third generation of ANNs, namely, spiking neural networks (SNNs), ...
Introducing Astrocytes on a Neuromorphic Processor: Synchronization, Local Plasticity and Edge of Chaos
NICE '19: Proceedings of the 7th Annual Neuro-inspired Computational Elements Workshop

While there is still a lot to learn about astrocytes and their neuromodulatory role in the spatial and temporal integration of neuronal activity, their introduction to neuromorphic hardware is timely, facilitating their computational exploration in ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Other conferences

ICONS 2021: International Conference on Neuromorphic Systems 2021

July 2021

198 pages

ISBN:9781450386913

DOI:10.1145/3477145

Editors:
Thomas E. Potok
Oak Ridge National Laboratory
,
Melika Payvand
ETH Zurich
,
Catherine Schuman
Oak Ridge National Laboratory
,
Prasanna Date
Oak Ridge National Laboratory
,
Mutsumi Kimura
Nara Institute of Science and Technology
,
Cory Merkel
Rochester Institute of Technology
,
Brad Aimone
Sandia National Laboratories
,
Sonia Buckley
National Institute of Standards and Technology
,
Yiran Chen
Duke University
,
Gregory Cohen
Western Sydney University
,
Todd Hylton
University of California, San Diego
,
Mutsumi Kimura
Ryukoku University, Japan
,
Robert Patton
Oak Ridge National Laboratory
,
Melika Payvand
ETH Zurich
,
Robinson Pino
U.S. Department of Energy
,
Thomas Potok
Oak Ridge National Laboratory
,
Garrett Rose
University of Tennessee, Knoxville

Copyright © 2021 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 13 October 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Short-paper
Research
Refereed limited

Conference

ICONS 2021

ICONS 2021: International Conference on Neuromorphic Systems 2021

July 27 - 29, 2021

TN, Knoxville, USA

Acceptance Rates

Overall Acceptance Rate 13 of 22 submissions, 59%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
104
Total Downloads

Downloads (Last 12 months)25
Downloads (Last 6 weeks)4

Reflects downloads up to 13 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Ganguly CBezugam SAbs EPayvand MDey SSuri M(2024)Spike frequency adaptation: bridging neural models and neuromorphic applicationsCommunications Engineering10.1038/s44172-024-00165-93:1Online publication date: 1-Feb-2024
https://doi.org/10.1038/s44172-024-00165-9
Knight JNowotny T(2023)Easy and efficient spike-based Machine Learning with mlGeNNNeuro-Inspired Computational Elements Conference10.1145/3584954.3585001(115-120)Online publication date: 12-Apr-2023
https://doi.org/10.1145/3584954.3585001

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Media

Figures

Other

Tables

View Table of Contents