Optimal Oscillator Memory Networks
Pages 81 - 83
Abstract
Associative memory [4, 11, 15] is an important building block in neural computing, neuromorphic engineering, and, in general, collective-state computing. Based on phasor associative memories (PAM) [9], a type of phasor neural network (PNN), we present a novel oscillator neural network (ONN) model that uses subharmonic injection locking (SHIL) [8, 14] to restrict the phase of the oscillators to Q discrete values. We show that the presence of SHIL increases the memory capacity of an ONN. Specifically, we find that for certain values of Q, the associative memory achieves greater capacity and information storage than previous models. To our knowledge, the proposed model is the first to validate the capacity analysis of Q-state PAM networks [2] through simulation and provide a model of how to implement such a memory on a physical system.
References
[1]
Toshio Aoyagi. 1995. Network of neural oscillators for retrieving phase information. Physical review letters 74, 20 (1995), 4075.
[2]
J. Cook. 1989. The mean-field theory of a Q-state neural network model. Journal of Physics A: Mathematical and General 22 (6 1989), 2057–2067. Issue 12. https://doi.org/10.1088/0305-4470/22/12/011
[3]
E. Paxon Frady and Friedrich T. Sommer. 2019. Robust computation with rhythmic spike patterns. Proceedings of the National Academy of Sciences of the United States of America (2019). https://doi.org/10.1073/pnas.1902653116
[4]
John J Hopfield. 1982. Neural networks and physical systems with emergent collective computational abilities. Proceedings of the national academy of sciences 79, 8 (1982), 2554–2558.
[5]
Frank C. Hoppensteadt and Eugene M. Izhikevich. 2000. Pattern recognition via synchronization in phase-locked loop neural networks. IEEE Transactions on Neural Networks 11 (5 2000), 734–738. Issue 3. https://doi.org/10.1109/72.846744
[6]
Ankit Kumar and Pritiraj Mohanty. 2017. Autoassociative memory and pattern recognition in micromechanical oscillator network. Scientific reports 7, 1 (2017), 1–9.
[7]
Dmitri E Nikonov, Gyorgy Csaba, Wolfgang Porod, Tadashi Shibata, Danny Voils, Dan Hammerstrom, Ian A Young, and George I Bourianoff. 2015. Coupled-oscillator associative memory array operation for pattern recognition. IEEE Journal on Exploratory Solid-State Computational Devices and Circuits 1(2015), 85–93.
[8]
Takashi Nishikawa, Frank C. Hoppensteadt, and Ying Cheng Lai. 2004. Oscillatory associative memory network with perfect retrieval. Physica D: Nonlinear Phenomena 197 (10 2004), 134–148. Issue 1-2. https://doi.org/10.1016/J.PHYSD.2004.06.011
[9]
André J Noest. 1987. Phasor neural networks. Proceedings of the 1987 International Conference on Neural Information Processing Systems, 584–591.
[10]
André J Noest. 1988. Discrete-state phasor neural networks. Physical Review A 38, 4 (1988), 2196.
[11]
Günther Palm. 1980. On associative memory. Biological cybernetics 36, 1 (1980), 19–31.
[12]
Karl Steinbuch. 1961. Die lernmatrix. Kybernetik 1, 1 (1961), 36–45.
[13]
Jacob Torrejon, Mathieu Riou, Flavio Abreu Araujo, Sumito Tsunegi, Guru Khalsa, Damien Querlioz, Paolo Bortolotti, Vincent Cros, Kay Yakushiji, Akio Fukushima, 2017. Neuromorphic computing with nanoscale spintronic oscillators. Nature 547, 7664 (2017), 428–431.
[14]
Tianshi Wang and Jaijeet Roychowdhury. 2019. OIM: Oscillator-based Ising machines for solving combinatorial optimisation problems. In International Conference on Unconventional Computation and Natural Computation. Springer, 232–256.
[15]
David J Willshaw, O Peter Buneman, and Hugh Christopher Longuet-Higgins. 1969. Non-holographic associative memory. Nature 222, 5197 (1969), 960–962.
Recommendations
Towards memory-efficient processing-in-memory architecture for convolutional neural networks
LCTES '17Convolutional neural networks (CNNs) are widely adopted in artificial intelligent systems. In contrast to conventional computing centric applications, the computational and memory resources of CNN applications are mixed together in the network weights. ...
Towards memory-efficient processing-in-memory architecture for convolutional neural networks
LCTES 2017: Proceedings of the 18th ACM SIGPLAN/SIGBED Conference on Languages, Compilers, and Tools for Embedded SystemsConvolutional neural networks (CNNs) are widely adopted in artificial intelligent systems. In contrast to conventional computing centric applications, the computational and memory resources of CNN applications are mixed together in the network weights. ...
Reading spin-torque memory with spin-torque sensors
NANOARCH '13: Proceedings of the 2013 IEEE/ACM International Symposium on Nanoscale ArchitecturesSpin-Transfer-Torque Magnetic Random Access Memory (STT-MRAM) is a promising candidate for future on-chip memory, owing to its high-density, zero-leakage and energy efficiency. In a conventional STT-MRAM cache write operations consume larger energy as ...
Comments
Information & Contributors
Information
Published In
Copyright © 2022 Owner/Author.
Permission to make digital or hard copies of part or all 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 third-party components of this work must be honored. For all other uses, contact the Owner/Author.
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 03 May 2022
Check for updates
Author Tags
Qualifiers
- Extended-abstract
- Research
- Refereed limited
Conference
NICE 2022
NICE 2022: Neuro-Inspired Computational Elements Conference
March 28 - April 1, 2022
Virtual Event, USA
Acceptance Rates
Overall Acceptance Rate 25 of 40 submissions, 63%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 77Total Downloads
- Downloads (Last 12 months)22
- Downloads (Last 6 weeks)1
Reflects downloads up to 01 Sep 2024
Other Metrics
Citations
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.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format