AHaH Computing–From Metastable Switches to Attractors to Machine Learning
Open accessThe DOI matches its Crossref record; 127 of the 131 references it cites were found in a registry or an index; 6 of the 40 sources its claims cite were checked for support.
Abstract
Modern computing architecture based on the separation of memory and processing leads to a well known problem called the von Neumann bottleneck, a restrictive limit on the data bandwidth between CPU and RAM. This paper introduces a new approach to computing we call AHaH computing where memory and processing are combined. The idea is based on the attractor dynamics of volatile dissipative electronics inspired by biological systems, presenting an attractive alternative architecture that is able to adapt, self-repair, and learn from interactions with the environment. We envision that both von Neumann and AHaH computing architectures will operate together on the same machine, but that the AHaH computing processor may reduce the power consumption and processing time for certain adaptive learning tasks by orders of magnitude. The paper begins by drawing a connection between the properties of volatility, thermodynamics, and Anti-Hebbian and Hebbian (AHaH) plasticity. We show how AHaH synaptic plasticity leads to attractor states that extract the independent components of applied data streams and how they form a computationally complete set of logic functions. After introducing a general memristive device model based on collections of metastable switches, we show how adaptive synaptic weights can be formed from differential pairs of incremental memristors. We also disclose how arrays of synaptic weights can be used to build a neural node circuit operating AHaH plasticity. By configuring the attractor states of the AHaH node in different ways, high level machine learning functions are demonstrated. This includes unsupervised clustering, supervised and unsupervised classification, complex signal prediction, unsupervised robotic actuation and combinatorial optimization of procedures-all key capabilities of biological nervous systems and modern machine learning algorithms with real world application.
Overview
CoChat Summary
# TL;DR
This paper introduces AHaH computing, an adaptive architecture that combines memory and processing using volatile, dissipative memristive devices and AHaH plasticity. Across software simulations, the authors report that AHaH nodes can support clustering, classification, signal prediction, robotic control, combinatorial optimization, and computationally complete logic.
# Key findings
- The paper argues that AHaH plasticity emerges from competing dissipative pathways and yields attractor states that can implement universal logic and machine learning functions.
- In clustering experiments, the AHaH clusterer was reported to achieve perfect performance with up to 18% noise at 100% pattern load, and greater than 90% vergence with up to 44% noise; at 200% pattern load, vergence fell below 90% after 12.5% noise.
- In classification benchmarks on Breast Cancer Wisconsin (Original), Census Income, MNIST Handwritten Digits, and Reuters-21578, the authors report that AHaH results “compare well” and “consistently match or exceed SVM performance.”
- For a temporal signal prediction proof of concept, the predictor was trained for 10,000 time steps and recursively predicted 300 steps into the future; for robotic arm control, the AHaH-guided arm was evaluated by the average total joint actuation needed to capture 100 moving targets.
# Methods
- All experiments were software simulations of AHaH nodes in Java; the paper states the code is open-sourced and tagged `PLOS_AHAH` on the master branch.
- The study used both functional and circuit models, with circuit simulations based on ideal components and a generalized memristive device model fitted to Ag-chalcogenide, AIST, GST, and WOx data; all AHaH node circuitry simulations used Ag-chalcogenide parameters unless otherwise noted.
- Main analyses included parameter sweeps for clustering, standard benchmark evaluation for classification, temporal prediction on a synthetic five-sinusoid signal, robotic arm control in a virtual environment, and strike-search optimization on a 64-city traveling salesman setup.
# Limitations
- The paper explicitly says it was not possible, given the broad scope, to provide much elaboration on some results, comparison with many other methods, or discussion of implications; it therefore open-sourced the code instead.
- The authors state that nonideal circuit effects such as parasitic impedances, signal delays, settling times, and memristor variability were not modeled, and should be addressed in future work.
- Evident from the text: most evidence is from simulations rather than physical hardware experiments, and the authors themselves note that experiments on physical devices had “not yet been carried out” for at least one memristor-series simulation result.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures




















Verification
Claims the paper makes
6 Valid · 18 Not valid · 21 Not checked · 183 Own results and interpretations
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“The modern memristor provides us with just such an adaptive pathway.”
§ AHaH Computing–From Metastable Switches to Attractors to Machine Learning > Theory > AHaH Memristor Circuit
What the sources say
- Not checked — no full text of the sourcecites [68] SH Jo, 2010, Nanoscale memristor device as synapse in neuromorphic systems, Nano Letters source
- Supportedcites [83] A Thomas, 2013, Memristor-based neural networks, Journal of Physics D: Applied Physics source
The Conclusions state that a memristor can realise synaptic behaviour, enabling adaptive analogue computer systems. This supports the claim that the memristor provides an adaptive pathway. (LLM, conf=0.92)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Several synapse-like memristors achieving ultra-low power pulsed synaptic updates have recently been reported [68], [70], [113].”
§ AHaH Computing–From Metastable Switches to Attractors to Machine Learning > Results and Discussion > Synaptic Power Consumption
What the sources say
- Not checked — no full text of the sourcecites [68] SH Jo, 2010, Nanoscale memristor device as synapse in neuromorphic systems, Nano Letters source
- Partly supportedcites [70] Li Y, Zhong Y, Xu L, Zhang J, Xu X, <etal>et al</etal>.. (2013) Ultrafast synaptic events in a chalcogenide memristor. Scientific Reports 3 doi:10.1038/srep01619. sourceExperimental — accuracy not yet measured
The Results section (‘Modification of synaptic efficacy and implementation of ultrafast STDP’; page unavailable) reports synaptic-weight updates using 30-ns electrical pulses in a chalcogenide memristor. The copy does not establish ultra-low power consumption for those updates; the Abstract’s picojoule-level figure describes an earlier study, not this device. (LLM, conf=0.78)
- Not checked — no full text of the sourcecites [113] D Kuzum, 2011, Nanoelectronic programmable synapses based on phase change materials for brain-inspired computing, Nano Letters source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“The energy consumption per synapse using roughly average voltage, pulse width, and resistance values taken from the pulse-driven memristive behavior plots in the three references results in a calculated energy consumption per synapse per update of ∼12 pJ, ∼67.5 pJ, and ∼56 pJ respectively.”
§ AHaH Computing–From Metastable Switches to Attractors to Machine Learning > Results and Discussion > Synaptic Power Consumption
What the sources say
- Not checked — no full text of the sourcecites [68] SH Jo, 2010, Nanoscale memristor device as synapse in neuromorphic systems, Nano Letters source
- Supportedcites [70] Li Y, Zhong Y, Xu L, Zhang J, Xu X, <etal>et al</etal>.. (2013) Ultrafast synaptic events in a chalcogenide memristor. Scientific Reports 3 doi:10.1038/srep01619. source
The Results section (page unavailable) gives the voltage, 30-ns pulse width, and roughly 2.2–3.0 kΩ resistance values used for synaptic-weight updates. Those values permit a roughly 12-pJ-per-update estimate; the citing sentence presents the energy figure as its own calculation, not as a number reported by Li et al. (LLM, conf=0.84)
- Not checked — no full text of the sourcecites [113] D Kuzum, 2011, Nanoelectronic programmable synapses based on phase change materials for brain-inspired computing, Nano Letters source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“After introducing a general memristive device model based on collections of metastable switches, we show how adaptive synaptic weights can be formed from differential pairs of incremental memristors.”
§ AHaH Computing–From Metastable Switches to Attractors to Machine Learning > Abstract
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“We further show that AHaH plasticity can be attained from simple memristive circuitry attempting to maximize circuit power dissipation in accordance with ideas in nonequilibrium thermodynamics.”
§ AHaH Computing–From Metastable Switches to Attractors to Machine Learning > Introduction
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
- Rests on an assumption not shown here.
116 more claims
Create a free account to see all 228 claims and to verify the 1 reference still open.
- It may state two separate claims as one. 48
- Probably not a substantial claim. 76
- The quote only partly states this claim. 4
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“As we have reported elsewhere [Nugent and W 2014], the binary encoding of a collection of AHaH nodes operating the FF-RU instruction can be used as the basis of a clustering algorithm.”
From From memristors to compositional machine learning: exploring neuromemristive algorithmic abstractions with the knowm API (2017) · cites this paper as Nugent and W 2014
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“The kT-RAM technology specification [Nugent and Molter 2017] describes multiple levels of abstraction and specialization needed to implement an Anti-Hebbian and Hebbian (AHaH) computing [Nugent and W 2014] compliant synaptic processor and integrate it into digital computing systems.”
From From memristors to compositional machine learning: exploring neuromemristive algorithmic abstractions with the knowm API (2017) · cites this paper as Nugent and W 2014
The cited source says what the claim attributes to it.
In the citing paper
“The result is an attractor state where the decision boundary splits the opposing distributions cleanly, forming a natural boundary that increases noise-tolerance and coincides with statistical techniques such as ICA and support vector maximization between pattern classes [Nugent and W 2014].”
From From memristors to compositional machine learning: exploring neuromemristive algorithmic abstractions with the knowm API (2017) · cites this paper as Nugent and W 2014
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
Maximum Likelihood from Incomplete Data Via the EM Algorithm
Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1977.tb01600.x · Cited by 50,444
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
UCI Machine Learning Repository
Asuncion, A. (2007) · Medical Entomology and Zoology · Cited by 25,410
(1967) · Cited by 23,719
Neural networks and physical systems with emergent collective computational abilities.
Hopfield, J. J. (1982) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.79.8.2554 · Cited by 19,270
Least squares quantization in PCM
Lloyd, S. (1982) · IEEE Transactions on Information Theory · doi:10.1109/tit.1982.1056489 · Cited by 15,836
Jain, A. K., Murty, M. N., & Flynn, P. J. (1999) · ACM Computing Surveys · doi:10.1145/331499.331504 · Cited by 13,199
The perceptron: A probabilistic model for information storage and organization in the brain.
Rosenblatt, F. (1958) · Psychological Review · doi:10.1037/h0042519 · Cited by 12,280
A training algorithm for optimal margin classifiers
Boser, B. E., Guyon, I. M., & Vapnik, V. N. (1992) · Proceedings of the fifth annual workshop on Computational learning theory · doi:10.1145/130385.130401 · Cited by 11,992
The chemical basis of morphogenesis
Turing, A. M. (1952) · Philosophical Transactions of the Royal Society of London. Series B, Biological Sciences · doi:10.1098/rstb.1952.0012 · Cited by 11,733 · cited 1×
“Turing spent the last two years of his life working on mathematical biology and published a paper titled ‘The chemical basis of morphogenesis’ in 1952 [85].”
BackgroundMemristor—The Missing Circuit Element
Chua, L. (1971) · IEEE Transactions on Circuit Theory · doi:10.1109/tct.1971.1083337 · Cited by 10,268 · cited 1×
“In 1971, Chua postulated on the basis of symmetry arguments the existence of a missing fourth two terminal circuit element called a memristor ( memory resistor ), where the resistance of the memristor depends on the integral of the input applied to the terminals [33,34].”
BackgroundOn computable numbers, with an application to the entscheidungsproblem
Turing, A. M. (1937) · Proceedings of the London Mathematical Society · doi:10.1112/plms/s2-42.1.230 · Cited by 8,283
Independent component analysis, A new concept?
Comon, P. (1994) · Signal Processing · doi:10.1016/0165-1684(94)90029-9 · Cited by 8,205
Text categorization with Support Vector Machines: Learning with many relevant features
Joachims, T. (1998) · Lecture Notes in Computer Science · doi:10.1007/bfb0026683 · Cited by 7,999
Swarm Intelligence: From Natural to Artificial Systems
Bonabeau, E., Dorigo, M., & Theraulaz, G. (1999) · Oxford University Press eBooks · doi:10.1093/oso/9780195131581.001.0001 · Cited by 6,435
Supervised Machine Learning: A Review of Classification Techniques
Kotsiantis, S. B. (2007) · Informatica · Cited by 6,007
The Organization of Behavior; A Neuropsychological Theory.
Attneave, F., B., M., & Hebb, D. O. (1950) · The American Journal of Psychology · doi:10.2307/1418888 · Cited by 5,146
Simple model of spiking neurons
Izhikevich, E. M. (2003) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2003.820440 · Cited by 4,828
Receptive fields of single neurones in the cat's striate cortex
Hubel, D. H., & Wiesel, T. N. (1959) · The Journal of Physiology · doi:10.1113/jphysiol.1959.sp006308 · Cited by 4,653
Forecasting with artificial neural networks:
Zhang, G., Eddy Patuwo, B., & Y. Hu, M. (1998) · International Journal of Forecasting · doi:10.1016/s0169-2070(97)00044-7 · Cited by 4,229
Nanoscale Memristor Device as Synapse in Neuromorphic Systems
Jo, S. H., Chang, T., Ebong, I., Bhadviya, B. B., Mazumder, P., & Lu, W. (2010) · Nano Letters · doi:10.1021/nl904092h · Cited by 4,174 · cited 3×
“While some neuromorphic computing research has focused on exploiting the synapse-like behavior of a single memristor [68,83] or using two serially connected memristive devices with different polarities [67], we implement synaptic weights via a differential pair of memristors with the same…”
BackgroundHoeting, J. A., Madigan, D., Raftery, A. E., & Volinsky, C. T. (1999) · Statistical Science · doi:10.1214/ss/1009212519 · Cited by 4,118
Ankerst, M. (1999) · doi:10.1145/304181.304187 · Cited by 3,982
Introduction to V.L.S.I. Systems
Mead, C. (1981) · IEE Proceedings I Solid State and Electron Devices · doi:10.1049/ip-i-1.1981.0010 · Cited by 3,720
Schrödinger, E. (1944) · Cited by 3,447
A Fast Fixed-Point Algorithm for Independent Component Analysis
Hyvärinen, A., & Oja, E. (1997) · Neural Computation · doi:10.1162/neco.1997.9.7.1483 · Cited by 3,391
Memristive switching mechanism for metal/oxide/metal nanodevices
Yang, J. J., Pickett, M. D., Li, X., Ohlberg, D. A. A., Stewart, D. R., & Williams, R. S. (2008) · Nature Nanotechnology · doi:10.1038/nnano.2008.160 · Cited by 2,987 · cited 2×
“In 2008, HP Laboratories announced the production of Chua’s postulated electronic device, the memristor [48] and explored their use as synapses in neuromorphic circuits [49].”
BackgroundBienenstock, E., Cooper, L., & Munro, P. (1982) · The Journal of Neuroscience · doi:10.1523/jneurosci.02-01-00032.1982 · Cited by 2,896 · cited 1×
“Beinenstock, Cooper and Munro published a theory of synaptic modification in 1982 [37].”
BackgroundProceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability; Vol. IV
Roy, H. L. L., Lecam, L., & Neyman, J. (1969) · Revue de l'Institut International de Statistique / Review of the International Statistical Institute · doi:10.2307/1402306 · Cited by 2,835
Memristive devices and systems
Chua, L. O., & Kang, S. M. (1976) · Proceedings of the IEEE · doi:10.1109/proc.1976.10092 · Cited by 2,604 · cited 1×
“In 1971, Chua postulated on the basis of symmetry arguments the existence of a missing fourth two terminal circuit element called a memristor (memory resistor), where the resistance of the memristor depends on the integral of the input applied to the terminals [33,34].”
BackgroundThe “independent components” of natural scenes are edge filters
Bell, A. J., & Sejnowski, T. J. (1997) · Vision Research · doi:10.1016/s0042-6989(97)00121-1 · Cited by 2,201
Scaling Up the Accuracy of Naive-Bayes Classifiers : a Decision-Tree Hybrid
Kohavi, R. (1996) · Knowledge Discovery and Data Mining · Cited by 2,141
Improved Use of Continuous Attributes in C4.5
Quinlan, J. R. (1996) · Journal of Artificial Intelligence Research · doi:10.1613/jair.279 · Cited by 1,846
Building high-level features using large scale unsupervised learning
Le, Q. V. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6639343 · Cited by 1,695
Analog VLSI Implementation of Neural Systems
(1989) · The Kluwer International Series in Engineering and Computer Science · doi:10.1007/978-1-4613-1639-8 · Cited by 1,680
Switching the electrical resistance of individual dislocations in single-crystalline SrTiO3
Szot, K., Speier, W., Bihlmayer, G., & Waser, R. (2006) · Nature Materials · doi:10.1038/nmat1614 · Cited by 1,651
Barlow, H. B. (1989) · Neural Computation · doi:10.1162/neco.1989.1.3.295 · Cited by 1,650
Machine learning: a review of classification and combining techniques
Kotsiantis, S. B., Zaharakis, I. D., & Pintelas, P. E. (2006) · Artificial Intelligence Review · doi:10.1007/s10462-007-9052-3 · Cited by 1,582
Competitive learning: From interactive activation to adaptive resonance
Grossberg, S. (1987) · Cognitive Science · doi:10.1111/j.1551-6708.1987.tb00862.x · Cited by 1,471 · cited 1×
“The reaction to Minsky and Papert diverted attention away from connection networks until the emergence of a number of new ideas, including Hopfield networks (1982) [30], back propagation of error (1986) [31], adaptive resonance theory (1987) [32], and many other permutations.”
BackgroundOPTICS: ordering points to identify the clustering structure
Ankerst, M., Breunig, M. M., Kriegel, H.-P., & Sander, J. (1999) · Proceedings of the 1999 ACM SIGMOD international conference on Management of data · doi:10.1145/304182.304187 · Cited by 1,335
Nanoelectronic programmable synapses based on phase change materials for brain-inspired computing
Kuzum, D., Jeyasingh, R. G. D., Lee, B., & Wong, H.-S. P. (2012) · Nano Letters · doi:10.1021/nl201040y · Cited by 1,267 · cited 2×
“Kuzum et al. [113] claim that scaling trends project energy consumption for electronic synapses down to 2 pJ.”
BackgroundUnsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition
Ranzato, M., Huang, F. J., Boureau, Y.-L., & LeCun, Y. (2007) · 2007 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2007.383157 · Cited by 1,086
Short-Term Memory to Long-Term Memory Transition in a Nanoscale Memristor
Chang, T., Jo, S.-H., & Lu, W. (2011) · ACS Nano · doi:10.1021/nn202983n · Cited by 1,058
Contribution to the Energetics of Evolution
Lotka, A. J. (1922) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.8.6.147 · Cited by 1,027
Maze—solving by an amoeboid organism
Nakagaki, T., Yamada, H., & Tóth, Á. (2000) · Nature · doi:10.1038/35035159 · Cited by 1,022
Constructal-theory network of conducting paths for cooling a heat generating volume
Bejan, A. (1997) · International Journal of Heat and Mass Transfer · doi:10.1016/0017-9310(96)00175-5 · Cited by 1,019
A Large-Scale Model of the Functioning Brain
Eliasmith, C., Stewart, T. C., Choo, X., Bekolay, T., DeWolf, T., Tang, Y., & Rasmussen, D. (2012) · Science · doi:10.1126/science.1225266 · Cited by 943
Kim, K.-H., Gaba, S., Wheeler, D., Cruz-Albrecht, J. M., Hussain, T., Srinivasa, N., & Lu, W. (2012) · Nano Letters · doi:10.1021/nl203687n · Cited by 924
Kriegel, H., Kröger, P., Sander, J., & Zimek, A. (2011) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.30 · Cited by 900
Summation and inhibition in the frog's retina
Barlow, H. B. (1953) · The Journal of Physiology · doi:10.1113/jphysiol.1953.sp004829 · Cited by 896
TEAM: ThrEshold Adaptive Memristor Model
Kvatinsky, S., Friedman, E. G., Kolodny, A., & Weiser, U. C. (2013) · IEEE Transactions on Circuits and Systems I: Regular Papers · doi:10.1109/tcsi.2012.2215714 · Cited by 843
Switching dynamics in titanium dioxide memristive devices
Pickett, M. D., Strukov, D. B., Borghetti, J. L., Yang, J. J., Snider, G. S., Stewart, D. R., & Williams, R. S. (2009) · Journal of Applied Physics · doi:10.1063/1.3236506 · Cited by 764
Memristor−CMOS Hybrid Integrated Circuits for Reconfigurable Logic
Xia, Q., Robinett, W., Cumbie, M. W., Banerjee, N., Cardinali, T. J., Yang, J. J., Wu, W., Li, X., Tong, W. M., Strukov, D. B., et al. (2009) · Nano Letters · doi:10.1021/nl901874j · Cited by 671
Integration of nanoscale memristor synapses in neuromorphic computing architectures
Indiveri, G., Linares-Barranco, B., Legenstein, R., Deligeorgis, G., & Prodromakis, T. (2013) · Nanotechnology · doi:10.1088/0957-4484/24/38/384010 · Cited by 613
Ball, P. (2015) · Philosophical Transactions of the Royal Society B: Biological Sciences · doi:10.1098/rstb.2014.0218 · Cited by 590
Q UORUM S ENSING IN P LANT-P ATHOGENIC B ACTERIA
von Bodman, S. B., Bauer, W. D., & Coplin, D. L. (2003) · Annual Review of Phytopathology · doi:10.1146/annurev.phyto.41.052002.095652 · Cited by 587
High-Density Crossbar Arrays Based on a Si Memristive System
Jo, S. H., Kim, K.-H., & Lu, W. (2009) · Nano Letters · doi:10.1021/nl8037689 · Cited by 574
What is Life?: With Mind and Matter and Autobiographical Sketches
Schrödinger, E., & Penrose, R. (1992) · doi:10.1017/cbo9781139644129 · Cited by 568
Exponential ionic drift: fast switching and low volatility of thin-film memristors
Strukov, D. B., & Williams, R. S. (2009) · Applied Physics A · doi:10.1007/s00339-008-4975-3 · Cited by 494
Pakkenberg, B. (2003) · Experimental Gerontology · doi:10.1016/s0531-5565(02)00151-1 · Cited by 485
Memristor-based neural networks
Thomas, A. (2013) · Journal of Physics D: Applied Physics · doi:10.1088/0022-3727/46/9/093001 · Cited by 471 · cited 1×
“While some neuromorphic computing research has focused on exploiting the synapse-like behavior of a single memristor [68,83] or using two serially connected memristive devices with different polarities [67], we implement synaptic weights via a differential pair of memristors with the same…”
BackgroundSynaptic behaviors and modeling of a metal oxide memristive device
Chang, T., Jo, S.-H., Kim, K.-H., Sheridan, P., Gaba, S., & Lu, W. (2011) · Applied Physics A · doi:10.1007/s00339-011-6296-1 · Cited by 432 · cited 2×
“The devices include the Ag-chalcogenide [55], AIST [99], GST [70], and WO x [63] devices, and they represent a wide spectrum of incremental memristive devices found in recent publications exhibiting diverse characteristics.”
BackgroundUltrafast Synaptic Events in a Chalcogenide Memristor
Li, Y., Zhong, Y., Xu, L., Zhang, J., Xu, X., Sun, H., & Miao, X. (2013) · Scientific Reports · doi:10.1038/srep01619 · Cited by 423 · cited 2×
“The devices include the Ag-chalcogenide [55], AIST [99], GST [70], and WO x [63] devices, and they represent a wide spectrum of incremental memristive devices found in recent publications exhibiting diverse characteristics.”
BackgroundRayleigh-Bénard Convection: Structures and Dynamics
Getling, A. V. (1998) · Advanced Series in Nonlinear Dynamics · doi:10.1142/3097 · Cited by 392
Chen, H.-L., Yang, B., Liu, J., & Liu, D.-Y. (2011) · Expert Systems with Applications · doi:10.1016/j.eswa.2011.01.120 · Cited by 382
The ecological significance of plasticity.
Grime, J. P., Crick, J., & Rincon, J. E. (1986) · PubMed · Cited by 380
Molecule-Independent Electrical Switching in Pt/Organic Monolayer/Ti Devices
Stewart, D. R., Ohlberg, D. A. A., Beck, P. A., Chen, Y., Williams, R. S., Jeppesen, J. O., Nielsen, K. A., & Stoddart, J. F. (2004) · Nano Letters · doi:10.1021/nl034795u · Cited by 357
2016 IEEE International Symposium on Circuits and Systems (ISCAS)
(2016) · doi:10.1109/iscas30516.2016 · Cited by 346
Spike-timing-dependent learning in memristive nanodevices
Snider, G. S. (2008) · 2008 IEEE International Symposium on Nanoscale Architectures · doi:10.1109/nanoarch.2008.4585796 · Cited by 341 · cited 1×
“In 2008, HP Laboratories announced the production of Chua’s postulated electronic device, the memristor [48] and explored their use as synapses in neuromorphic circuits [49].”
BackgroundLearning Abilities Achieved by a Single Solid‐State Atomic Switch
Hasegawa, T., Ohno, T., Terabe, K., Tsuruoka, T., Nakayama, T., Gimzewski, J. K., & Aono, M. (2010) · Advanced Materials · doi:10.1002/adma.200903680 · Cited by 330
Serrano-Gotarredona, R., Oster, M., Lichtsteiner, P., Linares-Barranco, A., Paz-Vicente, R., Gomez-Rodriguez, F., Camunas-Mesa, L., Berner, R., Rivas-Perez, M., Delbruck, T., et al. (2009) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2009.2023653 · Cited by 325
On Computable Numbers, with an Application to the Entscheidungsproblem (1936)
Turing, A. (2004) · The Essential Turing · doi:10.1093/oso/9780198250791.003.0005 · Cited by 322
(1996) · Cited by 315
Principles of General Thermodynamics
Hatsopoulos, G. N., Keenan, J. H., & Butler, H. W. (1966) · Journal of Applied Mechanics · doi:10.1115/1.3625109 · Cited by 302
Into the cool: energy flow, thermodynamics, and life
(2005) · Choice Reviews Online · doi:10.5860/choice.43-2191 · Cited by 281
Swenson, R. (1989) · Systems Research · doi:10.1002/sres.3850060302 · Cited by 269
The cat is out of the bag: cortical simulations with 10 9 neurons, 10 13 synapses
Ananthanarayanan, R., Esser, S. K., Simon, H. D., & Modha, D. S. (2009) · Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis · doi:10.1145/1654059.1654124 · Cited by 263
Towards a Thermodynamic Theory for Ecological Systems
(2004) · Elsevier eBooks · doi:10.1016/b978-0-08-044166-5.x5000-9 · Cited by 258
Self/non‐self discrimination in roots
Falik, O., Reides, P., Gersani, M., & Novoplansky, A. (2003) · Journal of Ecology · doi:10.1046/j.1365-2745.2003.00795.x · Cited by 244
A support vector machine approach to decision trees
Bennett, K. P., & Blue, J. A. (2002) · 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227) · doi:10.1109/ijcnn.1998.687237 · Cited by 235
Rayleigh-Bénard Convection: Structures and Dynamics
Getling, A. V., & Spiegel, E. A. (1999) · Physics Today · doi:10.1063/1.882823 · Cited by 228
Complementary resistive switching in tantalum oxide-based resistive memory devices
Yang, Y., Sheridan, P., & Lu, W. (2012) · Applied Physics Letters · doi:10.1063/1.4719198 · Cited by 224
A Low-Power Nonvolatile Switching Element Based on Copper-Tungsten Oxide Solid Electrolyte
Kozicki, M. N., Gopalan, C., Balakrishnan, M., & Mitkova, M. (2006) · IEEE Transactions On Nanotechnology · doi:10.1109/tnano.2006.880407 · Cited by 216
Cation-based resistance change memory
Valov, I., & Kozicki, M. N. (2013) · Journal of Physics D: Applied Physics · doi:10.1088/0022-3727/46/7/074005 · Cited by 198
SPICE modeling of memristive, memcapacitative and meminductive systems
Biolek, D., Biolek, Z., & Biolkova, V. (2009) · 2009 European Conference on Circuit Theory and Design · doi:10.1109/ecctd.2009.5274934 · Cited by 196
On the Importance of Information-Acquiring Systems in Plant-Plant Interactions
Aphalo, P. J., & Ballare, C. L. (1995) · Functional Ecology · doi:10.2307/2390084 · Cited by 191
Reproducible hysteresis and resistive switching in metal-CuxO-metal heterostructures
Dong, R., Lee, D. S., Xiang, W. F., Oh, S. J., Seong, D. J., Heo, S. H., Choi, H. J., Kwon, M. J., Seo, S. N., Pyun, M. B., et al. (2007) · Applied Physics Letters · doi:10.1063/1.2436720 · Cited by 185
Simulation of multilevel switching in electrochemical metallization memory cells
Menzel, S., Böttger, U., & Waser, R. (2012) · Journal of Applied Physics · doi:10.1063/1.3673239 · Cited by 166
Arabidopsis plants perform arithmetic division to prevent starvation at night
Scialdone, A., Mugford, S. T., Feike, D., Skeffington, A., Borrill, P., Graf, A., Smith, A. M., & Howard, M. (2013) · eLife · doi:10.7554/elife.00669 · Cited by 164
Nanoscale electronic synapses using phase change devices
Jackson, B. L., Rajendran, B., Corrado, G. S., Breitwisch, M., Burr, G. W., Cheek, R., Gopalakrishnan, K., Raoux, S., Rettner, C. T., Padilla, A., et al. (2013) · ACM Journal on Emerging Technologies in Computing Systems · doi:10.1145/2463585.2463588 · Cited by 163
Deep convex net: a scalable architecture for speech pattern classification
Deng, L., & Yu, D. (2011) · Interspeech 2011 · doi:10.21437/interspeech.2011-607 · Cited by 150
Building block of a programmable neuromorphic substrate: A digital neurosynaptic core
Arthur, J. V., Merolla, P. A., Akopyan, F., Alvarez, R., Cassidy, A., Chandra, S., Esser, S. K., Imam, N., Risk, W., Rubin, D. B. D., et al. (2012) · The 2012 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2012.6252637 · Cited by 131
Integrated Complementary Resistive Switches for Passive High-Density Nanocrossbar Arrays
Rosezin, R., Linn, E., Nielen, L., Kugeler, C., Bruchhaus, R., & Waser, R. (2011) · IEEE Electron Device Letters · doi:10.1109/led.2010.2090127 · Cited by 122
Sander, J. (2010) · Encyclopedia of Machine Learning · doi:10.1007/978-0-387-30164-8_211 · Cited by 116
Silver chalcogenide based memristor devices
Oblea, A. S., Timilsina, A., Moore, D., & Campbell, K. A. (2010) · The 2010 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2010.5596775 · Cited by 116
Memristor-based circuits for performing basic arithmetic operations
Merrikh-Bayat, F., & Shouraki, S. B. (2011) · Procedia Computer Science · doi:10.1016/j.procs.2010.12.022 · Cited by 112
Choudhary, S., Sloan, S., Fok, S., Neckar, A., Trautmann, E. M., Gao, P., Stewart, T., Eliasmith, C., & Boahen, K. A. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33269-2_16 · Cited by 98
Device and SPICE modeling of RRAM devices
Sheridan, P., Kim, K.-H., Gaba, S., Chang, T., Chen, L., & Lu, W. (2011) · Nanoscale · doi:10.1039/c1nr10557d · Cited by 98
AgInSbTe memristor with gradual resistance tuning
Zhang, J. J., Sun, H. J., Li, Y., Wang, Q., Xu, X. H., & Miao, X. S. (2013) · Applied Physics Letters · doi:10.1063/1.4804983 · Cited by 89
Shang, D. S., Shi, L., Sun, J. R., Shen, B. G., Zhuge, F., Li, R. W., & Zhao, Y. G. (2010) · Applied Physics Letters · doi:10.1063/1.3300637 · Cited by 87
Hybrid CMOS/memristor circuits
Strukov, D. B., Stewart, D. R., Borghetti, J. L., Li, X., Pickett, M. D., Medeiros‐Ribeiro, G., Robinett, W., Snider, G., Strachan, J. P., Wu, W., et al. (2010) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2010.5537020 · Cited by 83
Large linear classification when data cannot fit in memory
Yu, H.-F., Hsieh, C.-J., Chang, K.-W., & Lin, C.-J. (2012) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/2086737.2086743 · Cited by 69
Pino, R. E., Bohl, J. W., McDonald, N., Wysocki, B., Rozwood, P., Campbell, K. A., Oblea, A., & Timilsina, A. (2010) · 2010 IEEE/ACM International Symposium on Nanoscale Architectures · doi:10.1109/nanoarch.2010.5510936 · Cited by 64
Large linear classification when data cannot fit in memory
(2010) · doi:10.1145/1835804.1835910 · Cited by 64
An Analytical Approach for Memristive Nanoarchitectures
Kavehei, O., Al-Sarawi, S. F., Cho, K.-R., Eshraghian, K., & Abbott, D. (2011) · IEEE Transactions on Nanotechnology · doi:10.1109/tnano.2011.2174802 · Cited by 60
Merrikh-Bayat, F., & Shouraki, S. B. (2012) · IEEE Transactions on Cybernetics · doi:10.1109/tsmcb.2012.2205676 · Cited by 49
Pino, R. E., Bohl, J., McDonald, N., Wysocki, B. T., Rozwood, P., Campbell, K. A., Oblea, A. S., & Timilsina, A. (2010) · International Symposium on Nanoscale Architectures · doi:10.5555/1835957.1835959 · Cited by 49
Deep Big Multilayer Perceptrons for Digit Recognition
Cireşan, D. C., Meier, U., Gambardella, L. M., & Schmidhuber, J. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-35289-8_31 · Cited by 48 · cited 1×
“65% and ‘‘took a few days’’ to train on a desktop computer with GPU acceleration [111].”
BackgroundThermodynamics of ecological networks
Jørgensen, S. E., & Svirezhev, Y. M. (2004) · Elsevier eBooks · doi:10.1016/b978-008044166-5/50009-4 · Cited by 48
Memristive operations demonstrated by gap-type atomic switches
Hasegawa, T., Nayak, A., Ohno, T., Terabe, K., Tsuruoka, T., Gimzewski, J. K., & Aono, M. (2011) · Applied Physics A · doi:10.1007/s00339-011-6317-0 · Cited by 45
Memorization and delayed expression of regulatory messages in plants
Desbiez, M. O., Kergosien, Y., Champagnat, P., & Thellier, M. (1984) · Planta · doi:10.1007/bf00429754 · Cited by 43
Memristors can implement fuzzy logicPreprint
Klimo, M., & Šuch, O. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1110.2074 · Cited by 43
Physics-based memristor models
Williams, R. S., Pickett, M. D., & Strachan, J. P. (2013) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2013.6571821 · Cited by 36
Instar and outstar learning with memristive nanodevices
Snider, G. S. (2010) · Nanotechnology · doi:10.1088/0957-4484/22/1/015201 · Cited by 35
A hardware/software co-design model for face recognition using Cognimem Neural Network chip
Sardar, S., Tewari, G., & Babu, K. A. (2011) · International Conference on Image Information Processing (ICIIP) · doi:10.1109/iciip.2011.6108866 · Cited by 26
Report on a National Physical Laboratory
(1898) · doi:10.1038/058548a0 · Cited by 18
Resistance Drift Model for Conductive-Bridge (CB) RAM by Filament Surface Relaxation
Choi, S., Ambrogio, S., Balatti, S., Nardi, F., & Ielmini, D. (2012) · IEEE International Memory Workshop (IMW) · doi:10.1109/imw.2012.6213666 · Cited by 15
(2011) · Cited by 11
Bottleneck of using single memristor as a synapse and its solutionPreprint
Merrikh-Bayat, F., Shouraki, S. B., & Afrakoti, I. E. P. (2010) · arXiv (Cornell University) · doi:10.48550/arxiv.1008.3450 · Cited by 11
Neuromorphic Engineering: From Neural Systems to Brain-Like Engineered Systems
Morabito, F. C., Andreou, A. G., & Chicca, E. (2013) · Neural Networks · doi:10.1016/j.neunet.2013.07.001 · Cited by 10
Improved Use of Continuous Attributes in C4.5Preprint
Quinlan, J. R. (1996) · arXiv (Cornell University) · doi:10.48550/arxiv.cs/9603103 · Cited by 8
Analysis of a serial circuit with two memristors and voltage source at sine and impulse regime
Mladenov, V. M., & Kirilov, S. M. (2012) · 2012 13th International Workshop on Cellular Nanoscale Networks and their Applications · doi:10.1109/cnna.2012.6331476 · Cited by 6
Unsupervised adaptation to improve fault tolerance of neural network classifiers
Nugent, A., Kenyon, G., & Porter, R. (2004) · Proceedings. 2004 NASA/DoD Conference on Evolvable Hardware, 2004. · doi:10.1109/eh.2004.1310824 · Cited by 4 · cited 4×
“As demonstrated in [43,44], as well as the results of this paper, the attractor states of the AHaH rule coincide with the maximum-margin solution.”
BackgroundResultInfluentialCompetitive Learning : “ From Interactive Activation to Adaptive Resonance
Coleman, P. T., Mazzaro, K., Ben-Yehuda, R., Redding, N., Burns, D., Bartoli, A., Civico, A., & Yee, A. (2014) · The MIT Press eBooks · doi:10.7551/mitpress/4934.003.0007 · Cited by 3
Nugent, M. A., Porter, R., & Kenyon, G. T. (2008) · Physica D: Nonlinear Phenomena · doi:10.1016/j.physd.2008.03.043 · Cited by 2 · cited 3×
“As demonstrated in [43,44], as well as the results of this paper, the attractor states of the AHaH rule coincide with the maximum-margin solution.”
BackgroundResultSelf-citation
Research works printed but not linked: 5
- Widrow B (1987) The original adaptive neural net broom-balancer. In: Proc. 1987 IEEE International Symposium on Circuits and Systems. volume 2, 351–357.
- Minsky M, Seymour P (1969) Perceptrons. MIT press.
- Mead C, Conway L (1980) Introduction to VLSI Systems. Boston, MA, USA: Addison-Wesley Longman Publishing Co., Inc.
- Klimo M, Such O (2012) Fuzzy computer architecture based on memristor circuits. In: Proc. 2012 4th International Conference on Future Computational Technologies and Applications. 84–87.
- M Athelogou, 1989, Extremal properties of dendritic patterns: biological applications, Helvetica Physica Acta, 62, 250
Cited by
Survey of Machine Learning Accelerators
Reuther, A., Michaleas, P., Jones, M., Gadepally, V., Samsi, S., & Kepner, J. (2020) · 2020 IEEE High Performance Extreme Computing Conference (HPEC) · doi:10.1109/hpec43674.2020.9286149 · Cited by 163
Memristors for the Curious Outsiders
Carbajal, J. P., & Caravelli, F. (2018) · Technologies · doi:10.3390/technologies6040118 · Cited by 82
Krestinskaya, O., Choubey, B., & James, A. P. (2020) · Scientific Reports · doi:10.1038/s41598-020-62676-7 · Cited by 63
Structural and Parametric Identification of Knowm Memristors
Ostrovskii, V. Y., Fedoseev, P. S., Bobrova, Y. O., & Бутусов, Д. (2021) · Nanomaterials · doi:10.3390/nano12010063 · Cited by 59
Open source libraries and frameworks for biological data visualisation: A guide for developers
Wang, R., Pérez‐Riverol, Y., Hermjakob, H., & Vizcaíno, J. A. (2014) · PROTEOMICS · doi:10.1002/pmic.201400377 · Cited by 58
Metadata
- Authors
- Nugent, M. A., & Molter, T. W.
- Affiliations
- M. Alexander Nugent Consulting (United States) (US)
- Corresponding author
- Nugent, Michael Alexander
- Molter, Timothy Wesley
- Venue
- PLoS ONE
- Publisher
- Public Library of Science (PLoS)
- Published
- 2014-02-10
- Volume
- 9
- Issue
- 2
- Pages
- e85175
- ISSN
- 1932-6203 (ISSN-L)
- PMC
- PMC3919716
- OpenAlex
- W2035408474
- Semantic Scholar
- 1f85abd081b9cc423d79d0f9e3c3dccbfc14c9c7
- Cited by
- 55
- References
- 131
- Citations by year
- 2026: 5 · 2025: 5 · 2024: 2 · 2023: 4 · 2022: 4 · 2021: 7 · 2020: 5 · 2019: 6 · 2018: 5 · 2017: 5 · 2016: 4 · 2015: 1 · 2014: 2
- FWCI
- 2.10
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- PLoS ONE (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Europe PMC (PubMed Central) (submittedVersion, cc-by)
- PubMed Central (submittedVersion, cc-by)
- RePEc: Research Papers in Economics (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Figshare (submittedVersion, cc-by)
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Life Sciences › Neuroscience › Cellular and Molecular Neuroscience › Photoreceptor and optogenetics research
- Life Sciences › Neuroscience › Cognitive Neuroscience › Neural dynamics and brain function
- Keywords
- von Neumann bottleneck, attractor dynamics, memristors, synaptic plasticity, Hebbian plasticity, anti-Hebbian plasticity, independent component analysis, unsupervised clustering
- MeSH terms
- Algorithms, Artificial Intelligence, Computer Simulation, Electric Conductivity, Electronics, Models, Theoretical, Robotics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-09-29, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-09-29 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.