Real-Time Computation at the Edge of Chaos in Recurrent Neural Networks
The DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
Depending on the connectivity, recurrent networks of simple computational units can show very different types of dynamics, ranging from totally ordered to chaotic. We analyze how the type of dynamics (ordered or chaotic) exhibited by randomly connected networks of threshold gates driven by a time-varying input signal depends on the parameters describing the distribution of the connectivity matrix. In particular, we calculate the critical boundary in parameter space where the transition from ordered to chaotic dynamics takes place. Employing a recently developed framework for analyzing real-time computations, we show that only near the critical boundary can such networks perform complex computations on time series. Hence, this result strongly supports conjectures that dynamical systems that are capable of doing complex computational tasks should operate near the edge of chaos, that is, the transition from ordered to chaotic dynamics.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Intrinsic fluctuations that are poised ''at the edge of chaos'' are thought to maximize the computational efficiency of such systems and the flexibility to switch between adaptive regimes (Bertschinger & Natschla ¨ger, 2004).”
From A potential mechanism for Gibsonian resonance: behavioral entrainment emerges from local homeostasis in an unsupervised reservoir network (2024) · cites this paper as Bertschinger & Natschläger, 2004
In the citing paper
“Finally, we show that a randomly connected circuit model, akin to a “reservoir” network13-15, can reproduce the observed distribution of timescales, provided that the network operates at the critical point (or “edge of chaos”)16-18.”
From A reservoir of time constants for memory traces in cortical neurons (2011) · cites this paper as [17]
Citations
Cites
Self-organized criticality: An explanation of the 1/f noise
Bak, P., Tang, C., & Wiesenfeld, K. (1987) · Physical Review Letters · doi:10.1103/physrevlett.59.381 · Cited by 7,591
The origins of order; self organization and selection in evolution
(1994) · International Journal of Biochemistry · doi:10.1016/0020-711x(94)90119-8 · Cited by 6,649
Introduction to the theory of neural computation
(1994) · Neural Networks · doi:10.1016/0893-6080(94)90014-0 · Cited by 6,401
Bak, P., Tang, C., & Wiesenfeld, K. (1988) · Physical Review A · doi:10.1103/physreva.38.364 · Cited by 4,713
Maass, W., Natschläger, T., & Markram, H. (2002) · Neural Computation · doi:10.1162/089976602760407955 · Cited by 4,025 · cited 10×
“(Maass et al., 2002) and indepenently by Jaeger (Jaeger, 2002) who called it “echo state networks”.”
BackgroundInfluentialSelf-citationChaos in Neuronal Networks with Balanced Excitatory and Inhibitory Activity
van Vreeswijk, C., & Sompolinsky, H. (1996) · Science · doi:10.1126/science.274.5293.1724 · Cited by 1,811
Computation at the edge of chaos: Phase transitions and emergent computation
Langton, C. G. (1990) · Physica D: Nonlinear Phenomena · doi:10.1016/0167-2789(90)90064-v · Cited by 1,527 · cited 5×
“These results provide further evidence for the idea of “computation at the edge of chaos” (Langton, 1990).”
BackgroundResultInfluentialFading memory and the problem of approximating nonlinear operators with Volterra series
Boyd, S., & Chua, L. (1985) · IEEE Transactions on Circuits and Systems · doi:10.1109/tcs.1985.1085649 · Cited by 991
Random Networks of Automata: A Simple Annealed Approximation
Derrida, B., & Pomeau, Y. (1986) · Europhysics Letters (EPL) · doi:10.1209/0295-5075/1/2/001 · Cited by 706
Dynamic Patterns in Complex Systems
(1988) · doi:10.1142/0534 · Cited by 548
Research works printed but not linked: 1
- Mitchell M., 1993, Complex Systems, 7, 89
Cited by
Items 701–800 of 831
Noise driven broadening of the neural synchronisation transition in stage II retinal wavesPreprint
Karvouniari, D., Cessac, B., & Gil, L. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.03934 · Cited by 1
“From a theoretical point of view, it has been suggested [4, 5] that such a scale-free organisation could foster information storage and transfer, improvement of the computational capabilities [6], information transmission [3, 6, 7], sensitivity to stimuli and enlargement of dynamic range [8–11].”
BackgroundHow Chaotic Are Recurrent Neural Networks?Preprint
Vakilipourtakalou, P., & Mou, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.13838 · Cited by 1
“This is the typical setting of previous work on analyzing RNN’s chaotic behavior (Bertschinger & Natschlager, 2004; Laurent & von Brecht, 2016).”
Spoken digit classification using a spin-wave delay-line active-ring reservoir computingPreprint
Watt, S., & Kostylev, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.12557 · Cited by 5
“As a preliminary step, we also run the short-term memory (STM) task [7] and the parity check (PC) task [8,9] on the improved device.”
MethodNeuromorphic Computing Systems with Emerging Devices
Wei, Q., Tang, J., Gao, B., Li, X., Qian, H., & Wu, H. (2021) · Wiley eBooks · doi:10.1002/9783527835317.ch6 · Cited by 2
Criticality and sampling in neural networks
Neto, J. P. (2021) · eDiss (Georg-August-Universität Göttingen) · doi:10.53846/goediss-8439 · Cited by 1
How neural network structure alters the brain’s self-organized criticalityPreprint
Sugimoto, Y. A., Yadohisa, H., & Abe, M. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.09.24.614702 · Cited by 1
“Also, the properties stemmed from criticality can maximize some functions such as information processing capabilities and transmissions, suggesting that a brain benefits from being critical [3, 10, 11, 23, 33, 68].”
BackgroundResultHuman Motion Recognition using Nonlinear Transient Computation
Crook, N., & Goh, W. J. (2007) · Cited by 1
2022 roadmap on neuromorphic computing and engineering
Christensen, D. V., Dittmann, R., Linares-Barranco, B., Sebastian, A., Le Gallo, M., Redaelli, A., Slesazeck, S., Mikolajick, T., Spiga, S., Menzel, S., et al. (2022) · Neuromorphic Computing and Engineering · doi:10.1088/2634-4386/ac4a83
Focused surface acoustic wave induced nano-oscillator based reservoir computing
Chowdhury, M. F. F., Misba, W. A., Rajib, M. M., Edwards, A. J., Bhattacharya, D., Varghese, M. S., Friedman, J. S., & Atulasimha, J. (2022) · Applied Physics Letters · doi:10.1063/5.0110769 · Cited by 12
“We evaluate the quantitative performance of the reservoir with Short-Term Memory (STM) task and Parity Check (PC) task [24].”
MethodOn the Effect of Heterogeneity on the Dynamics and Performance of Dynamical Networks
Goudarzi, A. (2000) · doi:10.15760/etd.369
“Bertschinger and Natschläger [18] extended Derrida’s annealed approximation to calculate the spreading of perturbation in the LSM state that are due to changes in the input signals.”
BackgroundInformation Propagation in the Long-Term Behavior of Gene Regulatory Networks
Ribeiro, A. S., & Lloyd‐Price, J. (2011) · Intelligent systems reference library · doi:10.1007/978-3-642-19621-8_9
“This ability has been assessed by several methods in RBNs, and found to be maximum in the critical regime [9, 14, 11, 15, 16, 9].”
MethodSelf-organising agent communities for autonomic computing
Jacyno, M. (2010) · ePrints Soton (University of Southampton)
Neural Circuit Dynamics and Ensemble Coding in the Locust and Fruit Fly Olfactory System
Jayaraman, V. (2007) · CaltechTHESIS (California Institute of Technology) · doi:10.7907/a4vb-6c23
Schmidt, N. O. (2013) · viXra
Stability and amplification in plastic cortical circuits
Hennequin, G. (2013) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · doi:10.5075/epfl-thesis-5585 · Cited by 3
“Thus, on the edge of chaos, a chaotic network can be used as a dynamical substrate for solving complex computations that require some amount of short-term memory (Maass et al., 2002; Bertschinger and Natschläger, 2004; Buonomano and Maass, 2009; Sussillo and Abbott, 2009).”
BackgroundAn advantage of chaotic neural dynamics
András, P., & Lycett, S. (2007) · IEEE International Conference on Neural Networks/IEEE ... International Conference on Neural Networks · doi:10.1109/ijcnn.2007.4371166
“Recurrent neural networks characterized by a state space attractor can perform a wide range of computational tasks [16] [17] [18] [19].”
Priesemann, V., Wibral, M., & Munk, M. H. J. (2009) · BMC Neuroscience · doi:10.1186/1471-2202-10-s1-p161
“In addition, the critical state is optimal for information storage and processing [4].”
BackgroundInterplay between Network Topology and Dynamics in Neural SystemsPreprint
Johnson, S. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1302.3943
“This would be in line with research that shows how certain useful properties – such as the computational capacity of some neural-network models (Bertschinger and Natschläger, 2004), or the dynamic range of sensitivity to stimuli in sensory systems (Kinouchi and Copelli, 2006) – are optimised at…”
BackgroundResultInfluentialExploring a model of far-from-equilibrium computation
Florian, V. (2005)
Scheffer, M., Bascompte, J., Bjordam, T. K., Carpenter, S. R., Clarke, L. B., Folke, C., & Marquet, P. A. (2015)
Architectures and Algorithms for Intrinsic Computation with Memristive Devices
Bürger, J. (2000) · doi:10.15760/etd.3101
“This property is attributed to the dynamics of a system in the critical regime where the distinctions between states do not diverge or converge [9, 63, 97].”
BackgroundIs cortical criticality unique?Preprint
Kanders, K., & Stoop, R. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.09218
Phase Transitions in Living Neural Networks
Williams-García, R. V. (2016)
Criticality in Random Boolean Networks
Ott, T., Frey, M., & Stoop, R. (2005)
Coordinated neural activity: Mechanistic origins and impact on stimulus coding
Gajic, C., & Alexandra, N. (2015) · ResearchWorks at the University of Washington (University of Washington)
Deviation from Criticality in Functional Biological Networks
Lorimer, T., Gomez, F., & Stoop, R. (2014) · Communications in computer and information science · doi:10.1007/978-3-319-08672-9_36
Chaos-guided Input Structuring for Improved Learning in Recurrent Neural NetworksPreprint
Panda, P., & Roy, K. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.09206 · Cited by 1
“ne 1=2g2A2cos(wt+2z)=Gd3. Then, Eqn.19becomes d3 d2k dt2 = d3G+d( 2d +2(1+4d)m)k 2=3d3k3 (20) Now, we introduce the parameter n, where m=d +(n=2 4)d2 to further simplify Eqn.20as d2k dt2 = G+nk 2=3k3 (21) Eqn.21is the force equation (Eqn. 5 in the manuscript) from which we derived the potential energy. Note, the MFT a…”
A theory of how the brain computes
Tan, T. L. (2018) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/73797
Structural, functional and dynamical properties of a lognormal network of bursting neurons
Carvalho, M. M. (2017) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.76.2017.tde-25052017-110738
The cerebral cortex: An evolutionary breakthrough
Singer, W. (2017) · MPG.PuRe (Max Planck Society)
State or content of consciousness? : A reply to Valdas Noreika
Singer, W. (2015) · Gutenberg Open Science · doi:10.25358/openscience-86 · Cited by 1
Pose regulation of a constrained circular object using Echo State Networks
García-Rodríguez, R., & Parra‐Vega, V. (2018) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-18915
26th Annual Computational Neuroscience Meeting (CNS*2017): Part 1
Denham, S. L., Poirazi, P., Schutter, E. D., Friston, K. J., Chan, H. K., Nowotny, T., Han, D., Hong, S., Rosay, S., Wernle, T., et al. (2017) · BMC Neuroscience · doi:10.1186/s12868-017-0370-3 · Cited by 1
Dynamics of Oscillators Coupled by a Medium with Adaptive ImpactPreprint
Daneshvar, R. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1206.3338
Exploring Transfer Function Nonlinearity in Echo State NetworksPreprint
Goudarzi, A., Shabani, A., & Stefanović, D. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1502.04423 · Cited by 1
“ESN’s power in time series processing has been attributed to the reservoir’s memory [16], [17] and highdimensional projection of the input which acts like a temporal discriminant kernel [18] that is present in the critical dynamical regime, where input perturbations in the reservoir dynamics neither spread nor die out…”
BackgroundEvolutionary aspects of Reservoir ComputingPreprint
Seoane, L. F. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.04672
“A similar phenomenon was noted in computer science studying cellular automata and random Boolean networks [19, 73, 95–98].”
BackgroundMethodNeutral stability, rate propagation, and critical branching in feedforward networksPreprint
Cayco-Gajic, N. A., & Shea‐Brown, E. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1210.8406
Reservoir Computing Using Asynchronous Cellular Automata
Uragami, D., & Gunji, Y. (2020) · Transactions of the Society of Instrument and Control Engineers · doi:10.9746/sicetr.56.8
Jannesari, M., Saeedi, A., Zare, M., Ortiz‐Mantilla, S., Plenz, D., & BENASICH, A. A. (2020) · Brain Structure and Function · doi:10.1007/s00429-020-02042-5
RetractedNonlinear dynamics in neural computation.
Scheper, T. V. O., & Crook, N. (2006)
Reconciliation of theoretical and empirical brain criticality via network heterogeneityPreprint
Gu, L., & Wu, R. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.03.11.435016
Pseudocritical and Precritical States in Brain DynamicsPreprint
Gu, L., & Wu, R. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.07.04.451067
A Brain-inspired Decision-making Model for Spatio-temporal Pattern Recognition
Wang, B., Tan, B., Zou, X., Lin, X., Huang, C., Wu, S., & Mi, Y. (2021) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm52023.2021.9536113
“� � � �� � � �� The optimial regime for the above parameters are determined by fixing the dynamics of the module [15,16,17].”
Critical bistability and large-scale synchrony in human brain dynamics
Wang, S. H. (2021) · Helda - University of Helsinki Institutional Repository
Self-Organized Criticality Governs Dynamic Equilibrium in Bacterial CalciumPreprint
Kralj, J. M., & Meyer, C. T. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3925259
Peratic phase transition by bulk-to-surface response
Qiu, X., Wang, H., Xia, W., & Li, X. (2022) · Physical Review Research · doi:10.1103/physrevresearch.4.043009
“the Hamming distance evolution in the dual chaotic dynamics [38].”
BackgroundFísica da psicofísica: uma abordagem mecanística à lei de Stevens
Galera, E. F. (2019) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.59.2019.tde-17092021-085653
Cooperation-induced Criticality in Neural Networks
Zare, M. (2013) · University of North Texas Digital Library (University of North Texas) · doi:10.12794/metadc283813
Architectural designs of Echo State Network
Rodan, A. (2012) · UPT. Syiah Kuala University Library (Syiah Kuala University) · Cited by 1
Chaos Theory of Random Recurrent Neural Networks
Huang, H. (2021) · Springer eBooks · doi:10.1007/978-981-16-7570-6_16
The Capabilities of Chaos and Complexity
Abel, D. L. (2011) · Science Publishers eBooks · doi:10.1201/b11408-13
Report on scipost_202110_00024v1
(2021) · SciPost Physics · doi:10.21468/scipost.report.4037
Report on scipost_202110_00024v1
(2021) · SciPost Physics · doi:10.21468/scipost.report.3967
Computational annealing as mechanism in eye movement desensitization and reprocessing (EMDR)Preprint
Stwertka, S. A. (2021) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/6hxyd
Recent advances on micro-control for near-critical complex systems
Zhao, D., & Dong, Y. (2022) · Control Theory and Technology · doi:10.1007/s11768-022-00082-2
“When a real-time computing network is near critical, it can perform complex computations on time series [4].”
Information Processing Capacity in the Rat Auditory Cortex
Ishida, N., Kubota, T., Ito, Y., Shiramatsu, T. I., Suwa, E., & Takahashi, H. (2022) · IEEJ Transactions on Electronics Information and Systems · doi:10.1541/ieejeiss.142.569
Miller, P. C. (2019) · Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature · doi:10.3410/f.733245602.793556628
Neural Information Processing: between synchrony and chaosPreprint
Rosselló, J. L., Rosselló, J. L., Canals, V., & Morro, A. (2012) · Nature Precedings · doi:10.1038/npre.2012.6935
Homeostasis in neural networks: implications for information processing and learning
Schubert, F. (2022) · Publication Server of Goethe University Frankfurt am Main (Goethe University Frankfurt) · doi:10.21248/gups.68925
Robust chaos and multi-stability in piecewise linear recurrent neural networksPreprint
Monfared, Z., Patra, M., & Durstewitz, D. (2022) · Research Square · doi:10.21203/rs.3.rs-2147683/v1
Dehghani-Habibabadi, M., Safari, N., Shahbazi, F., & Zare, M. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.11.28.569071
“…show that optimal operations including phase synchrony 36 , information storage 40 , communication, and information transition 32 , optimal communication 32,34,41–44 , transition capability 34 , computational power 42 , and dynamic range 34,45 are found when the brain works near criticality.”
BackgroundHeuristic modeling of reflection in reflexive games
Markova, G. M., & Игоревич, Б. С. (2023) · Philosophical Problems of IT & Cyberspace (PhilIT&C) · doi:10.17726/philit.2023.2.5
Spreading Processes in Complex Networks of Cultured Neurons and Society
Spitzner, F. P. (2023) · eDiss (Georg-August-Universität Göttingen) · doi:10.53846/goediss-10266
Simulation of a physical reservoir made of a Ag2S islands network
Murase, Y., & Hasegawa, T. (2024) · Japanese Journal of Applied Physics · doi:10.35848/1347-4065/ad2652
Pathological cell assembly dynamics in a striatal MSN network model
Correa, A., Ponzi, A. P. D., Calderón, V., & Migliore, R. (2024) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2024.1410335
“Computational properties are often found to be optimal when such reservoirs operate close to the “edge of chaos” (Bertschinger and Natschläager, 2004; Legenstein and Maass, 2007; Sussillo and Abbott, 2009; Ponzi and Wickens, 2012, 2013).”
BackgroundScientific Arguments against Free Will
Tse, P. U. (2024) · Oxford University Press eBooks · doi:10.1093/oso/9780198876953.003.0004
Tse, P. U. (2024) · Oxford University Press eBooks · doi:10.1093/oso/9780198876953.002.0004
Tse, P. U. (2024) · Oxford University Press eBooks · doi:10.1093/oso/9780198876953.002.0005
Tse, P. U. (2024) · Oxford University Press eBooks · doi:10.1093/oso/9780198876953.002.0009
Tse, P. U. (2024) · Oxford University Press eBooks · doi:10.1093/oso/9780198876953.003.0003
Tse, P. U. (2024) · Oxford University Press eBooks · doi:10.1093/oso/9780198876953.003.0005
Tse, P. U. (2024) · Oxford University Press eBooks · doi:10.1093/oso/9780198876953.003.0002
Tse, P. U. (2024) · Oxford University Press eBooks · doi:10.1093/oso/9780198876953.003.0001
Tse, P. U. (2024) · Oxford University Press eBooks · doi:10.1093/oso/9780198876953.002.0008
Tse, P. U. (2024) · Oxford University Press eBooks · doi:10.1093/oso/9780198876953.002.0003
Krisenhafte Veränderungen in Gehirn und Psyche
Brenner, M., & Durstewitz, D. (2024) · Der Nervenarzt · doi:10.1007/s00115-024-01770-x
Rotationally Stable Dynamics Over Long Timescales Emerge in Neuronal DevelopmentPreprint
Burrows, D. R. W., & Rosch, R. E. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.12.31.630917
Kang, C., Moore, J. A., Robertson, S., Wilms, M., Towlson, E. K., & Forkert, N. D. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107308
Detecting Signatures of Criticality Using Divergence Rate
Chan, T., Soh, D. W., & Hillar, C. (2025) · Entropy · doi:10.3390/e27050487
“In these applications, it is frequently argued that optimal properties for computation emerge [11–17] when systems are critically poised at some special set of control parameters.”
Recent developments at the intersection of AI and theoretical physics
Ruehle, F. (2024) · Contemporary Physics · doi:10.1080/00107514.2025.2498817
“This phenomenon was described in [29, 30].”
Noè, D., Yamamoto, H., Katori, Y., & Sato, S. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.05.25.656058
“This behavior of the spectral radius is usually associated with a system approaching the "edge of chaos", a regime of operation characterized by enhanced temporal stability and memory capacity [38, 39].”
Kagan, B. J., & Kitchen, A. C. (2025) · Springer eBooks · doi:10.1007/978-3-031-93623-4_12 · Cited by 2
Nara, S., Miyahara, N., Yamaguti, Y., & Tsuda, I. (2025) · Dynamics · doi:10.3390/dynamics5030032
Reservoir Computing Using Series-Parallel-Connected Au Nanogaps and Electromigrated Coulomb Islands
Sakai, K., Tanaka, Y., Yagi, M., Ito, M., & Shirakashi, J. (2025) · ACS Applied Electronic Materials · doi:10.1021/acsaelm.5c01068
Stability of Difference Equations and Long Short-Term Memory Neural Networks
Stipanović, D. M. (2025) · Synthesis lectures on mathematics and statistics · doi:10.1007/978-3-032-00910-4_4
Homotopy, Computation of Equilibria, and Long Short-Term Memory Neural Networks
Stipanović, D. M. (2025) · Synthesis lectures on mathematics and statistics · doi:10.1007/978-3-032-00910-4_5
Transition to chaos with conical billiards
Braverman, L., & Nelson, D. R. (2025) · Physical review. E · doi:10.1103/18f7-sqhz · Cited by 2
“At such interfaces dynamical systems can optimize complex computations [39, 40], consequently garnering widespread interest in fields such as neural networks [39].”
Residual Reservoir Memory Networks
Pinna, M., Ceni, A., & Gallicchio, C. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227859 · Cited by 3
“In future work, this analysis could be complemented by exploring the eigenspectra in polar form, investigating the differences between each configuration from the perspective of eigenvalues’ magnitudes and angles, rather than their real and imaginary parts.”
Response function as a quantitative measure of consciousness in brain dynamics
Du, W., & Huang, H. (2025) · Physical Review Research · doi:10.1103/6lx7-qsv7 · Cited by 1
“This observation highlights the important role of criticality even in real brain data analysis, as the concept was previously explored in theoretical and computational frameworks [18, 28–30].”
Additional file 1 of Hydropathicity-based prediction of pain-causing NaV1.7 variants
Xenakis, M. N., Kapetis, D., Yang, Y., Gerrits, M. M., Heijman, J., Waxman, S. G., Lauria, G., Faber, C. G., Westra, R. L., Lindsey, P. J., et al. (2021) · Figshare · doi:10.6084/m9.figshare.14478915
Modified Internal Model Control and Neural Networks
Stipanović, D. M. (2025) · Synthesis lectures on mathematics and statistics · doi:10.1007/978-3-032-00910-4_8
Stability of Convex Combinations and Gated Recurrent Unit Neural Networks
Stipanović, D. M. (2025) · Synthesis lectures on mathematics and statistics · doi:10.1007/978-3-032-00910-4_6
Introduction, Inspirations and Motivations
Stipanović, D. M. (2025) · Synthesis lectures on mathematics and statistics · doi:10.1007/978-3-032-00910-4_1
Difference Equations, Sequences and Discrete-Time Dynamical Systems
Stipanović, D. M. (2025) · Synthesis lectures on mathematics and statistics · doi:10.1007/978-3-032-00910-4_2
Dynamical alignment: a principle for adaptive neural computation
Chen, X. (2026) · Neuromorphic Computing and Engineering · doi:10.1088/2634-4386/ae3acd · Cited by 1
“…that apparent randomness often reflects deterministic chaos [22], and the established view of the ‘edge of chaos’ as optimal for computation [23, 24], we find that the key quality indicator is not local chaotic sensitivity but the input trajectories’ global rate of phase space volume change.”
Autapses enable temporal pattern recognition in spiking neural networks
Yaqoob, M., Steuber, V., & Wróbel, B. (2026) · PLoS ONE · doi:10.1371/journal.pone.0339918
Criticality emerges within coherent functional organization in human forebrain organoidsPreprint
Itatani, N., & Zavaglia, M. (2026) · Research Square · doi:10.21203/rs.3.rs-8640242/v1
Decodability, sensitivity, and criticality measured through single-neuron perturbations
Farrell, M., & Toyoizumi, T. (2026) · Nature Communications · doi:10.1038/s41467-026-69121-9
Metadata
- Authors
- Bertschinger, N., & Natschläger, T.
- Affiliations
- Graz University of Technology (AT)
- Software Competence Center Hagenberg (Austria) (AT)
- ORCID
- Bertschinger, Nils
- Venue
- Neural Computation
- Publisher
- MIT Press - Journals
- Published
- 2004-07-01
- Volume
- 16
- Issue
- 7
- Pages
- 1413-1436
- ISSN
- 0899-7667 (ISSN-L)
- 1530-888X
- OpenAlex
- W2057755457
- Cited by
- 833
- References
- 26
- Citations by year
- 2026: 45 · 2025: 73 · 2024: 61 · 2023: 48 · 2022: 66 · 2021: 73 · 2020: 52 · 2019: 53 · 2018: 47 · 2017: 48 · 2016: 26 · 2015: 33 · 2014: 29 · 2013: 33 · 2012: 27
- FWCI
- 13.53
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Neural Computation (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Cellular Automata and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Reservoir Computing
- Keywords
- edge of chaos, recurrent neural networks, critical connectivity, threshold gates, random connectivity, real-time processing, dynamical systems
- MeSH terms
- Animals, Artificial Intelligence, Computer Simulation, Feedback, Memory, Models, Neurological, Time Factors, Neural Networks, Computer, Nonlinear Dynamics
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.
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.