Blooming and pruning: learning from mistakes with memristive synapses.
Learning from mistakes
Memristive devices
Neuromorphic computing
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
02 Apr 2024
02 Apr 2024
Historique:
received:
03
11
2023
accepted:
20
03
2024
medline:
3
4
2024
pubmed:
3
4
2024
entrez:
2
4
2024
Statut:
epublish
Résumé
Blooming and pruning is one of the most important developmental mechanisms of the biological brain in the first years of life, enabling it to adapt its network structure to the demands of the environment. The mechanism is thought to be fundamental for the development of cognitive skills. Inspired by this, Chialvo and Bak proposed in 1999 a learning scheme that learns from mistakes by eliminating from the initial surplus of synaptic connections those that lead to an undesirable outcome. Here, this idea is implemented in a neuromorphic circuit scheme using CMOS integrated HfO
Identifiants
pubmed: 38565677
doi: 10.1038/s41598-024-57660-4
pii: 10.1038/s41598-024-57660-4
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
7802Subventions
Organisme : Deutsche Forschungsgemeinschaft
ID : 432009531
Organisme : Deutsche Forschungsgemeinschaft
ID : 434434223 - CRC 1461
Organisme : Deutsche Forschungsgemeinschaft
ID : 432009531
Organisme : Carl-Zeiss-Stiftung
ID : Memristive Materials for Neuromorphic Engineering (MemWerk)
Informations de copyright
© 2024. The Author(s).
Références
Singer, W. & Gray, C. M. Visual feature integration and the temporal correlation hypothesis. Annu. Rev. Neurosci. 18, 555–586 (1995).
doi: 10.1146/annurev.ne.18.030195.003011
pubmed: 7605074
Andersen, P. The Hippocampus Book (Oxford University Press, 2007).
Ignatov, M., Ziegler, M., Hansen, M. & Kohlstedt, H. Memristive stochastic plasticity enables mimicking of neural synchrony: Memristive circuit emulates an optical illusion. Sci. Adv. 3, e1700849 (2017).
doi: 10.1126/sciadv.1700849
pubmed: 29075665
pmcid: 5656427
Rajendran, B., Sebastian, A., Schmuker, M., Srinivasa, N. & Eleftheriou, E. Low-power neuromorphic hardware for signal processing applications: A review of architectural and system-level design approaches. IEEE Signal Process. Mag. 36, 97–110. https://doi.org/10.1109/MSP.2019.2933719 (2019).
doi: 10.1109/MSP.2019.2933719
Heaven, D. Deep trouble for deep learning. Nature 574, 163–166 (2019).
doi: 10.1038/d41586-019-03013-5
pubmed: 31597977
Sinz, F. H., Pitkow, X., Reimer, J., Bethge, M. & Tolias, A. S. Engineering a less artificial intelligence. Neuron 103, 967–979 (2019).
doi: 10.1016/j.neuron.2019.08.034
pubmed: 31557461
da Silva, I. N., Spatti, D. H., Andrade Flauzino, R., Liboni, L. H. B. & dos Reis Alves, S. F. Artificial Neural Networks A Practical Course (Springer, 2017).
doi: 10.1007/978-3-319-43162-8
Silver, D. et al. Mastering the game of go with deep neural networks and tree search. Nature 529, 484–489. https://doi.org/10.1038/nature16961 (2016).
doi: 10.1038/nature16961
pubmed: 26819042
James, C. D. et al. A historical survey of algorithms and hardware architectures for neural-inspired and neuromorphic computing applications. Biol. Insp. Cognit. Arch. 19, 49–64. https://doi.org/10.1016/j.bica.2016.11.002 (2017).
doi: 10.1016/j.bica.2016.11.002
Van Den Heuvel, M. P. et al. The neonatal connectome during preterm brain development. Cereb. Cortex 25, 3000–3013 (2015).
doi: 10.1093/cercor/bhu095
pubmed: 24833018
Huttenlocher, P. R. & Dabholkar, A. S. Regional differences in synaptogenesis in human cerebral cortex. J. Compar. Neurol. 387, 167–178 (1997).
doi: 10.1002/(SICI)1096-9861(19971020)387:2<167::AID-CNE1>3.0.CO;2-Z
Dehaene-Lambertz, G. & Spelke, E. S. The infancy of the human brain. Neuron 88, 93–109 (2015).
doi: 10.1016/j.neuron.2015.09.026
pubmed: 26447575
Huttenlocher, P. R. Synaptic density in human frontal cortex - developmental changes and effects of aging. Brain Res. 163, 195–205 (1979).
doi: 10.1016/0006-8993(79)90349-4
pubmed: 427544
Ackerman, S. Discovering the Brain (National Academies Press, 1992).
Stiles, J. & Jernigan, T. L. The basics of brain development. Neuropsychol. Rev. 20, 327–348. https://doi.org/10.1007/s11065-010-9148-4 (2010).
doi: 10.1007/s11065-010-9148-4
pubmed: 21042938
pmcid: 2989000
Chialvo, D. R. & Bak, P. Learning from mistakes. Neuroscience 90, 1137–1148 (1999).
doi: 10.1016/S0306-4522(98)00472-2
pubmed: 10338284
Bak, P. & Chialvo, D. R. Adaptive learning by extremal dynamics and negative feedback. Phys. Rev. E 63, 031912 (2001).
doi: 10.1103/PhysRevE.63.031912
Brigham, M. Self-Organised Learning in the Chialvo-Bak Model. Master’s thesis, University of Edinburgh (2009).
Wakeling, J. Order-disorder transition in the chialvo-bak ‘minibrain’ controlled by network geometry. Phys. A 325, 561–569 (2003).
doi: 10.1016/S0378-4371(03)00147-X
Carbajal, J. P., Martin, D. A. & Chialvo, D. R. Learning by mistakes in memristor networks. Phys. Rev. E 105, 054306. https://doi.org/10.1103/PhysRevE.105.054306 (2022).
doi: 10.1103/PhysRevE.105.054306
pubmed: 35706169
Gaba, S., Sheridan, P., Zhou, J., Choi, S. & Lu, W. Stochastic memristive devices for computing and neuromorphic applications. Nanoscale 5, 5872–5878 (2013).
doi: 10.1039/c3nr01176c
pubmed: 23698627
Zahari, F. et al. Analogue pattern recognition with stochastic switching binary cmos-integrated memristive devices. Sci. Rep. 10, 14450 (2020).
doi: 10.1038/s41598-020-71334-x
pubmed: 32879397
pmcid: 7467933
Hebb, D. The Organization of Behavior (JOHN WILEY and SONS, 1949).
Gerstner, W. & Kistler, W. M. Mathematical formulations of hebbian learning. Biol. Cybern. 87, 404–415 (2002).
doi: 10.1007/s00422-002-0353-y
pubmed: 12461630
Ziegler, M., Riggert, C., Hansen, M., Bartsch, T. & Kohlstedt, H. Memristive hebbian plasticity model: Device requirements for the emulation of hebbian plasticity based on memristive devices. IEEE Trans. Biomed. Circuits Syst. 9, 197–206 (2015).
doi: 10.1109/TBCAS.2015.2410811
pubmed: 25879966
Ziegler, M., Wenger, C., Chicca, E. & Kohlstedt, H. Tutorial: Concepts for closely mimicking biological learning with memristive devices: Principles to emulate cellular forms of learning. J. Appl. Phys. 124, 152003 (2018).
doi: 10.1063/1.5042040
Ziegler, M. & Kohlstedt, H. Memristive models for the emulation of biological learning. In Memristor Computing Systems, 247–272 (Springer, 2022).
Perez, E., Grossi, A., Zambelli, C., Olivo, P. & Wenger, C. Impact of the incremental programming algorithm on the filament conduction in hfo2-based rram arrays. IEEE J. Electron Dev. Soc. 5, 64–68. https://doi.org/10.1109/JEDS.2016.2618425 (2017).
doi: 10.1109/JEDS.2016.2618425
Strukov, D. B., Snider, G. S., Stewart, D. R. & Williams, R. S. The missing memristor found. Nature 453, 80–83 (2008).
doi: 10.1038/nature06932
pubmed: 18451858
Chua, L. O. & Kang, S. M. Memristive devices and systems. Proceedings of the IEEE64, 209–223 (1976).
Perez, E., Zambelli, C., Mahadevaiah, M. K., Olivo, P. & Wenger, C. Toward reliable multi-level operation in rram arrays: Improving post-algorithm stability and assessing endurance/data retention. IEEE J. Electron Dev. Soc. 7, 740–747 (2019).
doi: 10.1109/JEDS.2019.2931769
Kalishettyhalli Mahadevaiah, M. et al. Integration of memristive devices into a 130 nm cmos baseline technology. In Bio-Inspired Information Pathways: From Neuroscience To Neurotronics, 177–190 (Springer International Publishing, 2024).