{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T06:49:35Z","timestamp":1791355775994,"version":"4.3.1"},"reference-count":105,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T00:00:00Z","timestamp":1791331200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100009117","name":"Technische Universit\u00e4t Chemnitz","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009117","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Biological systems are constrained by anatomy and metabolism, with synaptic maintenance consuming substantial energy and spatial limitations restricting connectivity. These constraints favor neural codes that compress behaviorally relevant information into low-redundancy patterns. Here, we investigate whether an excitatory competitive Hebbian rule can implement synaptic resource allocation under anatomical and metabolic constraints, and whether the resulting representations occupy a more favorable cost-performance regime than reference learning rules.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Representational cost is operationalized using mutual-information-based quantities derived from the Variational Information Bottleneck objective. Experiments employ three audiovisual benchmarks (AVE, Kinetics-Sounds, and VGGSound100) with fixed upstream audiovisual embeddings as a controlled higher-level sensory regime. We isolate downstream associative plasticity and compare Hebbian learning against biologically inspired local target-propagation (DDTP) and backpropagation (BP) under matched sparsity and architectural constraints.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Hebbian learning yields lower task-information cost\n                      <jats:italic>CTI<\/jats:italic>\n                      than sparse BP- and DDTP-trained networks in the main compressed comparisons, while reaching a\n                      <jats:italic>CTI<\/jats:italic>\n                      range comparable to shallow nonnegativity-constrained BP. Rather than uniformly improving classification performance, Hebbian learning shifts the trade-off between task-relevant information and representational cost, yielding lower\n                      <jats:italic>CTI<\/jats:italic>\n                      at comparable functional performance in several settings.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Overall, the results indicate an explicit cost-performance trade-off rather than uniform accuracy gains, while maintaining functional task performance under the evaluated constraints. For a given level of task-relevant information, less information about the input is retained; task performance remains functional, although it can be slightly reduced on some datasets. These results support a computational-neuroscientific interpretation of Hebbian learning as a local mechanism for synaptic resource allocation, rather than as a general-purpose strategy for maximizing audiovisual classification accuracy.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fncom.2026.1825378","type":"journal-article","created":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T05:51:07Z","timestamp":1791352267000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Constrained Hebbian learning supports efficient representational allocation under structural constraints"],"prefix":"10.3389","volume":"20","author":[{"given":"Patrick","family":"Inoue","sequence":"first","affiliation":[{"name":"Knowledge Engineering and Information Management (KEIM) Institute, Albstadt-Sigmaringen University","place":["Albstadt, Germany"]},{"name":"Department of Computer Science, Chemnitz University of Technology","place":["Chemnitz, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Florian","family":"R\u00f6hrbein","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Chemnitz University of Technology","place":["Chemnitz, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Knoblauch","sequence":"additional","affiliation":[{"name":"Knowledge Engineering and Information Management (KEIM) Institute, Albstadt-Sigmaringen University","place":["Albstadt, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,7]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.04467","article-title":"TensorFlow: large-scale machine learning on heterogeneous systems","author":"Abadi","year":"2016","journal-title":"arXiv"},{"key":"B2","doi-asserted-by":"publisher","first-page":"2897","DOI":"10.1109\/TPAMI.2017.2784440","article-title":"Information dropout: learning optimal representations through noisy computation","volume":"40","author":"Achille","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B3","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1109\/ICCV48922.2021.00088","article-title":"\u201cSS-IL: separated softmax for incremental learning,\u201d","author":"Ahn","year":"2021","journal-title":"IEEE\/CVF international conference on computer vision (ICCV)"},{"key":"B4","unstructured":"\u201cDeep variational information bottleneck,\u201d\n          \n          \n            \n              Alemi\n              A. A.\n            \n            \n              Fischer\n              I.\n            \n            \n              Dillon\n              J. V.\n            \n            \n              Murphy\n              K.\n            \n          \n          Proceedings of the international conference on learning representations (ICLR) 2017\n          \n          2017"},{"key":"B5","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1109\/ICCV.2017.73","article-title":"\u201cLook, listen and learn,\u201d","author":"Arandjelovi\u0107","year":"2017","journal-title":"2017 IEEE international conference on computer vision (ICCV)"},{"key":"B6","doi-asserted-by":"publisher","first-page":"4411","DOI":"10.1007\/s10994-022-06266-w","article-title":"A brain-inspired algorithm for training highly sparse neural networks","volume":"111","author":"Atashgahi","year":"2022","journal-title":"Mach. Learn"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1133","DOI":"10.1097\/00004647-200110000-00001","article-title":"An energy budget for signaling in the grey matter of the brain","volume":"21","author":"Attwell","year":"2001","journal-title":"J. Cereb. Blood Flow Metab"},{"key":"B8","first-page":"217","article-title":"Possible principles underlying the transformations of sensory messages","volume":"1","author":"Barlow","year":"1961","journal-title":"Sens. Commun"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-03733-1","author":"Braitenberg","year":"1998","journal-title":"Cortex: Statistics and Geometry of Neuronal Connectivity"},{"key":"B10","doi-asserted-by":"publisher","first-page":"e1007692","DOI":"10.1371\/journal.pcbi.1007692","article-title":"Learning to represent signals spike by spike","volume":"16","author":"Brendel","year":"2020","journal-title":"PLoS Comput. Biol"},{"key":"B11","doi-asserted-by":"publisher","first-page":"8","DOI":"10.3389\/fnene.2010.00008","article-title":"Interpreting oxygenation-based neuroimaging signals: the importance and the challenge of understanding brain oxygen metabolism","volume":"2","author":"Buxton","year":"2010","journal-title":"Front. Neuroenergetics"},{"key":"B12","doi-asserted-by":"publisher","first-page":"20190624","DOI":"10.1098\/rstb.2019.0624","article-title":"The thermodynamics of thinking: connections between neural activity, energy metabolism and blood flow","volume":"376","author":"Buxton","year":"2021","journal-title":"Philos. Trans. R. Soc. B"},{"key":"B13","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1038\/nrn3136","article-title":"Normalization as a canonical neural computation","volume":"13","author":"Carandini","year":"2012","journal-title":"Nat. Rev. Neurosci"},{"key":"B14","doi-asserted-by":"publisher","first-page":"6974","DOI":"10.1609\/aaai.v35i8.16859","article-title":"Provable benefits of overparameterization in model compression: from double descent to pruning neural networks","volume":"35","author":"Chang","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intell"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1759","DOI":"10.1162\/089976698300017124","article-title":"Synaptic pruning in development: a computational account","volume":"10","author":"Chechik","year":"1998","journal-title":"Neural Comput"},{"key":"B16","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1109\/ICASSP40776.2020.9053174","article-title":"\u201cVGGSound: a large-scale audio-visual dataset,\u201d","author":"Chen","year":"2020","journal-title":"IEEE international conference on acoustics, speech and signal processing (ICASSP)"},{"key":"B17","first-page":"1597","article-title":"\u201cA simple framework for contrastive learning of visual representations,\u201d","volume-title":"Proceedings of the 37th international conference on machine learning","author":"Chen","year":"2020"},{"key":"B18","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/TNNLS.2014.2310059","article-title":"Learning understandable neural networks with nonnegative weight constraints","volume":"26","author":"Chorowski","year":"2015","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B19","doi-asserted-by":"publisher","first-page":"25","DOI":"10.3389\/fnsyn.2010.00025","article-title":"Voltage and spike timing interact in STDP \u2013 a unified model","volume":"2","author":"Clopath","year":"2010","journal-title":"Front. Synaptic Neurosci"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1907.04840","article-title":"Sparse networks from scratch: faster training without losing performance","author":"Dettmers","year":"2019","journal-title":"arXiv"},{"key":"B21","doi-asserted-by":"publisher","first-page":"10995","DOI":"10.1109\/CVPR52729.2023.01058","article-title":"\u201cMaskclip: masked self-distillation advances contrastive language-image pretraining,\u201d","author":"Dong","year":"2023","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)"},{"key":"B22","first-page":"2943","article-title":"\u201cRigging the lottery: making all tickets winners,\u201d","volume-title":"Proceedings of the 37th international conference on machine learning, Vol. 119","author":"Evci","year":"2020"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/cercor\/1.1.1","article-title":"Distributed hierarchical processing in the primate cerebral cortex","volume":"1","author":"Felleman","year":"1991","journal-title":"Cereb. Cortex"},{"key":"B24","article-title":"\u201cThe lottery ticket hypothesis: finding sparse, trainable neural networks,\u201d","volume-title":"International conference for learning representations (ICLR)","author":"Frankle","year":"2019"},{"key":"B25","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/385533a0","article-title":"Synaptic tagging and long-term potentiation","volume":"385","author":"Frey","year":"1997","journal-title":"Nature"},{"key":"B26","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1038\/nrn2787","article-title":"The free-energy principle: a unified brain theory?","volume":"11","author":"Friston","year":"2010","journal-title":"Nat. Rev. Neurosci"},{"key":"B27","doi-asserted-by":"publisher","first-page":"2100","DOI":"10.3390\/e14112100","article-title":"A free energy principle for biological systems","volume":"14","author":"Friston","year":"2012","journal-title":"Entropy"},{"key":"B28","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1098\/rspb.1993.0125","article-title":"Principal component analysis learning algorithms: a neurobiological analysis","volume":"254","author":"Friston","year":"1993","journal-title":"Proc. Biol. Sci"},{"key":"B29","doi-asserted-by":"publisher","first-page":"4","DOI":"10.3389\/fnsyn.2010.00004","article-title":"Genetic controls balancing excitatory and inhibitory synaptogenesis in neurodevelopmental disorder models","volume":"2","author":"Gatto","year":"2010","journal-title":"Front. Synaptic Neurosci"},{"key":"B30","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1016\/S0042-6989(00)00277-7","article-title":"Edge co-occurrence in natural images predicts contour grouping performance","volume":"41","author":"Geisler","year":"2001","journal-title":"Vis. Res"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2212.04614","article-title":"Is bio-inspired learning better than backprop? Benchmarking bio learning vs. backprop","author":"Gupta","year":"2023","journal-title":"arXiv"},{"key":"B32","article-title":"\u201cLearning both weights and connections for efficient neural networks,\u201d","volume-title":"Proceedings of the 29th international conference on neural information processing systems","author":"Han","year":"2015"},{"key":"B33","doi-asserted-by":"publisher","first-page":"762","DOI":"10.1016\/j.neuron.2012.08.019","article-title":"Synaptic energy use and supply","volume":"75","author":"Harris","year":"2012","journal-title":"Neuron"},{"key":"B34","doi-asserted-by":"publisher","first-page":"12329","DOI":"10.1073\/pnas.0914886107","article-title":"Metabolic cost as a unifying principle governing neuronal biophysics","volume":"107","author":"Hasenstaub","year":"2010","journal-title":"Proc. Natl. Acad. Sci. U. S. A"},{"key":"B35","doi-asserted-by":"publisher","first-page":"2539","DOI":"10.1523\/JNEUROSCI.5487-07.2008","article-title":"A hierarchy of temporal receptive windows in human cortex","volume":"28","author":"Hasson","year":"2008","journal-title":"J. Neurosci"},{"key":"B36","doi-asserted-by":"publisher","first-page":"16000","DOI":"10.1109\/CVPR52688.2022.01553","article-title":"\u201cMasked autoencoders are scalable vision learners,\u201d","author":"He","year":"2022","journal-title":"Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B37","doi-asserted-by":"publisher","first-page":"9726","DOI":"10.1109\/CVPR42600.2020.00975","article-title":"\u201cMomentum contrast for unsupervised visual representation learning,\u201d","author":"He","year":"2020","journal-title":"Proceedings of the 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)"},{"key":"B38","volume-title":"The Organization of Behavior: A Neuropsychological Theory","author":"Hebb","year":"1949"},{"key":"B39","first-page":"22","article-title":"\u201cDie thermodynamik chemischer vorg\u00e4nge,\u201d","volume-title":"Sitzungsberichte der k\u00f6niglich Preu\u00dfischen akademie der wissenschaften zu Berlin","author":"Helmholtz","year":"1882"},{"key":"B40","doi-asserted-by":"publisher","first-page":"3094","DOI":"10.1109\/TNNLS.2021.3050422","article-title":"Synaptic scaling\u2013an artificial neural network regularization inspired by nature","volume":"33","author":"Hofmann","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B41","first-page":"65","article-title":"A simple sequentially rejective multiple test procedure","volume":"6","author":"Holm","year":"1979","journal-title":"Scand. J. Stat"},{"key":"B42","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1016\/j.neuron.2012.08.011","article-title":"Slow cortical dynamics and the accumulation of information over long timescales","volume":"76","author":"Honey","year":"2012","journal-title":"Neuron"},{"key":"B43","doi-asserted-by":"publisher","first-page":"28708","DOI":"10.52202\/068431-2081","article-title":"\u201cMasked autoencoders that listen,\u201d","author":"Huang","year":"2022","journal-title":"Proceedings of the 36th international conference on neural information processing systems"},{"key":"B44","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1113\/jphysiol.1968.sp008455","article-title":"Receptive fields and functional architecture of monkey striate cortex","volume":"195","author":"Hubel","year":"1968","journal-title":"J. Physiol"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2607.16027","article-title":"Constrained hebbian learning supports efficient representational allocation under structural constraints","author":"Inoue","year":"","journal-title":"arXiv"},{"key":"B46","article-title":"\u201cEnergy-efficient information representation in MNIST classification using biologically inspired learning,\u201d","author":"Inoue","year":"","journal-title":"Proceedings of the 10th bwHPC symposium"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2603.03234","article-title":"Guiding sparse neural networks with neurobiological principles to elicit biologically plausible representations","author":"Inoue","year":"","journal-title":"arXiv"},{"key":"B48","doi-asserted-by":"publisher","first-page":"2829","DOI":"10.1109\/WACV56688.2023.00285","article-title":"\u201cSelf-distilled self-supervised representation learning,\u201d","author":"Jang","year":"2023","journal-title":"IEEE\/CVF winter conference on applications of computer vision"},{"key":"B49","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1146\/annurev-neuro-080317-061956","article-title":"Memory allocation: mechanisms and function","volume":"41","author":"Josselyn","year":"2018","journal-title":"Annu. Rev. Neurosci"},{"key":"B50","article-title":"\u201cHebbian deep learning without feedback,\u201d","volume-title":"International conference for learning representations (ICLR)","author":"Journ\u00e9","year":"2023"},{"key":"B51","doi-asserted-by":"publisher","first-page":"16050","DOI":"10.1109\/CVPR52688.2022.01560","article-title":"\u201cClass-incremental learning by knowledge distillation with adaptive feature consolidation,\u201d","author":"Kang","year":"2022","journal-title":"2022 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)"},{"key":"B52","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1109\/72.485677","article-title":"Accelerating the training of feedforward neural networks using generalized hebbian rules for initializing the internal representations","volume":"7","author":"Karayiannis","year":"1996","journal-title":"IEEE Trans. Neural Netw"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1705.06950","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv"},{"key":"B54","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1016\/j.neuron.2018.03.044","article-title":"A task-optimized neural network replicates human auditory behavior, predicts brain responses and reveals a cortical processing hierarchy","volume":"98","author":"Kell","year":"2018","journal-title":"Neuron"},{"key":"B55","doi-asserted-by":"publisher","first-page":"e2506920","DOI":"10.1002\/adma.202506920","article-title":"Hardware implementation of on-chip hebbian learning through integrated neuromorphic architecture","volume":"37","author":"Kim","year":"2025","journal-title":"Adv. Mater"},{"key":"B56","article-title":"\u201cAdam: a method for stochastic optimization,\u201d","volume-title":"International conference for learning representations (ICLR)","author":"Kingma","year":"2015"},{"key":"B57","article-title":"\u201cAuto-encoding variational bayes,\u201d","volume-title":"International conference on learning representations (ICLR)","author":"Kingma","year":"2014"},{"key":"B58","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1016\/B978-0-12-803784-3.00017-2","article-title":"\u201cImpact of structural plasticity on memory formation and decline,\u201d","author":"Knoblauch","year":"2017","journal-title":"Rewiring the Brain: A Computational Approach to Structural Plasticity in the Adult Brain"},{"key":"B59","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2606.29528","article-title":"Supervised hebbian learning in deep counterstream associative networks","author":"Knoblauch","year":"2026","journal-title":"arXiv"},{"key":"B60","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1162\/neco.2009.08-07-588","article-title":"Memory capacities for synaptic and structural plasticity","volume":"22","author":"Knoblauch","year":"2010","journal-title":"Neural Comput"},{"key":"B61","doi-asserted-by":"publisher","first-page":"63","DOI":"10.3389\/fnana.2016.00063","article-title":"Structural plasticity, effectual connectivity and memory in cortex","volume":"10","author":"Knoblauch","year":"2016","journal-title":"Front. Neuroanat"},{"key":"B62","doi-asserted-by":"publisher","first-page":"7723","DOI":"10.1073\/pnas.1820458116","article-title":"Unsupervised learning by competing hidden units","volume":"116","author":"Krotov","year":"2019","journal-title":"Proc. Natl. Acad. Sci. U. S. A"},{"key":"B63","doi-asserted-by":"publisher","first-page":"127867","DOI":"10.1016\/j.neucom.2024.127867","article-title":"Scalable bio-inspired training of deep neural networks with FastHebb","volume":"595","author":"Lagani","year":"2024","journal-title":"Neurocomputing"},{"key":"B64","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1007\/978-3-319-23528-8_31","article-title":"\u201cDifference target propagation,\u201d","author":"Lee","year":"2015","journal-title":"Joint European conference on machine learning and knowledge discovery in databases, Lecture Notes in Computer Science"},{"key":"B65","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1016\/S0960-9822(03)00135-0","article-title":"The cost of cortical computation","volume":"13","author":"Lennie","year":"2003","journal-title":"Curr. Biol"},{"key":"B66","author":"Li","year":"2017","journal-title":"Pruning filters for efficient convnets"},{"key":"B67","doi-asserted-by":"publisher","first-page":"1089373","DOI":"10.3389\/fnins.2022.1089373","article-title":"Energy efficiency and coding of neural network","volume":"16","author":"Li","year":"2023","journal-title":"Front. Neurosci"},{"key":"B68","doi-asserted-by":"publisher","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","article-title":"Learning without forgetting","volume":"40","author":"Li","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B69","article-title":"\u201cCertified monotonic neural networks,\u201d","volume-title":"Proceedings of the 34th international conference on neural information processing systems","author":"Liu","year":"2020"},{"key":"B70","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1002\/syn.890050103","article-title":"Associative synaptic potentiation and depression: quantification of dissociable modifications in the hippocampal dentate gyrus favors a particular class of synaptic modification equations","volume":"5","author":"Lopez","year":"1990","journal-title":"Synapse"},{"key":"B71","unstructured":"\u201cLearning sparse neural networks through l0 regularization,\u201d\n          \n          \n            \n              Louizos\n              C.\n            \n            \n              Welling\n              M.\n            \n            \n              Kingma\n              D. P.\n            \n          \n          International conference on learning representations (ICLR) 2018\n          \n          2018"},{"key":"B72","doi-asserted-by":"publisher","first-page":"e2408125122","DOI":"10.1073\/pnas.2408125122","article-title":"A general framework for interpretable neural learning based on local information-theoretic goal functions","volume":"122","author":"Makkeh","year":"2025","journal-title":"Proc. Natl. Acad. Sci. U. S. A"},{"key":"B73","first-page":"20024","article-title":"\u201cA theoretical framework for target propagation,\u201d","author":"Meulemans","year":"2020","journal-title":"Proceedings of the 34th international conference on neural information processing systems"},{"key":"B74","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.01729","article-title":"Hebbian learning with gradients: Hebbian convolutional neural networks with modern deep learning frameworks","author":"Miconi","year":"2021","journal-title":"arXiv"},{"key":"B75","doi-asserted-by":"publisher","first-page":"e2021925118","DOI":"10.1073\/pnas.2021925118","article-title":"Local dendritic balance enables learning of efficient representations in networks of spiking neurons","volume":"118","author":"Mikulasch","year":"2021","journal-title":"Proc. Natl. Acad. Sci. U. S. A"},{"key":"B76","doi-asserted-by":"publisher","first-page":"5522","DOI":"10.52202\/068431-0399","article-title":"\u201cSize and depth of monotone neural networks: interpolation and approximation,\u201d","author":"Mikulincer","year":"2022","journal-title":"Advances in neural information processing systems 35"},{"key":"B77","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.5413733","article-title":"NM-Hebb: coupling local hebbian plasticity with metric learning for more accurate and interpretable CNNs","author":"Mili\u010devi\u0107","year":"2025","journal-title":"arXiv"},{"key":"B78","first-page":"1037","article-title":"Direct feedback alignment provides learning in deep neural networks","volume":"29","author":"N\u00f8kland","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B79","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1007\/BF00275687","article-title":"A simplified neuron model as a principal component analyzer","volume":"15","author":"Oja","year":"1982","journal-title":"J. Math. Biol"},{"key":"B80","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1142\/S0129065789000475","article-title":"Neural networks, principal components and subspaces","volume":"1","author":"Oja","year":"1989","journal-title":"Int. J. Neural Syst"},{"key":"B81","first-page":"385","article-title":"\u201cLearning in non-linear constrained hebbian networks,\u201d","author":"Oja","year":"1991","journal-title":"Proceedings of the"},{"key":"B82","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1038\/381607a0","article-title":"Emergence of simple-cell receptive field properties by learning a sparse code for natural images","volume":"381","author":"Olshausen","year":"1996","journal-title":"Nature"},{"key":"B83","doi-asserted-by":"publisher","first-page":"1473","DOI":"10.1162\/neco.2008.07-06-295","article-title":"Solving the problem of negative synaptic weights in cortical models","volume":"20","author":"Parisien","year":"2008","journal-title":"Neural Comput"},{"key":"B84","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.00717","article-title":"\u201cAudio-visual class-incremental learning,\u201d","volume-title":"2023 IEEE\/CVF international conference on computer vision (ICCV)","author":"Pian","year":"2023"},{"key":"B85","first-page":"13924","article-title":"Towards biologically plausible convolutional networks","volume":"34","author":"Pogodin","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B86","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/j.conb.2018.10.013","article-title":"Neuronal competition: microcircuit mechanisms define the sparsity of the engram","volume":"54","author":"Rao-Ruiz","year":"2019","journal-title":"Curr. Opin. Neurobiol"},{"key":"B87","doi-asserted-by":"publisher","first-page":"129440","DOI":"10.1016\/j.neucom.2025.129440","article-title":"Unsupervised representation learning with hebbian synaptic and structural plasticity in brain-like feedforward neural networks","volume":"626","author":"Ravichandran","year":"2025","journal-title":"Neurocomputing"},{"key":"B88","doi-asserted-by":"publisher","first-page":"5533","DOI":"10.1109\/CVPR.2017.587","article-title":"\u201ciCaRL: incremental classifier and representation learning,\u201d","author":"Rebuffi","year":"2017","journal-title":"Proceedings of 2017 IEEE conference on computer vision and pattern recognition (CVPR)"},{"key":"B89","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1038\/nrn2963","article-title":"Making memories last: the synaptic tagging and capture hypothesis","volume":"12","author":"Redondo","year":"2011","journal-title":"Nat. Rev. Neurosci"},{"key":"B90","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1034\/j.1601-183X.2003.00037.x","article-title":"Model of autism: increased ratio of excitation\/inhibition in key neural systems","volume":"2","author":"Rubenstein","year":"2003","journal-title":"Genes Brain Behav"},{"key":"B91","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1016\/0893-6080(89)90044-0","article-title":"Optimal unsupervised learning in a single-layer linear feedforward neural network","volume":"2","author":"Sanger","year":"1989","journal-title":"Neural Netw"},{"key":"B92","doi-asserted-by":"publisher","first-page":"e1003157","DOI":"10.1371\/journal.pcbi.1003157","article-title":"Information and efficiency in the nervous system-a synthesis","volume":"9","author":"Sengupta","year":"2013","journal-title":"PLoS Comput. Biol"},{"key":"B93","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2408.08408","article-title":"Oja's plasticity rule overcomes several challenges of training neural networks under biological constraints","author":"Shervani-Tabar","year":"2025","journal-title":"arXiv"},{"key":"B94","doi-asserted-by":"publisher","first-page":"109983","DOI":"10.1016\/j.sigpro.2025.109983","article-title":"Understanding encoder-decoder structures in machine learning using information measures","volume":"234","author":"Silva","year":"2025","journal-title":"Signal Process"},{"key":"B95","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/9780262028707.001.0001","volume-title":"Principles of Neural Design","author":"Sterling","year":"2015"},{"key":"B96","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IJCNN60899.2024.10650478","article-title":"\u201cWeight perturbation and competitive hebbian plasticity for training sparse excitatory neural networks,\u201d","author":"Stricker","year":"2024","journal-title":"2024 international joint conference on neural networks (IJCNN)"},{"key":"B97","article-title":"\u201cPruning neural networks without any data by iteratively conserving synaptic flow,\u201d","volume-title":"Proceedings of the 34th international conference on neural information processing systems","author":"Tanaka","year":"2020"},{"key":"B98","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1007\/978-3-030-01216-8_16","article-title":"\u201cAudio-visual event localization in unconstrained videos,\u201d","author":"Tian","year":"2018","journal-title":"ECCV 2018: 15th european conference"},{"key":"B99","first-page":"368","article-title":"\u201cThe information bottleneck method,\u201d","volume-title":"Proceedings of the 37th annual Allerton conference on communication, control and computing","author":"Tishby","year":"1999"},{"key":"B100","doi-asserted-by":"crossref","DOI":"10.52202\/068431-0732","article-title":"\u201cVideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training,\u201d","volume-title":"Proceedings of the 36th international conference on neural information processing systems","author":"Tong","year":"2022"},{"key":"B101","doi-asserted-by":"publisher","first-page":"80","DOI":"10.2307\/3001968","article-title":"Individual comparisons by ranking methods","volume":"1","author":"Wilcoxon","year":"1945","journal-title":"Biom. Bull"},{"key":"B102","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICASSP49357.2023.10095969","article-title":"\u201cLarge-scale contrastive language-audio pretraining with feature fusion and keyword-to-caption augmentation,\u201d","author":"Wu","year":"2023","journal-title":"IEEE international conference on acoustics, speech and signal processing (ICASSP)"},{"key":"B103","doi-asserted-by":"publisher","first-page":"8619","DOI":"10.1073\/pnas.1403112111","article-title":"Performance-optimized hierarchical models predict neural responses in higher visual cortex","volume":"111","author":"Yamins","year":"2014","journal-title":"Proc. Natl. Acad. Sci. U. S. A"},{"key":"B104","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.13400","article-title":"Activation learning by local competitions","author":"Zhou","year":"2022","journal-title":"arXiv"},{"key":"B105","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1038\/s44172-025-00479-2","article-title":"Neuromorphic Hebbian learning with magnetic tunnel junction synapses","volume":"4","author":"Zhou","year":"2025","journal-title":"Commun. Eng"}],"container-title":["Frontiers in Computational Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2026.1825378\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T05:51:14Z","timestamp":1791352274000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2026.1825378\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,7]]},"references-count":105,"alternative-id":["10.3389\/fncom.2026.1825378"],"URL":"https:\/\/doi.org\/10.3389\/fncom.2026.1825378","relation":{},"ISSN":["1662-5188"],"issn-type":[{"value":"1662-5188","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,7]]},"article-number":"1825378"}}