{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T02:22:13Z","timestamp":1760235733224,"version":"build-2065373602"},"reference-count":57,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2021,9,17]],"date-time":"2021-09-17T00:00:00Z","timestamp":1631836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>In dealing with the algorithmic aspects of intelligent systems, the analogy with the biological brain has always been attractive, and has often had a dual function. On the one hand, it has been an effective source of inspiration for their design, while, on the other hand, it has been used as the justification for their success, especially in the case of Deep Learning (DL) models. However, in recent years, inspiration from the brain has lost its grip on its first role, yet it continues to be proposed in its second role, although we believe it is also becoming less and less defensible. Outside the chorus, there are theoretical proposals that instead identify important demarcation lines between DL and human cognition, to the point of being even incommensurable. In this article we argue that, paradoxically, the partial indifference of the developers of deep neural models to the functioning of biological neurons is one of the reasons for their success, having promoted a pragmatically opportunistic attitude. We believe that it is even possible to glimpse a biological analogy of a different kind, in that the essentially heuristic way of proceeding in modern DL development bears intriguing similarities to natural evolution.<\/jats:p>","DOI":"10.3390\/a14090272","type":"journal-article","created":{"date-parts":[[2021,9,17]],"date-time":"2021-09-17T21:23:29Z","timestamp":1631913809000},"page":"272","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["How Neurons in Deep Models Relate with Neurons in the Brain"],"prefix":"10.3390","volume":"14","author":[{"given":"Arianna","family":"Pavone","sequence":"first","affiliation":[{"name":"Department of Cognitive Science, Universit\u00e0 di Messina, via Concezione n.6\/8, 98122 Messina, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessio","family":"Plebe","sequence":"additional","affiliation":[{"name":"Department of Cognitive Science, Universit\u00e0 di Messina, via Concezione n.6\/8, 98122 Messina, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,9,17]]},"reference":[{"key":"ref_1","first-page":"359","article-title":"Brain Inspiration Is Not Panacea","volume":"Volume 1310","author":"Perconti","year":"2021","journal-title":"Brain-Inspired Cognitive Architectures for Artificial Intelligence"},{"key":"ref_2","unstructured":"Fazi, M.B. (2020). Beyond Human: Deep Learning, Explainability and Representation. Theory Cult. Soc., 1\u201323."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"D\u01d2silovi\u0107, F.K., Br\u010di\u0107, M., and Hlupi\u0107, N. (2018, January 21\u201325). Explainable artificial intelligence: A survey. Proceedings of the 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), Opatija, Croatia.","DOI":"10.23919\/MIPRO.2018.8400040"},{"key":"ref_4","unstructured":"Molnar, C. (2019). Interpretable Machine Learning. A Guide for Making Black Box Models Explainable, Lulu Press."},{"key":"ref_5","unstructured":"van Lent, M., Fisher, W., and Mancuso, M. (2004, January 25\u201329). An Explainable Artificial Intelligence System for Small-unit Tactical Behavior. Proceedings of the AAAI Conference on Artificial Intelligence, San Jose, CA, USA."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016). \u201cWhy Should I Trust You?\u201d: Explaining the Predictions of Any Classifier. arXiv.","DOI":"10.1145\/2939672.2939778"},{"key":"ref_7","unstructured":"Lundberg, S.M., and Lee, S.I. (2017, January 4\u20139). A unified approach to interpreting model predictions. Proceedings of the 31st International Conference on Neural Information Processing Systems, (NIPS 2017), Long Beach, CA, USA."},{"key":"ref_8","first-page":"1","article-title":"How the machine \u2019thinks\u2019: Understanding opacity in machine learning algorithms","volume":"3","author":"Burrel","year":"2016","journal-title":"Big Data Soc."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1007\/s11023-019-09512-8","article-title":"The unbearable shallow understanding of deep learning","volume":"29","author":"Plebe","year":"2019","journal-title":"Minds Mach."},{"key":"ref_10","unstructured":"Samek, W., Wiegand, T., and M\u00fcller, K.-R. (2017). Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1007\/s13347-019-00382-7","article-title":"Solving the black box problem: A normative framework for explainable artificial intelligence","volume":"34","author":"Zednik","year":"2021","journal-title":"Philos. Technol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep learning in neural networks: An overview","volume":"61","author":"Schmidhuber","year":"2015","journal-title":"Neural Netw."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., and McClelland, J.L. (1986). Parallel Distributed Processing: Explorations in the Microstructure of Cognition, MIT Press.","DOI":"10.7551\/mitpress\/5236.001.0001"},{"key":"ref_14","first-page":"e6","article-title":"The artificial intelligence renaissance: Deep learning and the road to human-level machine intelligence","volume":"7","author":"Tan","year":"2019","journal-title":"APSIPA Trans. Signal Inf. Process."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1126\/science.aax0162","article-title":"In defense of the black box","volume":"364","author":"Holm","year":"2019","journal-title":"Science"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Berner, J., Grohs, P., Kutyniok, G., and Petersen, P. (2021). The Modern Mathematics of Deep Learning. arXiv.","DOI":"10.1017\/9781009025096.002"},{"key":"ref_17","unstructured":"Plebe, A., and Grasso, G. (2015, January 8\u201311). The Brain in Silicon: History, and Skepticism. Proceedings of the 3rd International Conference on History and Philosophy of Computing (HaPoC), Pisa, Italy."},{"key":"ref_18","unstructured":"Minsky, M.L. (1954). Neural Nets and the Brain-Model Problem. [Ph.D. Thesis, Princeton University]."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/BF02478259","article-title":"A logical calculus of the ideas immanent in nervous activity","volume":"5","author":"McCulloch","year":"1943","journal-title":"Bull. Math. Biophys."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Taylor, J. (1993). The Promise of Neural Networks, Springer.","DOI":"10.1007\/978-1-4471-0395-0"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1016\/j.cell.2015.09.029","article-title":"Reconstruction and simulation of neocortical microcircuitry","volume":"163","author":"Markram","year":"2015","journal-title":"Cell"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e253","DOI":"10.1017\/S0140525X16001837","article-title":"Building machines that learn and think like people","volume":"40","author":"Lake","year":"2017","journal-title":"Behav. Brain Sci."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2061","DOI":"10.1007\/s11229-019-02192-y","article-title":"Making AI meaningful again","volume":"198","author":"Landgrebe","year":"2019","journal-title":"Synthese"},{"key":"ref_24","unstructured":"Marcus, G. (2018). Deep learning: A critical appraisal. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"104365","DOI":"10.1016\/j.cognition.2020.104365","article-title":"Deep learning and cognitive science","volume":"203","author":"Perconti","year":"2020","journal-title":"Cognition"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1807","DOI":"10.1007\/s11229-019-02167-z","article-title":"Judging machines: Philosophical aspects of deep learning","volume":"198","author":"Schubbach","year":"2019","journal-title":"Synthese"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1202","DOI":"10.1126\/science.1225266","article-title":"A Large-Scale Model of the Functioning Brain","volume":"338","author":"Eliasmith","year":"2012","journal-title":"Science"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Eliasmith, C. (2013). How to Build a Brain: A Neural Architecture for Biological Cognition, Oxford University Press.","DOI":"10.1093\/acprof:oso\/9780199794546.001.0001"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"10619","DOI":"10.1073\/pnas.1201884109","article-title":"Adaptive evolution of voltage-gated sodium channels: The first 800 million years","volume":"109","author":"Zakon","year":"2012","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_30","unstructured":"Squire, L.R., Bloom, F., McConnell, S., Roberts, J., Spitzer, N., and Zigmond, M. (2003). Fundamental Neuroscience, Academic Press."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1111\/cogs.12012","article-title":"Neural Computation and the Computational Theory of Cognition","volume":"34","author":"Piccinini","year":"2013","journal-title":"Cogn. Sci."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Piccinini, G. (2015). Physical Computation: A Mechanistic Account, Oxford University Press.","DOI":"10.1093\/acprof:oso\/9780199658855.001.0001"},{"key":"ref_33","unstructured":"Ince, D.C. (1969). Intelligent machinery. Collected Works of A. M. Turing: Mechanical Intelligence, Edinburgh University Press. Technical Report for National Physical Laboratory."},{"key":"ref_34","first-page":"536","article-title":"Methode generale le pour la resolution des systemess d\u2019equations simultatees","volume":"25","author":"Cauchy","year":"1847","journal-title":"Compt. Rend. Seances Acad. Sci. Paris"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by backpropagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref_36","unstructured":"Bottou, L., and LeCun, Y. (2004). Large scale online learning. Advances in Neural Information Processing Systems, MIT Press."},{"key":"ref_37","unstructured":"Hinton, G.E., Sejnowski, T.J., and Ackley, D.H. (1984). Boltzmann Machines: Constraint Networks That Learn, Carnegie-Mellon University, Computer Science Department. Technical Report 84\u2013119."},{"key":"ref_38","unstructured":"Bartunov, S., Santoro, A., Richards, B.A., Marris, L., Hinton, G.E., and Lillicrap, T. (2018, January 3\u20138). Assessing the scalability of biologically-motivated deep learning algorithms and architectures. Proceedings of the 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montreal, QC, Canada."},{"key":"ref_39","unstructured":"Shai, S.S., and Shai, B.D. (2014). Understanding Machine Learning: From Theory to Algorithms, Cambridge University Press."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Bianchini, M., and Scarselli, F. (2014, January 23\u201325). On the complexity of shallow and deep neural network classifiers. Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium.","DOI":"10.1109\/TNNLS.2013.2293637"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1553","DOI":"10.1109\/TNNLS.2013.2293637","article-title":"On the complexity of neural network classifiers: A Comparison Between Shallow and Deep Architectures","volume":"25","author":"Bianchini","year":"2014","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1007\/BF02824604","article-title":"Teoria della elasticita","volume":"7","author":"Betti","year":"1872","journal-title":"Il Nuovo Cimento (1869\u20131876)"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Sun, S., Chen, W., Wang, L., Liu, X., and Liu, T.Y. (2016, January 12\u201317). On the Depth of Deep Neural Networks: A Theoretical View. Proceedings of the AAAI Conference on Artificial Intelligence, Phoenix, AZ, USA.","DOI":"10.1609\/aaai.v30i1.10243"},{"key":"ref_44","first-page":"1","article-title":"The Power of Depth for Feedforward Neural Networks","volume":"49","author":"Eldan","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref_45","unstructured":"Safran, I., and Shamir, O. (2017). Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1223","DOI":"10.1007\/s10955-017-1836-5","article-title":"Why does deep and cheap learning work so well?","volume":"168","author":"Lin","year":"2017","journal-title":"J. Stat. Phys."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Darwin, C. (1859). On the Origin of Species by Means of Natural Selection, or the Preservation of Favoured Races in the Struggle for Life, Routledge.","DOI":"10.5962\/bhl.title.68064"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Kuhn, M., and Johnson, K. (2013). Applied Predictive Modeling, Springer.","DOI":"10.1007\/978-1-4614-6849-3"},{"key":"ref_49","unstructured":"Dauphin, Y.H., de Vries, H., Chung, J., and Bengio, Y. (2015). RMSProp and equilibrated adaptive learning rates for non-convex optimization. arXiv."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.neunet.2021.02.011","article-title":"Convergence of the RMSProp deep learning method with penalty for nonconvex optimization","volume":"139","author":"Xu","year":"2021","journal-title":"Neural Netw."},{"key":"ref_51","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv."},{"key":"ref_52","unstructured":"Yu, T., and Zhu, H. (2020). Hyper-Parameter Optimization: A Review of Algorithms and Applications. arXiv."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/j.neucom.2019.10.007","article-title":"Autonomous deep learning: A genetic DCNN designer for image classification","volume":"379","author":"Ma","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"7994","DOI":"10.1109\/ACCESS.2021.3049892","article-title":"A Deep Learning Trained by Genetic Algorithm to Improve the Efficiency of Path Planning for Data Collection with Multi-UAV","volume":"9","author":"Pan","year":"2021","journal-title":"IEEE Access"},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1093\/cercor\/12.7.671","article-title":"Human-specific organization of primary visual cortex: Alternating compartments of dense Cat-301 and calbindin immunoreactivity in layer 4A","volume":"12","author":"Preuss","year":"2002","journal-title":"Cereb. Cortex"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of Go without human knowledge","volume":"550","author":"Silver","year":"2017","journal-title":"Nature"},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"2248","DOI":"10.1038\/s41467-017-02334-1","article-title":"Solving for ambiguities in radar geophysical exploration of planetary bodies by mimicking bats echolocation","volume":"8","author":"Carrer","year":"2017","journal-title":"Nat. Commun."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/14\/9\/272\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:01:24Z","timestamp":1760166084000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/14\/9\/272"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,17]]},"references-count":57,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2021,9]]}},"alternative-id":["a14090272"],"URL":"https:\/\/doi.org\/10.3390\/a14090272","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2021,9,17]]}}}