{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T21:40:47Z","timestamp":1686692447887},"reference-count":39,"publisher":"MIT Press","issue":"1","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,1,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>While interest in artificial neural networks (ANNs) has been renewed by the ubiquitous use of deep learning to solve high-dimensional problems, we are still far from general artificial intelligence. In this article, we address the problem of emergent cognitive capabilities and, more crucially, of their detection, by relying on co-evolving creatures with mutable morphology and neural structure. The former is implemented via both static and mobile structures whose shapes are controlled by cubic splines. The latter uses ESHyperNEAT to discover not only appropriate combinations of connections and weights but also to extrapolate hidden neuron distribution. The creatures integrate low-level perceptions (touch\/pain proprioceptors, retina-based vision, frequency-based hearing) to inform their actions. By discovering a functional mapping between individual neurons and specific stimuli, we extract a high-level module-based abstraction of a creature\u2019s brain. This drastically simplifies the discovery of relationships between naturally occurring events and their neural implementation. Applying this methodology to creatures resulting from solitary and tag-team co-evolution showed remarkable dynamics such as range-finding and structured communication. Such discovery was made possible by the abstraction provided by the modular ANN which allowed groups of neurons to be viewed as functionally enclosed entities.<\/jats:p>","DOI":"10.1162\/artl_a_00389","type":"journal-article","created":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T15:33:53Z","timestamp":1664465633000},"page":"66-93","update-policy":"http:\/\/dx.doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":0,"title":["Explaining the Neuroevolution of Fighting Creatures Through Virtual fMRI"],"prefix":"10.1162","volume":"29","author":[{"given":"Kevin","family":"Godin-Dubois","sequence":"first","affiliation":[{"name":"University of Toulouse, IRIT. kevin.dubois@irit.fr"},{"name":"CNRS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sylvain","family":"Cussat-Blanc","sequence":"additional","affiliation":[{"name":"University of Toulouse, IRIT"},{"name":"CNRS"},{"name":"Artificial and Natural Intelligence Toulouse Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yves","family":"Duthen","sequence":"additional","affiliation":[{"name":"University of Toulouse, IRIT"},{"name":"CNRS"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","published-online":{"date-parts":[[2023,1,2]]},"reference":[{"issue":"15","key":"2023061321052925100_bib1","doi-asserted-by":"publisher","first-page":"Article 152001","DOI":"10.1103\/PhysRevLett.102.152001","article-title":"Measurement of the top-quark mass with\n                        dilepton events selected using neuroevolution at CDF","volume":"102","author":"Aaltonen","year":"2009","journal-title":"Physical Review Letters"},{"issue":"3","key":"2023061321052925100_bib2","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1080\/09540091.2015.1031081","article-title":"A reinforcement learning model of joy, distress, hope and fear","volume":"27","author":"Broekens","year":"2015","journal-title":"Connection Science"},{"key":"2023061321052925100_bib3","doi-asserted-by":"publisher","first-page":"Article 570308","DOI":"10.3389\/fnbot.2020.570308","article-title":"Neurorobots as a means toward neuroethology and explainable AI","volume":"14","author":"Chen","year":"2020","journal-title":"Frontiers in Neurorobotics"},{"key":"2023061321052925100_bib4","doi-asserted-by":"publisher","first-page":"506","DOI":"10.7551\/mitpress\/3118.003.0061","article-title":"Co-evolution of pursuit and evasion II: Simulation methods and results","volume-title":"From animals to animats 4: Proceedings of the fourth international conference on simulation of adaptive behavior","author":"Cliff","year":"1996"},{"key":"2023061321052925100_bib5","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1007\/978-3-540-76631-5_35","article-title":"Modeling emotion-influenced social behavior for intelligent virtual agents","volume-title":"MICAI 2007: Advances in artificial intelligence","author":"de Freitas","year":"2007"},{"issue":"2","key":"2023061321052925100_bib6","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/s00354-007-0009-5","article-title":"On the use of virtual animals with artificial fear in virtual environments","volume":"25","author":"Delgado-Mata","year":"2007","journal-title":"New Generation Computing"},{"issue":"4","key":"2023061321052925100_bib7","doi-asserted-by":"publisher","first-page":"Article e1004128","DOI":"10.1371\/journal.pcbi.1004128","article-title":"Neural modularity helps organisms evolve to learn new skills without forgetting old skills","volume":"11","author":"Ellefsen","year":"2015","journal-title":"PLOS Computational Biology"},{"key":"2023061321052925100_bib8","volume-title":"On the benefits of emergent communication for threat appraisal","author":"Godin-Dubois","year":"2021"},{"key":"2023061321052925100_bib9","doi-asserted-by":"publisher","DOI":"10.1162\/isal_a_00431","article-title":"Spontaneous modular neuroevolution arising from a life\/dinner paradox","volume-title":"ALIFE 2021: Proceedings of the 2021 conference on artificial life","author":"Godin-Dubois","year":"2021"},{"key":"2023061321052925100_bib10","doi-asserted-by":"publisher","first-page":"439","DOI":"10.7551\/978-0-262-31709-2-ch063","article-title":"Coevolutionary dynamics caused by asymmetries in predator-prey and morphology-behavior relationships","volume-title":"ECAL 2013: The twelfth European conference on artificial life","author":"Ito","year":"2013"},{"issue":"3","key":"2023061321052925100_bib11","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1162\/106454600568861","article-title":"Talking helps: Evolving communicating agents for the predator-prey pursuit problem","volume":"6","author":"Jim","year":"2000","journal-title":"Artificial Life"},{"key":"2023061321052925100_bib12","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/j.cogsys.2020.11.003","article-title":"Cognitive evaluation of machine learning agents","volume":"66","author":"Kadam","year":"2021","journal-title":"Cognitive Systems Research"},{"key":"2023061321052925100_bib13","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1162\/isal_a_00140","article-title":"An artificial life approach to studying niche differentiation in soundscape ecology","volume-title":"ALIFE 2019: Proceedings of the 2019 conference on artificial life","author":"Kadish","year":"2019"},{"key":"2023061321052925100_bib14","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.compag.2018.02.016","article-title":"Deep learning in agriculture: A survey","volume":"147","author":"Kamilaris","year":"2018","journal-title":"Computers and Electronics in Agriculture"},{"key":"2023061321052925100_bib15","volume-title":"The emotional brain: The mysterious underpinnings of emotional life","author":"Ledoux","year":"1998"},{"key":"2023061321052925100_bib16","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.neunet.2014.06.012","article-title":"Practical emotional neural networks","volume":"59","author":"Lotfi","year":"2014","journal-title":"Neural Networks"},{"key":"2023061321052925100_bib17","doi-asserted-by":"publisher","first-page":"3066","DOI":"10.1109\/CEC.2008.4631212","article-title":"Evosphere: Evolutionary dynamics in a population of fighting virtual creatures","volume-title":"2008 IEEE congress on evolutionary computation","author":"Miconi","year":"2008"},{"key":"2023061321052925100_bib18","first-page":"3559","article-title":"Differentiable plasticity: Training plastic neural networks with backpropagation","volume-title":"ICML 2018: Proceedings of the 35th international conference on machine learning","author":"Miconi","year":"2018"},{"issue":"7540","key":"2023061321052925100_bib19","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"2023061321052925100_bib20","doi-asserted-by":"publisher","first-page":"468","DOI":"10.7551\/mitpress\/3118.003.0056","article-title":"Evolving obstacle avoidance behavior in a robot arm","volume-title":"From animals to animats 4: Proceedings of the fourth international conference on simulation of adaptive behavior","author":"Moriarty","year":"1996"},{"key":"2023061321052925100_bib21","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/978-3-642-55337-0_9","article-title":"Artificial evolution of plastic neural networks: A few key concepts","volume-title":"Growing adaptive machines","author":"Mouret","year":"2014"},{"key":"2023061321052925100_bib22","doi-asserted-by":"publisher","first-page":"250","DOI":"10.7551\/978-0-262-33936-0-ch045","article-title":"Exploring the coevolution of predator and prey morphology and behavior","volume-title":"ALIFE 2016: Proceedings of the fifteenth international conference on the synthesis and simulation of living systems","author":"Olson","year":"2016"},{"issue":"1","key":"2023061321052925100_bib23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/evco_a_00282","article-title":"A systematic literature review of the successors of \u201cNeuroevolution of augmenting topologies.\u201d","volume":"29","author":"Papavasileiou","year":"2021","journal-title":"Evolutionary Computation"},{"key":"2023061321052925100_bib24","doi-asserted-by":"publisher","DOI":"10.1007\/s00146-021-01313-x","article-title":"Interdependence as the key for an ethical artificial autonomy","author":"Pianca","year":"2022","journal-title":"AI & Society"},{"key":"2023061321052925100_bib25","first-page":"474","article-title":"Evolving morphological and behavioral diversity without predefined behavior primitives","author":"Pichler","year":"2008","journal-title":"ALIFE XI: Proceedings of the 11th international conference on the synthesis and simulation of living systems"},{"key":"2023061321052925100_bib26","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1145\/3412841.3441884","article-title":"Natural vs. balanced distribution in deep learning on whole slide images for cancer detection","volume-title":"SAC \u201921: Proceedings of the 36th annual ACM symposium on applied computing","author":"Reshma","year":"2021"},{"issue":"4","key":"2023061321052925100_bib27","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1162\/ARTL_a_00071","article-title":"An enhanced hypercube-based encoding for evolving the placement, density, and connectivity of neurons","volume":"18","author":"Risi","year":"2012","journal-title":"Artificial Life"},{"issue":"4","key":"2023061321052925100_bib28","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1162\/artl.1994.1.4.353","article-title":"Evolving 3D morphology and behavior by competition","volume":"1","author":"Sims","year":"1994","journal-title":"Artificial Life"},{"issue":"2","key":"2023061321052925100_bib29","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/s10710-007-9028-8","article-title":"Compositional pattern producing networks: A novel abstraction of development","volume":"8","author":"Stanley","year":"2007","journal-title":"Genetic Programming and Evolvable Machines"},{"key":"2023061321052925100_bib30","first-page":"182","article-title":"Evolving neural network agents in the NERO video game","author":"Stanley","year":"2005","journal-title":"CIG\u201905: Proceedings of the IEEE symposium on computational intelligence and games"},{"issue":"1","key":"2023061321052925100_bib31","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1038\/s42256-018-0006-z","article-title":"Designing neural networks through neuroevolution","volume":"1","author":"Stanley","year":"2019","journal-title":"Nature Machine Intelligence"},{"issue":"2","key":"2023061321052925100_bib32","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1162\/artl.2009.15.2.15202","article-title":"A hypercube-based encoding for evolving large-scale neural networks","volume":"15","author":"Stanley","year":"2009","journal-title":"Artificial Life"},{"issue":"2","key":"2023061321052925100_bib33","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1162\/106365602320169811","article-title":"Evolving neural networks through augmenting topologies","volume":"10","author":"Stanley","year":"2002","journal-title":"Evolutionary Computation"},{"issue":"11","key":"2023061321052925100_bib34","doi-asserted-by":"publisher","first-page":"Article e79138","DOI":"10.1371\/journal.pone.0079138","article-title":"On the relationships between generative encodings, regularity, and learning abilities when evolving plastic artificial neural networks","volume":"8","author":"Tonelli","year":"2013","journal-title":"PLOS ONE"},{"key":"2023061321052925100_bib35","doi-asserted-by":"publisher","first-page":"1167","DOI":"10.1007\/s00146-020-01065-0","article-title":"The brain, the artificial neural network and the snake: Why we see what we see","volume":"36","author":"Treccani","year":"2020","journal-title":"AI & Society"},{"key":"2023061321052925100_bib36","first-page":"496","article-title":"Sticky feet: Evolution in a multi-creature physical simulation","volume-title":"Artificial life XII: Proceedings of the 12th international conference on the synthesis and simulation of living systems","author":"Turk","year":"2010"},{"key":"2023061321052925100_bib37","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1145\/2001576.2001776","article-title":"Constraining connectivity to encourage modularity in HyperNEAT","author":"Verbancsics","year":"2011","journal-title":"GECCO \u201911: Proceedings of the 13th annual genetic and evolutionary computation conference"},{"issue":"4","key":"2023061321052925100_bib38","doi-asserted-by":"publisher","first-page":"Article e0152756","DOI":"10.1371\/journal.pone.0152756","article-title":"Emergence of swarming behavior: Foraging agents evolve collective motion based on signaling","volume":"11","author":"Witkowski","year":"2016","journal-title":"PLOS ONE"},{"issue":"1","key":"2023061321052925100_bib39","doi-asserted-by":"publisher","first-page":"Article 3770","DOI":"10.1038\/s41467-019-11786-6","article-title":"A critique of pure learning and what artificial neural networks can learn from animal brains","volume":"10","author":"Zador","year":"2019","journal-title":"Nature Communications"}],"container-title":["Artificial Life"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/artl\/article-pdf\/29\/1\/66\/2129117\/artl_a_00389.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/artl\/article-pdf\/29\/1\/66\/2129117\/artl_a_00389.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T21:05:40Z","timestamp":1686690340000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/artl\/article\/29\/1\/66\/113185\/Explaining-the-Neuroevolution-of-Fighting"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":39,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,1,2]]},"published-print":{"date-parts":[[2023,1,2]]}},"URL":"https:\/\/doi.org\/10.1162\/artl_a_00389","relation":{},"ISSN":["1064-5462","1530-9185"],"issn-type":[{"value":"1064-5462","type":"print"},{"value":"1530-9185","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023]]},"published":{"date-parts":[[2023]]}}}