{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T07:48:14Z","timestamp":1767772094868,"version":"build-2238731810"},"reference-count":86,"publisher":"Maximum Academic Press","license":[{"start":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T00:00:00Z","timestamp":1643846400000},"content-version":"unspecified","delay-in-days":33,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":["cambridge.org"],"crossmark-restriction":true},"short-container-title":["The Knowledge Engineering Review"],"published-print":{"date-parts":[[2022]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Artificial neural networks (ANNs) can be employed as controllers for robotic agents. Their structure is often complex, with many neurons and connections, especially when the robots have many sensors and actuators distributed across their bodies and\/or when high expressive power is desirable. Pruning (removing neurons or connections) reduces the complexity of the ANN, thus increasing its energy efficiency, and has been reported to improve the generalization capability, in some cases. In addition, it is well-known that pruning in biological neural networks plays a fundamental role in the development of brains and their ability to learn. In this study, we consider the evolutionary optimization of neural controllers for the case study of Voxel-based soft robots, a kind of modular, bio-inspired soft robots, applying pruning during fitness evaluation. For a locomotion task, and for centralized as well as distributed controllers, we experimentally characterize the effect of different forms of pruning on after-pruning effectiveness, life-long effectiveness, adaptability to new terrains, and behavior. We find that incorporating some forms of pruning in neuroevolution leads to almost equally effective controllers as those evolved without pruning, with the benefit of higher robustness to pruning. We also observe occasional improvements in generalization ability.<\/jats:p>","DOI":"10.1017\/s0269888921000151","type":"journal-article","created":{"date-parts":[[2022,2,2]],"date-time":"2022-02-02T22:17:52Z","timestamp":1643840272000},"update-policy":"https:\/\/doi.org\/10.1017\/policypage","source":"Crossref","is-referenced-by-count":6,"title":["Merging pruning and neuroevolution: towards robust and efficient controllers for modular soft robots"],"prefix":"10.48130","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3535-9748","authenticated-orcid":false,"given":"Giorgia","family":"Nadizar","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5652-2113","authenticated-orcid":false,"given":"Eric","family":"Medvet","sequence":"additional","affiliation":[]},{"given":"Hola","family":"Huse Ramstad","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4696-9872","authenticated-orcid":false,"given":"Stefano","family":"Nichele","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4423-1666","authenticated-orcid":false,"given":"Felice Andrea","family":"Pellegrino","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9920-9095","authenticated-orcid":false,"given":"Marco","family":"Zullich","sequence":"additional","affiliation":[]}],"member":"27968","published-online":{"date-parts":[[2022,2,3]]},"reference":[{"key":"S0269888921000151_ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2172702"},{"key":"S0269888921000151_ref62","unstructured":"Real, E. , Moore, S. , Selle, A. , Saxena, S. , Suematsu, Y. L. , Tan, J. , Le, Q. V. & Kurakin, A. (2017). Large-scale evolution of image classifiers. In International Conference on Machine Learning, 2902\u20132911. PMLR."},{"key":"S0269888921000151_ref25","doi-asserted-by":"publisher","DOI":"10.4324\/9781410612403"},{"key":"S0269888921000151_ref38","unstructured":"LeCun, Y. , Denker, J. S. , Solla, S. A. , Howard, R. E. & Jackel, L. D. (1989). Optimal brain damage. In NIPs, 2. Citeseer, 598\u2013605."},{"key":"S0269888921000151_ref69","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2019.00405"},{"key":"S0269888921000151_ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412993"},{"key":"S0269888921000151_ref6","unstructured":"Bartoldson, B. R. , Morcos, A. S. , Barbu, A. & Erlebacher, G. (2019). The generalization-stability tradeoff in neural network pruning. arXiv preprint arXiv:1906.03728."},{"key":"S0269888921000151_ref3","doi-asserted-by":"publisher","DOI":"10.5220\/0008960300520059"},{"key":"S0269888921000151_ref21","unstructured":"Frankle, J. & Carbin, M. (2019). The lottery ticket hypothesis: finding sparse, trainable neural networks. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rJl-b3RcF7."},{"key":"S0269888921000151_ref68","doi-asserted-by":"publisher","DOI":"10.1016\/S0928-4257(00)80055-8"},{"key":"S0269888921000151_ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.biosystems.2004.09.016"},{"key":"S0269888921000151_ref32","doi-asserted-by":"publisher","DOI":"10.1038\/35081509"},{"key":"S0269888921000151_ref8","unstructured":"Bengio, Y. , Le Roux, N. , Vincent, P. , Delalleau, O. & Marcotte, P. (2006). Convex neural networks. In Advances in Neural Information Processing systems, 18, 123."},{"key":"S0269888921000151_ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2739480.2754662"},{"key":"S0269888921000151_ref55","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3585.001.0001"},{"key":"S0269888921000151_ref13","unstructured":"Brown, T. , Mann, B. , Ryder, N. , Subbiah, M. , Kaplan, J. D. , Dhariwal, P. , Neelakantan, A. , Shyam, P. , Sastry, G. , Askell, A. , Agarwal, S. , Herbert-Voss, A. , Krueger, G. , Henighan, T. , Child, R. , Ramesh, A. , Ziegler, D. , Wu, J. , Winter, C. , Hesse, C. , Chen, M. , Sigler, E. , Litwin, M. , Gray, S. , Chess, B. , Clark, J. , Berner, C. , McCandlish, S. , Radford, A. , Sutskever, I. & Amodei, D. (2020). Language models are few-shot learners. In Advances in Neural Information Processing Systems, Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M. F. & Lin, H. (eds), 33. Curran Associates, Inc., 1877\u20131901. https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf."},{"key":"S0269888921000151_ref22","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511815706"},{"key":"S0269888921000151_ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3377930.3390173"},{"key":"S0269888921000151_ref37","unstructured":"Laurenti, L. , Patane, A. , Wicker, M. , Bortolussi, L. , Cardelli, L. & Kwiatkowska, M. (2019). Global adversarial robustness guarantees for neural networks."},{"key":"S0269888921000151_ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3005348"},{"key":"S0269888921000151_ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2737082"},{"key":"S0269888921000151_ref49","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00023"},{"key":"S0269888921000151_ref41","unstructured":"Lipson, H. , Sunspiral, V. , Bongard, J. & Cheney, N. (2016). On the difficulty of co-optimizing morphology and control in evolved virtual creatures. In Artificial Life Conference Proceedings 13. MIT Press, 226\u2013233."},{"key":"S0269888921000151_ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3407197.3407198"},{"key":"S0269888921000151_ref57","doi-asserted-by":"publisher","DOI":"10.1002\/wdev.216"},{"key":"S0269888921000151_ref60","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1813416116"},{"key":"S0269888921000151_ref80","unstructured":"Variengien, A. , Nichele, S. , Glover, T. & Pontes-Filho, S. (2021). Towards self-organized control: Using neural cellular automata to robustly control a cart-pole agent. arXiv preprint arXiv:2106.15240."},{"key":"S0269888921000151_ref44","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2006.1883"},{"key":"S0269888921000151_ref33","unstructured":"Kassahun, Y. & Sommer, G. (2005). Efficient reinforcement learning through evolutionary acquisition of neural topologies. In ESANN, 259\u2013266."},{"key":"S0269888921000151_ref74","doi-asserted-by":"crossref","unstructured":"Strubell, E. , Ganesh, A. & McCallum, A. (2019). Energy and policy considerations for deep learning in nlp. arXiv preprint arXiv:1906.02243.","DOI":"10.18653\/v1\/P19-1355"},{"key":"S0269888921000151_ref78","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065791000352"},{"key":"S0269888921000151_ref34","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-31868-7"},{"key":"S0269888921000151_ref71","doi-asserted-by":"publisher","DOI":"10.31887\/DCNS.2013.15.3\/osporns"},{"key":"S0269888921000151_ref64","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-cellbio-100913-013038"},{"key":"S0269888921000151_ref70","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2009.5179035"},{"key":"S0269888921000151_ref75","doi-asserted-by":"crossref","unstructured":"Sudhakaran, S. , Grbic, D. , Li, S. , Katona, A. , Najarro, E. , Glanois, C. & Risi, S. (2021). Growing 3D artefacts and functional machines with neural cellular automata. arXiv preprint arXiv:2103.08737.","DOI":"10.1162\/isal_a_00451"},{"key":"S0269888921000151_ref76","doi-asserted-by":"crossref","unstructured":"Talamini, J. , Medvet, E. , Bartoli, A. & De Lorenzo, A. (2019). Evolutionary synthesis of sensing controllers for voxel-based soft robots. In Artificial Life Conference Proceedings, MIT Press, 574\u2013581.","DOI":"10.1162\/isal_a_00223"},{"key":"S0269888921000151_ref16","doi-asserted-by":"publisher","DOI":"10.7551\/978-0-262-32621-6-ch037"},{"key":"S0269888921000151_ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66125-0_6"},{"key":"S0269888921000151_ref46","first-page":"12","article-title":"2D-VSR-Sim: a simulation tool for the optimization of 2-D voxel-based soft robots","author":"Medvet","year":"2020","journal-title":"SoftwareX"},{"key":"S0269888921000151_ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01092"},{"key":"S0269888921000151_ref81","doi-asserted-by":"publisher","DOI":"10.1162\/netn_a_00153"},{"key":"S0269888921000151_ref84","doi-asserted-by":"publisher","DOI":"10.1038\/nrn3962"},{"key":"S0269888921000151_ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s12065-007-0002-4"},{"key":"S0269888921000151_ref43","unstructured":"Liu, Z. , Sun, M. , Zhou, T. , Huang, G. & Darrell, T. (2019). Rethinking the value of network pruning. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rJlnB3C5Ym."},{"key":"S0269888921000151_ref51","unstructured":"Naumov, M. , Chien, L. , Vandermersch, P. & Kapasi, U. (2010). Cusparse library. In GPU Technology Conference."},{"key":"S0269888921000151_ref54","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00027.003"},{"key":"S0269888921000151_ref27","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1201895109"},{"key":"S0269888921000151_ref63","unstructured":"Renda, A. , Frankle, J. & Carbin, M. (2020). Comparing fine-tuning and rewinding in neural network pruning. In International Conference on Learning Representations."},{"key":"S0269888921000151_ref56","unstructured":"Pontes-Filho, S. & Nichele, S. (2019). Towards a framework for the evolution of artificial general intelligence. arXiv preprint arXiv:1903.10410."},{"key":"S0269888921000151_ref65","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2010281117"},{"key":"S0269888921000151_ref83","unstructured":"You, H. , Li, C. , Xu, P. , Fu, Y. , Wang, Y. , Chen, X. , Baraniuk, R. G. , Wang, Z. & Lin, Y. (2019). Drawing early-bird tickets: Towards more efficient training of deep networks. arXiv preprint arXiv:1909.11957."},{"key":"S0269888921000151_ref1","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/aww194"},{"key":"S0269888921000151_ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-72812-0_3"},{"key":"S0269888921000151_ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.05.007"},{"key":"S0269888921000151_ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nn.4502"},{"key":"S0269888921000151_ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2017.03.018"},{"key":"S0269888921000151_ref40","unstructured":"Lin, T. , Stich, S. U. , Barba, L. , Dmitriev, D. & Jaggi, M. (2020). Dynamic model pruning with feedback. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SJem8lSFwB."},{"key":"S0269888921000151_ref59","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2018.8628848"},{"key":"S0269888921000151_ref61","unstructured":"Ramesh, A. , Pavlov, M. , Goh, G. , Gray, S. , Voss, C. , Radford, A. , Chen, M. & Sutskever, I. (2021). Zero-shot text-to-image generation. arXiv preprint arXiv:2102.12092."},{"key":"S0269888921000151_ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3449726.3463161"},{"key":"S0269888921000151_ref85","unstructured":"Zhang, B.-T. & M\u00fchlenbein, H. (1993). Genetic programming of minimal neural nets using occam\u2019s razor. In Proceedings of the 5th International Conference on Genetic Algorithms (ICGA\u201993). Citeseer."},{"key":"S0269888921000151_ref9","doi-asserted-by":"crossref","unstructured":"Bishop, C. M. (1995). Neural Networks for Pattern Recognition. Clarendon Press, chapter 9.5.3 - Saliency of Weights.","DOI":"10.1093\/oso\/9780198538493.001.0001"},{"key":"S0269888921000151_ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2004.07.008"},{"key":"S0269888921000151_ref79","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-0258(19970228)16:4<385::AID-SIM380>3.0.CO;2-3"},{"key":"S0269888921000151_ref66","doi-asserted-by":"publisher","DOI":"10.1137\/0907087"},{"key":"S0269888921000151_ref11","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2017.00441"},{"key":"S0269888921000151_ref19","unstructured":"Fedus, W. , Zoph, B. & Shazeer, N. (2021). Switch transformers: scaling to trillion parameter models with simple and efficient sparsity. arXiv preprint arXiv:2101.03961."},{"key":"S0269888921000151_ref52","unstructured":"Neyshabur, B. , Li, Z. , Bhojanapalli, S. , LeCun, Y. & Srebro, N. (2019). The role of over-parametrization in generalization of neural networks. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=BygfghAcYX."},{"key":"S0269888921000151_ref26","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2021.611183"},{"key":"S0269888921000151_ref35","doi-asserted-by":"crossref","unstructured":"Kriegman, S. , Cheney, N. , Corucci, F. & Bongard, J. C. (2018). Interoceptive robustness through environment-mediated morphological development. arXiv preprint arXiv:1804.02257.","DOI":"10.1145\/3205455.3205529"},{"key":"S0269888921000151_ref48","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2010.00200"},{"key":"S0269888921000151_ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s00018-014-1729-6"},{"key":"S0269888921000151_ref29","unstructured":"Hoefler, T. , Alistarh, D. , Ben-Nun, T. , Dryden, N. & Peste, A. (2021). Sparsity in deep learning: pruning and growth for efficient inference and training in neural networks. arXiv preprint arXiv:2102.00554."},{"key":"S0269888921000151_ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2001576.2001602"},{"key":"S0269888921000151_ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2017.05.016"},{"key":"S0269888921000151_ref24","volume-title":"In Advances in Neural Information Processing Systems","author":"Han","year":"2015"},{"key":"S0269888921000151_ref36","doi-asserted-by":"publisher","DOI":"10.1038\/236"},{"key":"S0269888921000151_ref42","unstructured":"Liu, S. , Chen, T. , Chen, X. , Atashgahi, Z. , Yin, L. , Kou, H. , Shen, L. , Pechenizkiy, M. , Wang, Z. & Mocanu, D. C. (2021). Sparse training via boosting pruning plasticity with neuroregeneration. arXiv preprint arXiv:2106.10404."},{"key":"S0269888921000151_ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3449639.3459315"},{"key":"S0269888921000151_ref73","doi-asserted-by":"publisher","DOI":"10.1162\/106365602320169811"},{"key":"S0269888921000151_ref12","volume-title":"Classification and Regression Trees","author":"Breiman","year":"1984"},{"key":"S0269888921000151_ref5","doi-asserted-by":"publisher","DOI":"10.3389\/fnmol.2017.00191"},{"key":"S0269888921000151_ref77","unstructured":"Thimm, G. & Fiesler, E. (1995). Evaluating pruning methods. In Proceedings of the International Symposium on Artificial neural networks, 20\u201325, Citeseer."},{"key":"S0269888921000151_ref82","doi-asserted-by":"crossref","unstructured":"Ye, S. , Xu, K. , Liu, S. , Cheng, H. , Lambrechts, J.-H. , Zhang, H. , Zhou, A. , Ma, K. , Wang, Y. & Lin, X. (2019). Adversarial robustness vs. model compression, or both?. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 111\u2013120.","DOI":"10.1109\/ICCV.2019.00020"},{"key":"S0269888921000151_ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412705"}],"updated-by":[{"DOI":"10.1017\/s0269888922000017","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T00:00:00Z","timestamp":1643846400000}}],"container-title":["The Knowledge Engineering Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S0269888921000151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T14:42:22Z","timestamp":1767624142000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S0269888921000151\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":86,"alternative-id":["S0269888921000151"],"URL":"https:\/\/doi.org\/10.1017\/s0269888921000151","relation":{},"ISSN":["0269-8889","1469-8005"],"issn-type":[{"value":"0269-8889","type":"print"},{"value":"1469-8005","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"\u00a9 The Author(s), 2022. Published by Cambridge University Press","name":"copyright","label":"Copyright","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}}],"article-number":"e3"}}