{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T21:55:17Z","timestamp":1773438917281,"version":"3.50.1"},"reference-count":70,"publisher":"SAGE Publications","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["ICA"],"published-print":{"date-parts":[[2020,9,11]]},"abstract":"<jats:p>Tackling multi-agent environments where each agent has a local limited observation of the global state is a non-trivial task that often requires hand-tuned solutions. A team of agents coordinating in such scenarios must handle the complex underlying environment, while each agent only has partial knowledge about the environment. Deep reinforcement learning has been shown to achieve super-human performance in single-agent environments, and has since been adapted to the multi-agent paradigm. This paper proposes A3C3, a multi-agent deep learning algorithm, where agents are evaluated by a centralized referee during the learning phase, but remain independent from each other in actual execution. This referee\u2019s neural network is augmented with a permutation invariance architecture to increase its scalability to large teams. A3C3 also allows agents to learn communication protocols with which agents share relevant information to their team members, allowing them to overcome their limited knowledge, and achieve coordination. A3C3 and its permutation invariant augmentation is evaluated in multiple multi-agent test-beds, which include partially-observable scenarios, swarm environments, and complex 3D soccer simulations.<\/jats:p>","DOI":"10.3233\/ica-200631","type":"journal-article","created":{"date-parts":[[2020,5,19]],"date-time":"2020-05-19T15:33:54Z","timestamp":1589902434000},"page":"333-351","source":"Crossref","is-referenced-by-count":11,"title":["Exploring communication protocols and centralized critics in multi-agent deep learning"],"prefix":"10.1177","volume":"27","author":[{"given":"David","family":"Sim\u00f5es","sequence":"first","affiliation":[{"name":"Institute of Electronics and Informatics Engineering of Aveiro, University of Aveiro, Aveiro, Portugal"}]},{"given":"Nuno","family":"Lau","sequence":"additional","affiliation":[{"name":"Institute of Electronics and Informatics Engineering of Aveiro, University of Aveiro, Aveiro, Portugal"}]},{"given":"Lu\u00eds Paulo","family":"Reis","sequence":"additional","affiliation":[{"name":"Artificial Intelligence and Computer Science Lab, Faculty of Engineering of the University of Porto, Porto, Portugal"}]}],"member":"179","reference":[{"issue":"3","key":"10.3233\/ICA-200631_ref1","doi-asserted-by":"crossref","first-page":"273","DOI":"10.3233\/ICA-180596","article-title":"Multi-object tracking with discriminant correlation filter based deep learning tracker","volume":"26","author":"Yang","year":"2019","journal-title":"Integrated Computer-Aided Engineering"},{"issue":"1","key":"10.3233\/ICA-200631_ref2","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1026544419097","article-title":"Distributed control for 3D metamorphosis","volume":"10","author":"Yim","year":"2001","journal-title":"Autonomous Robots"},{"key":"10.3233\/ICA-200631_ref3","doi-asserted-by":"crossref","first-page":"287","DOI":"10.2495\/978-1-78466-155-7\/024","article-title":"Using multi-agent technology for the distributed management of a cluster of remote sensing satellites","volume":"90","author":"Skobelev","year":"2016","journal-title":"Complex Systems: Fundamentals & Applications"},{"key":"10.3233\/ICA-200631_ref4","doi-asserted-by":"crossref","unstructured":"Mannion P, Duggan J, Howley E. An experimental review of reinforcement learning algorithms for adaptive traffic signal control. In: Autonomic Road Transport Support Systems. Springer, 2016. pp. 47-66.","DOI":"10.1007\/978-3-319-25808-9_4"},{"key":"10.3233\/ICA-200631_ref5","doi-asserted-by":"crossref","first-page":"4300","DOI":"10.21595\/jve.2017.18924","article-title":"Multi-agent replicator controller for sustainable vibration control of smart structures","volume":"19","author":"Gutierrez\u00a0Soto","year":"2017","journal-title":"J Vibroeng"},{"key":"10.3233\/ICA-200631_ref6","unstructured":"Korczak J, Hernes M, Bac M. Risk avoiding strategy in multi-agent trading system. In: Computer Science and Information Systems (FedCSIS), 2013 Federated Conference on. IEEE, 2013, pp. 1131-1138."},{"key":"10.3233\/ICA-200631_ref7","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/j.artint.2012.09.004","article-title":"Evaluating practical negotiating agents: Results and analysis of the 2011 international competition","volume":"198","author":"Baarslag","year":"2013","journal-title":"Artificial Intelligence"},{"issue":"3","key":"10.3233\/ICA-200631_ref8","doi-asserted-by":"crossref","first-page":"281","DOI":"10.3233\/ICA-150491","article-title":"Multi-Agent System for intelligent Scrum project management","volume":"22","author":"Lin","year":"2015","journal-title":"Integrated Computer-Aided Engineering"},{"issue":"7","key":"10.3233\/ICA-200631_ref9","first-page":"647","article-title":"Ciber-rato: A simulation environment for mobile and autonomous robots","volume":"3","author":"Lau","year":"2002","journal-title":"Electr\u00f3nica e Telecomunica\u00e7\u00f5es"},{"issue":"6419","key":"10.3233\/ICA-200631_ref10","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1126\/science.aar6404","article-title":"A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play","volume":"362","author":"Silver","year":"2018","journal-title":"Science"},{"key":"10.3233\/ICA-200631_ref11","unstructured":"Schrom-Feiertag H, Stubenschrott M, Regal G, Schrammel J, Settgast V. Using cognitive agent-based simulation for the evaluation of indoor wayfinding systems. arXiv preprint arXiv161102459, 2016."},{"key":"10.3233\/ICA-200631_ref12","doi-asserted-by":"crossref","unstructured":"Szymanezyk O, Duckett T, Dickinson P. Agent-based crowd simulation in airports using games technology. In: Transactions on Computational Collective Intelligence VIII. Springer, 2012, pp. 192-213.","DOI":"10.1007\/978-3-642-34645-3_9"},{"key":"10.3233\/ICA-200631_ref13","unstructured":"Hernandez-Leal P, Kaisers M, Baarslag T, de Cote EM. A survey of learning in multiagent environments: Dealing with non-stationarity. arXiv preprint arXiv170709183, 2017."},{"key":"10.3233\/ICA-200631_ref14","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1016\/j.artint.2018.01.002","article-title":"Autonomous agents modelling other agents: A comprehensive survey and open problems","volume":"258","author":"Albrecht","year":"2018","journal-title":"Artificial Intelligence"},{"key":"10.3233\/ICA-200631_ref15","unstructured":"Hernandez-Leal P, Kartal B, Taylor ME. Is multiagent deep reinforcement learning the answer or the question? A brief survey. arXiv preprint arXiv181005587, 2018."},{"issue":"11","key":"10.3233\/ICA-200631_ref16","doi-asserted-by":"crossref","first-page":"1238","DOI":"10.1177\/0278364913495721","article-title":"Reinforcement learning in robotics: A survey","volume":"32","author":"Kober","year":"2013","journal-title":"The International Journal of Robotics Research"},{"key":"10.3233\/ICA-200631_ref17","unstructured":"Bowling M, Veloso M. Rational and Convergent Learning in Stochastic Games. In: Proceedings of the 17th International Joint Conference on Artificial Intelligence\u00a0\u2013 Volume 2. IJCAI\u201901. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc., 2001, pp. 1021-1026. Available from: http\/\/dl.acm.org\/citation.cfm?id=1642194.1642231."},{"key":"10.3233\/ICA-200631_ref18","doi-asserted-by":"crossref","unstructured":"Lau N, Reis LP. FC Portugal-high-level coordination methodologies in soccer robotics. In: Robotic Soccer. InTech, 2007.","DOI":"10.5772\/5130"},{"key":"10.3233\/ICA-200631_ref19","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1007\/978-3-540-88063-9_24","article-title":"A token-based approach to sharing beliefs in a large multiagent team","author":"Velagapudi","year":"2009","journal-title":"Optimization and Cooperative Control Strategies. Springer"},{"key":"10.3233\/ICA-200631_ref20","doi-asserted-by":"crossref","unstructured":"Sim\u00f5es D, Lau N, Reis LP. Multi-agent Neural Reinforcement-Learning System with Communication. In: Rocha \u00c1, Adeli H, Reis LP, Costanzo S, editors. New Knowledge in Information Systems and Technologies. Springer International Publishing, 2019, pp. 3-12.","DOI":"10.1007\/978-3-030-16184-2_1"},{"key":"10.3233\/ICA-200631_ref21","doi-asserted-by":"crossref","unstructured":"Wang SC. Artificial neural network. In: Interdisciplinary Computing in Java Programming. Springer, 2003, pp. 81-100.","DOI":"10.1007\/978-1-4615-0377-4_5"},{"issue":"Preprint","key":"10.3233\/ICA-200631_ref22","first-page":"1","article-title":"A scalable approach based on deep learning for big data time series forecasting","author":"Torres","year":"2018","journal-title":"Integrated Computer-Aided Engineering"},{"key":"10.3233\/ICA-200631_ref23","doi-asserted-by":"crossref","first-page":"134413","DOI":"10.1016\/j.scitotenv.2019.134413","article-title":"A novel deep learning neural network approach for predicting flash flood susceptibility: A case study at a high frequency tropical storm area","volume":"701","author":"Bui","year":"2020","journal-title":"Science of The Total Environment"},{"key":"10.3233\/ICA-200631_ref24","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1016\/j.soildyn.2017.05.013","article-title":"NEEWS: a novel earthquake early warning model using neural dynamic classification and neural dynamic optimization","volume":"100","author":"Rafiei","year":"2017","journal-title":"Soil Dynamics and Earthquake Engineering"},{"issue":"6","key":"10.3233\/ICA-200631_ref25","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1111\/mice.12359","article-title":"Deep learning for accelerated seismic reliability analysis of transportation networks","volume":"33","author":"Nabian","year":"2018","journal-title":"Computer-Aided Civil and Infrastructure Engineering"},{"issue":"12","key":"10.3233\/ICA-200631_ref26","doi-asserted-by":"crossref","first-page":"3074","DOI":"10.1109\/TNNLS.2017.2682102","article-title":"A new neural dynamic classification algorithm","volume":"28","author":"Rafiei","year":"2017","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"4","key":"10.3233\/ICA-200631_ref27","doi-asserted-by":"crossref","first-page":"337","DOI":"10.3233\/ICA-170551","article-title":"Image recognition with deep neural networks in presence of noise\u00a0\u2013 dealing with and taking advantage of distortions","volume":"24","author":"Koziarski","year":"2017","journal-title":"Integrated Computer-Aided Engineering"},{"issue":"9","key":"10.3233\/ICA-200631_ref28","doi-asserted-by":"crossref","first-page":"1950010","DOI":"10.1142\/S0129065719500102","article-title":"Scaled subprofile modeling and convolutional neural networks for the identification of Parkinson\u2019s disease in 3d nuclear imaging data","volume":"29","author":"Manzanera","year":"2019","journal-title":"International Journal of Neural Systems"},{"key":"10.3233\/ICA-200631_ref29","first-page":"1","article-title":"Vehicle type detection by ensembles of convolutional neural networks operating on super resolved images","author":"Molina-Cabello","year":"2018","journal-title":"Integrated Computer-Aided Engineering"},{"issue":"5","key":"10.3233\/ICA-200631_ref30","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1111\/mice.12425","article-title":"Image-based post-disaster inspection of reinforced concrete bridge systems using deep learning with Bayesian optimization","volume":"34","author":"Liang","year":"2019","journal-title":"Computer-Aided Civil and Infrastructure Engineering"},{"issue":"5","key":"10.3233\/ICA-200631_ref31","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1111\/mice.12421","article-title":"Zernike-moment measurement of thin-crack width in images enabled by dual-scale deep learning","volume":"34","author":"Ni","year":"2019","journal-title":"Computer-Aided Civil and Infrastructure Engineering"},{"issue":"8","key":"10.3233\/ICA-200631_ref32","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1111\/mice.12440","article-title":"Encoder-decoder network for pixel-level road crack detection in black-box images","volume":"34","author":"Bang","year":"2019","journal-title":"Computer-Aided Civil and Infrastructure Engineering"},{"issue":"7","key":"10.3233\/ICA-200631_ref33","doi-asserted-by":"crossref","first-page":"616","DOI":"10.1111\/mice.12433","article-title":"Automatic pixel-level multiple damage detection of concrete structure using fully convolutional network","volume":"34","author":"Li","year":"2019","journal-title":"Computer-Aided Civil and Infrastructure Engineering"},{"issue":"9","key":"10.3233\/ICA-200631_ref34","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1111\/mice.12458","article-title":"Deep leaf-bootstrapping generative adversarial network for structural image data augmentation","volume":"34","author":"Gao","year":"2019","journal-title":"Computer-Aided Civil and Infrastructure Engineering"},{"key":"10.3233\/ICA-200631_ref35","first-page":"48","article-title":"Approximation with artificial neural networks","volume":"24","author":"Cs\u00e1ji","year":"2001","journal-title":"Faculty of Sciences, Etvs Lornd University, Hungary"},{"issue":"4","key":"10.3233\/ICA-200631_ref36","doi-asserted-by":"crossref","first-page":"1850011","DOI":"10.1142\/S0129065718500119","article-title":"Neonatal seizure detection using deep convolutional neural networks","volume":"29","author":"Ansari","year":"2019","journal-title":"International Journal of Neural Systems"},{"issue":"8","key":"10.3233\/ICA-200631_ref37","doi-asserted-by":"crossref","first-page":"1850009","DOI":"10.1142\/S0129065718500090","article-title":"Deep neural architectures for mapping scalp to intracranial EEG","volume":"28","author":"Antoniades","year":"2018","journal-title":"International Journal of Neural Systems"},{"issue":"4","key":"10.3233\/ICA-200631_ref38","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1111\/mice.12422","article-title":"Deep neural network with high-order neuron for the prediction of foamed concrete strength","volume":"34","author":"Nguyen","year":"2019","journal-title":"Computer-Aided Civil and Infrastructure Engineering"},{"key":"10.3233\/ICA-200631_ref39","unstructured":"Arulkumaran K, Cully A, Togelius J. Alphastar: An evolutionary computation perspective. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2019, pp. 314-315."},{"key":"10.3233\/ICA-200631_ref40","unstructured":"Berner C, Brockman G, Chan B, Cheung V, Debiak P, Dennison C, et al. Dota 2 with Large Scale Deep Reinforcement Learning. arXiv preprint arXiv191206680, 2019."},{"key":"10.3233\/ICA-200631_ref41","unstructured":"Sutton RS, Barto AG, et al. Introduction to reinforcement learning. vol. 135, MIT press Cambridge, 1998."},{"key":"10.3233\/ICA-200631_ref42","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016","journal-title":"International conference on machine learning"},{"issue":"2","key":"10.3233\/ICA-200631_ref43","doi-asserted-by":"crossref","first-page":"171","DOI":"10.3233\/ICA-170538","article-title":"Layer multiplexing FPGA implementation for deep back-propagation learning","volume":"24","author":"Ortega-Zamorano","year":"2017","journal-title":"Integrated Computer-Aided Engineering"},{"key":"10.3233\/ICA-200631_ref44","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O. Proximal policy optimization algorithms. arXiv preprint arXiv170706347, 2017."},{"key":"10.3233\/ICA-200631_ref45","doi-asserted-by":"crossref","unstructured":"Foerster JN, Farquhar G, Afouras T, Nardelli N, Whiteson S. Counterfactual multi-agent policy gradients. In: Thirty-Second AAAI Conference on Artificial Intelligence, 2018.","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"10.3233\/ICA-200631_ref46","unstructured":"Sukhbaatar S, Fergus R, et al. Learning multiagent communication with backpropagation. In: Advances in Neural Information Processing Systems, 2016, pp. 2244-2252."},{"key":"10.3233\/ICA-200631_ref47","unstructured":"Claus C, Boutilier C. The Dynamics of Reinforcement Learning in Cooperative Multiagent Systems. In: Proceedings of the Fifteenth National\/Tenth Conference on Artificial Intelligence\/Innovative Applications of Artificial Intelligence. AAAI \u201998\/IAAI \u201998. Menlo Park, CA, USA: American Association for Artificial Intelligence; 1998. pp. 746-752. Available from: http\/\/dl.acm.org\/citation.cfm?id=295240.295800."},{"key":"10.3233\/ICA-200631_ref48","unstructured":"Sunehag P, Lever G, Gruslys A, Czarnecki WM, Zambaldi V, Jaderberg M, et al. Value-Decomposition Networks For Cooperative Multi-Agent Learning Based On Team Reward. In: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems. AAMAS \u201918. Richland, SC: International Foundation for Autonomous Agents and Multiagent Systems; 2018, pp. 2085-2087. Available from: http\/\/dl.acm.org\/citation.cfm?id=3237383.3238080."},{"key":"10.3233\/ICA-200631_ref50","doi-asserted-by":"crossref","unstructured":"Mordatch I, Abbeel P. Emergence of grounded compositional language in multi-agent populations. In: Thirty-Second AAAI Conference on Artificial Intelligence, 2018.","DOI":"10.1609\/aaai.v32i1.11492"},{"issue":"3","key":"10.3233\/ICA-200631_ref51","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"Williams","year":"1992","journal-title":"Machine Learning"},{"key":"10.3233\/ICA-200631_ref52","doi-asserted-by":"crossref","unstructured":"Das A, Kottur S, Moura JM, Lee S, Batra D. Learning cooperative visual dialog agents with deep reinforcement learning. In: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2951-2960.","DOI":"10.1109\/ICCV.2017.321"},{"key":"10.3233\/ICA-200631_ref53","unstructured":"Lazaridou A, Peysakhovich A, Baroni M. Multi-agent cooperation and the emergence of (natural) language. Proceedings of the International Conference on Learning Representations, 2017."},{"key":"10.3233\/ICA-200631_ref54","unstructured":"Sim\u00f5es D, Lau N, Reis LP. Multi-agent Double Deep Q-Networks. In: Oliveira E, Gama J, Vale Z, Lopes Cardoso H, editors. Progress in Artificial Intelligence. Lecture Notes in Computer Science, vol. 10423. Springer International Publishing, 2017, pp. 123-134."},{"issue":"4","key":"10.3233\/ICA-200631_ref55","doi-asserted-by":"crossref","first-page":"819","DOI":"10.1287\/moor.27.4.819.297","article-title":"The complexity of decentralized control of Markov decision processes","volume":"27","author":"Bernstein","year":"2002","journal-title":"Mathematics of Operations Research"},{"key":"10.3233\/ICA-200631_ref56","unstructured":"Foerster JN, Assael YM, de Freitas N, Whiteson S. Learning to Communicate with Deep Multi-Agent Reinforcement Learning. CoRR. 2016abs\/1605.06676, Available from: http\/\/arxiv.org\/abs\/1605.06676."},{"key":"10.3233\/ICA-200631_ref57","doi-asserted-by":"crossref","unstructured":"Gebhardt GH, Daun K, Schnaubelt M, Neumann G. Learning robust policies for object manipulation with robot swarms. In: 2018 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2018, pp. 7688-7695.","DOI":"10.1109\/ICRA.2018.8463215"},{"key":"10.3233\/ICA-200631_ref58","doi-asserted-by":"crossref","unstructured":"Saska M, Chudoba J, Precil L, Thomas J, Loianno G, Tresnak A, et al. Autonomous deployment of swarms of micro-aerial vehicles in cooperative surveillance. In: Unmanned Aircraft Systems (ICUAS), 2014 International Conference on. IEEE, 2014, pp. 584-595.","DOI":"10.1109\/ICUAS.2014.6842301"},{"key":"10.3233\/ICA-200631_ref59","doi-asserted-by":"crossref","first-page":"1950014","DOI":"10.1142\/S012906571950014X","article-title":"Performing multi-target regression via a parameter sharing-based deep network","author":"Reyes","year":"2019","journal-title":"International Journal of Neural Systems"},{"key":"10.3233\/ICA-200631_ref60","doi-asserted-by":"crossref","unstructured":"Sim\u00f5es D, Lau N, Reis LP. Guided Deep Reinforcement Learning in the GeoFriends2 Environment. In: IJCNN 18: International Joint-Conference on Neural Networks, 2018, pp. 375-381.","DOI":"10.1109\/IJCNN.2018.8489372"},{"issue":"1","key":"10.3233\/ICA-200631_ref61","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11721-013-0089-4","article-title":"Cooperative navigation in robotic swarms","volume":"8","author":"Ducatelle","year":"2014","journal-title":"Swarm Intelligence"},{"key":"10.3233\/ICA-200631_ref62","unstructured":"Gebhardt GHW, H\u00fcttenrauch M, Neumann G. Using M-Embeddings to Learn Control Strategies for Robot Swarms. Submitted to Swarm Intelligence. submitted; Available from: https:\/\/www.ias.informatik.tu-darmstadt.de\/uploads\/Team\/GregorGebhardt\/UsingMEmbeddingsToLearnControlStrategiesForRobotSwarms.pdf."},{"key":"10.3233\/ICA-200631_ref65","doi-asserted-by":"crossref","unstructured":"Sim\u00f5es D, Lau N, Reis LP. Multi-Agent Deep Reinforcement Learning with Emergent Communication. In: 2019 International Joint Conference on Neural Networks (IJCNN). IEEE, 2019.","DOI":"10.1109\/IJCNN.2019.8852293"},{"issue":"7","key":"10.3233\/ICA-200631_ref66","doi-asserted-by":"crossref","first-page":"966","DOI":"10.1016\/j.robot.2013.08.006","article-title":"Kilobot: A low cost robot with scalable operations designed for collective behaviors","volume":"62","author":"Rubenstein","year":"2014","journal-title":"Robotics and Autonomous Systems"},{"key":"10.3233\/ICA-200631_ref67","unstructured":"Kitano H, Asada M, Kuniyoshi Y, Noda I, Osawa E. Robocup: The robot world cup initiative. In: Proceedings of the first international conference on Autonomous agents. ACM, 1997, pp. 340-347."},{"key":"10.3233\/ICA-200631_ref68","unstructured":"Shamsuddin S, Ismail LI, Yussof H, Zahari NI, Bahari S, Hashim H, et al. Humanoid robot NAO: Review of control and motion exploration. In: 2011 IEEE International Conference on Control System, Computing and Engineering, IEEE, 2011, pp. 511-516."},{"key":"10.3233\/ICA-200631_ref69","unstructured":"Reis LP, Lau N. FC Portugal team description: RoboCup 2000 simulation league champion. In: Robot Soccer World Cup. Springer, 2000, pp. 29-40."},{"key":"10.3233\/ICA-200631_ref70","unstructured":"Nair V, Hinton GE. Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th international conference on machine learning (ICML-10), 2010, pp. 807-814."},{"key":"10.3233\/ICA-200631_ref71","unstructured":"Clevert DA, Unterthiner T, Hochreiter S. Fast and accurate deep network learning by exponential linear units (elus). International Conference for Learning Representations, 2016."},{"key":"10.3233\/ICA-200631_ref72","unstructured":"Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. In: Teh YW, Titterington M, editors. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. vol.\u00a09 of Proceedings of Machine Learning Research. Chia Laguna Resort, Sardinia, Italy: PMLR, 2010, pp. 249-256. Available from: http\/\/proceedings.mlr.press\/v9\/glorot10a.html."},{"key":"10.3233\/ICA-200631_ref73","unstructured":"Kingma DP, Ba J. Adam: A method for stochastic optimization. 3rd International Conference for Learning Representations, San Diego, 2015."}],"container-title":["Integrated Computer-Aided Engineering"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/ICA-200631","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T13:09:47Z","timestamp":1741612187000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/ICA-200631"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,11]]},"references-count":70,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.3233\/ica-200631","relation":{},"ISSN":["1069-2509","1875-8835"],"issn-type":[{"value":"1069-2509","type":"print"},{"value":"1875-8835","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,11]]}}}