The DOI matches its Crossref record; 99 of the 101 references it cites were found in a registry or an index.
Neuroevolution: from architectures to learning
Open accessOverview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Neural Networks: A Comprehensive Foundation
Haykin, S. (1998) · Cited by 30,070
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. G. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.1998.712192 · Cited by 27,225 · cited 1×
“Reinforcement learning is a class of learning algorithms that attempts to estimate explicitly or implicitly the value of the states experienced by the agents in order to favor the choice of those actions that maximize the amount of positive reinforcement received by the agent over time [84].”
BackgroundReinforcement Learning: An Introduction
(2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 24,496
Hodgkin, A. L., & Huxley, A. F. (1952) · The Journal of Physiology · doi:10.1113/jphysiol.1952.sp004764 · Cited by 23,191 · cited 1×
“describe in detail the electrochemical processes that produce spiking events by means of differential equations [34].”
BackgroundParallel Distributed Processing: Explorations in the Microstructure of Cognition: Foundations
Rumelhart, D. E., McClelland, J. L., & AU (1986) · doi:10.7551/mitpress/5236.001.0001 · Cited by 15,686
A neural substrate of prediction and reward
Schultz, W., Dayan, P., & Montague, P. R. (1997) · Science · doi:10.1126/science.275.5306.1593 · Cited by 9,388 · cited 1×
“learning mechanisms that result in behaviors similar to those produced by Reinforcement learning [50, 74].”
Proceedings of the 19th International Joint Conference on Artificial Intelligence
Pujol, J. M., Delgado, J., Ramon Sangüesa, A., & Flache, A. (2005) · International Joint Conference on Artificial Intelligence · Cited by 5,771
Learning to predict by the methods of temporal differences
Sutton, R. S. (1988) · Machine Learning · doi:10.1007/bf00115009 · Cited by 5,148 · cited 1×
“The actor-critic model [5, 83 ] for example, is a simple neural architecture that implements reinforcement learning with two modules, the Actor and the Critic shown in Fig. 12. Both modules receive information on the current sensory state.”
MethodCompletely Derandomized Self-Adaptation in Evolution Strategies
Hansen, N., & Ostermeier, A. (2001) · Evolutionary Computation · doi:10.1162/106365601750190398 · Cited by 4,397
WIDROW, B., & HOFF, M. E. (1960) · doi:10.21236/ad0241531 · Cited by 4,009
Evolving Neural Networks through Augmenting Topologies
Stanley, K. O., & Miikkulainen, R. (2002) · Evolutionary Computation · doi:10.1162/106365602320169811 · Cited by 3,258 · cited 9×
“Redrawn from Stanley and Miikkulainen [79] genotype is a collection of rules governing the process of cell divisions (a single cell is replaced by two ''daughter'' cells) and transformations (new connections can be added and the weights of the connections departing from a cell can be modified).”
MethodInfluentialNazuno, J. F. (2000) · Computación y Sistemas · Cited by 3,201
Visual Feature Integration and the Temporal Correlation Hypothesis
Singer, W., & Gray, C. M. (1995) · Annual Review of Neuroscience · doi:10.1146/annurev.ne.18.030195.003011 · Cited by 3,123 · cited 1×
“This hints at the fact that spiking neurons may use other ways to efficiently encode information, such as the firing time of single spikes or the temporal coincidence of spikes coming from multiple sources [77, 67].”
BackgroundEvolving artificial neural networks
Yao, X. (1999) · Proceedings of the IEEE · doi:10.1109/5.784219 · Cited by 2,981
Barto, A. G. (1998) · IFAC Proceedings Volumes · doi:10.1016/s1474-6670(17)38315-5 · Cited by 2,976
Spikes: Exploring the Neural Code
Rieke, F. M., Warland, D., van Steveninck, R. R. D. R., & Bialek, W. (1996) · Medical Entomology and Zoology · Cited by 2,844
Evolutionsstrategie : Optimierung technischer Systeme nach Prinzipien der biologischen Evolution
Rechenberg, I. (1973) · Frommann-Holzboog eBooks · Cited by 2,440
A framework for mesencephalic dopamine systems based on predictive Hebbian learning
Montague, P., Dayan, P., & Sejnowski, T. (1996) · The Journal of Neuroscience · doi:10.1523/jneurosci.16-05-01936.1996 · Cited by 2,066 · cited 1×
“learning mechanisms that result in behaviors similar to those produced by Reinforcement learning [50, 74].”
Genetic programming II: Automatic discovery of reusable programs
(1995) · Computers & Mathematics with Applications · doi:10.1016/0898-1221(95)90099-3 · Cited by 1,901
Baldwin, J. M. (1896) · The American Naturalist · doi:10.1086/276408 · Cited by 1,781
Banzhaf, W., Francone, F. D., Keller, R. E., & Nordin, P. C. (1998) · Cited by 1,678
On Evolution, Search, Optimization, Genetic Algorithms and Martial Arts : Towards Memetic Algorithms
Moscato, P. (1989) · Cited by 1,516
Vent, W. (1975) · Feddes Repertorium · doi:10.1002/fedr.19750860506 · Cited by 1,331
(1991) · Choice Reviews Online · doi:10.5860/choice.29-0605 · Cited by 1,284 · cited 1×
“The existing evidence points to the combined action of evolved value systems [58] and neuromodulatory effects [2, 18].”
BackgroundModels of Information Processing in the Basal Ganglia
(1994) · doi:10.7551/mitpress/4708.001.0001 · Cited by 1,190
Pfeifer, R., & Scheier, C. (1999) · The MIT Press eBooks · doi:10.7551/mitpress/6979.001.0001 · Cited by 1,155
Genetic Programming: An Introduction
Banzhaf, W., Keller, R. E., & Nordin, P. C. (1997) · Cited by 1,052
Training feedforward neural networks using genetic algorithms
Montana, D. J., & Davis, L. D. (1989) · International Joint Conference on Artificial Intelligence · Cited by 1,006
Approximation of dynamical systems by continuous time recurrent neural networks
Funahashi, K.-I., & Nakamura, Y. (1993) · Neural Networks · doi:10.1016/s0893-6080(05)80125-x · Cited by 980 · cited 1×
“While being one of the simplest nonlinear, continuous dynamic network models, CTRNNs are universal dynamic approximators [24].”
BackgroundThe neural basis of cognitive development: A constructivist manifesto
Quartz, S. R., & Sejnowski, T. J. (1997) · Behavioral and Brain Sciences · doi:10.1017/s0140525x97001581 · Cited by 864
How Learning Can Guide Evolution.
Hinton, G. E., & Nowlan, S. J. (1987) · Addison-Wesley Longman Publishing Co., Inc. eBooks · Cited by 845
Genetic algorithms and neural networks: optimizing connections and connectivity
Whitley, D., Starkweather, T., & Bogart, C. (1990) · Parallel Computing · doi:10.1016/0167-8191(90)90086-o · Cited by 747 · cited 1×
“for a different classification task by other authors [88].”
ResultHaasdijk, E., Bredeche, N., Nolfi, S., & Eiben, A. E. (2014) · Evolutionary Intelligence · doi:10.1007/s12065-014-0113-7 · Cited by 608
Combinations of genetic algorithms and neural networks: a survey of the state of the art
Schaffer, J. D., Whitley, D., & Eshelman, L. J. (2003) · [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks · doi:10.1109/cogann.1992.273950 · Cited by 570 · cited 1×
“It has been argued [72, 61] that evolving neural networks may not be trivial because the population may include individuals with competing conventions (see Fig.”
BackgroundEvolving Dynamical Neural Networks for Adaptive Behavior
Beer, R. D., & Gallagher, J. C. (1992) · Adaptive Behavior · doi:10.1177/105971239200100105 · Cited by 500 · cited 9×
“Evolution of CTRNNs has been applied to difficult problems such as robot control [86].”
MethodInfluentialIncremental Evolution of Complex General Behavior
Gomez, F., & Miikkulainen, R. (1997) · Adaptive Behavior · doi:10.1177/105971239700500305 · Cited by 428 · cited 6×
“Redrawn from Stanley and Miikkulainen [79] genotype is a collection of rules governing the process of cell divisions (a single cell is replaced by two ''daughter'' cells) and transformations (new connections can be added and the weights of the connections departing from a cell can be modified).”
InfluentialCompetitive Coevolution through Evolutionary Complexification
Stanley, K. O., & Miikkulainen, R. (2004) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1338 · Cited by 413 · cited 1×
“Neuro-evolution of augmenting topologies (NEAT) has been applied to many problems such as pole balancing [79], robot control [80], computer games [66, 82] or an automobile crash warning system [81].”
MethodIs Heterosynaptic modulation essential for stabilizing hebbian plasiticity and memory
Bailey, C. H., Giustetto, M., Huang, Y.-Y., Hawkins, R. D., & Kandel, E. R. (2000) · Nature Reviews Neuroscience · doi:10.1038/35036191 · Cited by 382 · cited 1×
“The existing evidence points to the combined action of evolved value systems [58] and neuromodulatory effects [2, 18].”
BackgroundArita, T., & Suzuki, R. (2000) · Artificial Life VII · doi:10.7551/mitpress/1432.003.0027 · Cited by 353 · cited 1×
“Ackley and Littman [1] for instance claimed that in artificial evolution, where inherited characters can easily be coded into the genotype given that the mapping between genotype and phenotype is generally quite simple, it is preferable to use Lamarckian evolution.”
BackgroundEfficient reinforcement learning through symbiotic evolution
Moriarty, D. E., & Miikkulainen, R. (1996) · Machine Learning · doi:10.1007/bf00114722 · Cited by 325 · cited 5×
“Redrawn from Stanley and Miikkulainen [79] genotype is a collection of rules governing the process of cell divisions (a single cell is replaced by two ''daughter'' cells) and transformations (new connections can be added and the weights of the connections departing from a cell can be modified).”
BackgroundInfluentialAutomatic Definition of Modular Neural Networks
Gruau, F. (1994) · Adaptive Behavior · doi:10.1177/105971239400300202 · Cited by 269 · cited 7×
“Cellular encodings have been applied to different control problems such as pole balancing [29] or the control of a hexapod robot [28].”
BackgroundMethodInfluentialA Comparison between Cellular Encoding and Direct Encoding for Genetic Neural Networks
(1996) · Genetic Programming 1996 · doi:10.7551/mitpress/3242.003.0013 · Cited by 268 · cited 1×
“Cellular encodings have been applied to different control problems such as pole balancing [29] or the control of a hexapod robot [28].”
MethodLearning to Adapt to Changing Environments in Evolving Neural Networks
Nolfi, S., & Parisi, D. (1996) · Adaptive Behavior · doi:10.1177/105971239600500104 · Cited by 251 · cited 3×
“Nolfi and Parisi [56] evolved a neural controller for a mobile robot whose output layer included two ''teaching neurons'' that were used to modify the connection weights from the sensory neurons to the motor neurons with backpropagation learning during the robot's lifetime.”
BackgroundInfluentialDynamic Parameter Encoding for genetic algorithms
Schraudolph, N. N., & Belew, R. K. (1992) · Machine Learning · doi:10.1007/bf00993252 · Cited by 250 · cited 3×
“In this case, Belew et al. [8] found that the best evolved networks employed learning rates ten times higher than values suggested before (i.e., much less than 1.0), but this result may depend on several factors, such as the order of presentation of the patterns, the number of learning cycles allowed before computing…”
MethodInfluentialEvolutionary robots with on-line self-organization and behavioral fitness
Floreano, D., & Urzelai, J. (2000) · Neural Networks · doi:10.1016/s0893-6080(00)00032-0 · Cited by 240 · cited 2×
“Finally, Floreano and Urzelai [21] showed that dynamic environments favor the genetic expression of plastic connections over static connections.”
BackgroundSelf-citationThe Evolution of Learning: An Experiment in Genetic Connectionism
Chalmers, D. J. (1991) · Connectionist Models · doi:10.1016/b978-1-4832-1448-1.50014-7 · Cited by 193 · cited 1×
“Chalmers [11] suggested to describe this function as a linear combination of the products between the variables weighted by constants.”
BackgroundWulfram Gerstner, B. (1999) · Cited by 191
Evolving an expert checkers playing program without using human expertise
Chellapilla, K., & Fogel, D. B. (2001) · IEEE Transactions on Evolutionary Computation · doi:10.1109/4235.942536 · Cited by 186 · cited 1×
“Evolved neural networks with direct encoding have also been applied to a variety of other problems such as game playing [13], data classification [12] or the control of robot swarms [85].”
BackgroundEvolving modular genetic regulatory networks
Bongard, J. (2003) · Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600) · doi:10.1109/cec.2002.1004528 · Cited by 185 · cited 3×
“The so-called implicit encoding is frequently used as a representation for GRN models [10]”
MethodInfluentialEnsemble Learning Using Multi-Objective Evolutionary Algorithms
Chandra, A., & Yao, X. (2006) · Journal of Mathematical Modelling and Algorithms · doi:10.1007/s10852-005-9020-3 · Cited by 179 · cited 1×
“Evolved neural networks with direct encoding have also been applied to a variety of other problems such as game playing [13], data classification [12] or the control of robot swarms [85].”
BackgroundNolfi, S., & Floreano, D. (1999) · Autonomous Robots · doi:10.1023/a:1008973931182 · Cited by 175 · cited 1×
“with some form of learning [55].”
Self-citation(2003) · Elsevier eBooks · doi:10.1016/b978-0-12-428765-5.x5029-4 · Cited by 174
Landscapes, Learning Costs, and Genetic Assimilation
Mayley, G. (1996) · Evolutionary Computation · doi:10.1162/evco.1996.4.3.213 · Cited by 173 · cited 2×
“3 By systematically varying the cost of learning and the correlation between the learning space and the evolutionary space, Mayley [47] showed that: (1) the adaptive advantage of learning is proportional to the correlation between the two search spaces; (2) the assimilation of characters first acquired through learnin…”
BackgroundNiv, Y., Joel, D., Meilijson, I., & Ruppin, E. (2002) · Adaptive Behavior · doi:10.1177/10597123020101001 · Cited by 170
Shapiro, J. A. (2005) · Gene · doi:10.1016/j.gene.2004.11.020 · Cited by 166 · cited 4×
“The results of his computational experiments showed that his simple model allowed for the evolution of complex morphologies capable of simple locomotion behaviors and indicated that the evolution of modular GRNs was beneficial for the success of the agents.”
BackgroundInfluentialBetter Living Through Chemistry: Evolving GasNets for Robot Control
Husbands, P., Smith, T., Jakobi, N., & O'Shea, M. (1998) · Connection Science · doi:10.1080/095400998116404 · Cited by 162 · cited 4×
“This is in line with Magg and Philippides [43] whose results indicate that GasNets perform extremely well on tasks that require some kind of neural pattern generator or timer, while performing worse on tasks which do not require different time scales in the network.”
ResultInfluentialNeuroevolution for reinforcement learning using evolution strategies
Igel, C. (2004) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2003.1299414 · Cited by 147 · cited 1×
“Recent benchmark experiments with Evolution Strategies [62], which use a floating-point representation of the synaptic weights, have reported excellent performance with direct encoding of a small, fixed architecture [38].”
BackgroundEvolution of Spiking Neural Controllers for Autonomous Vision-Based Robots
Floreano, D., & Mattiussi, C. (2001) · Lecture notes in computer science · doi:10.1007/3-540-45502-7_2 · Cited by 139 · cited 4×
“From Mattiussi et al. [46] Reil [63, 64] studied the structural properties of such gene networks with a simple computational model.”
BackgroundInfluentialSelf-citationSequential Behavior and Learning in Evolved Dynamical Neural Networks
Yamauchi, B. M., & Beer, R. D. (1994) · Adaptive Behavior · doi:10.1177/105971239400200301 · Cited by 137 · cited 1×
“For example, Yamauchi and Beer [90] evolved CTRNNs capable of generating and learning short sequences without synaptic plasticity.”
BackgroundReil, T. (1999) · Lecture notes in computer science · doi:10.1007/3-540-48304-7_63 · Cited by 130 · cited 4×
“From Mattiussi et al. [46] Reil [63, 64] studied the structural properties of such gene networks with a simple computational model.”
BackgroundInfluentialEvolution of Plastic Neurocontrollers for Situated Agents
Floreano, D., & Francesco Mondada, C. (1996) · The MIT Press eBooks · doi:10.7551/mitpress/3118.003.0049 · Cited by 126
Self-citationPhenotypic plasticity in evolving neural networks
Nolfi, S., Miglino, O., & Parisi, D. (2005) · From Perception to Action Conference (PerAc) · doi:10.1109/fpa.1994.636092 · Cited by 123
Evolution of Plastic Neurocontrollers for Situated Agents
Floreano, D., & Mondada, F. (1996) · Repository for Publications and Research Data (ETH Zurich) · doi:10.3929/ethz-a-010111547 · Cited by 118 · cited 1×
“Floreano and Mondada [20] allowed evolution to choose among four Hebbian learning rules for each synaptic connection and evaluated the approach for a mobile robot requested to solve a sequential task involving multiple sensory modalities and environmental landmarks.”
BackgroundSelf-citationEvolution of Adaptive Synapses: Robots with Fast Adaptive Behavior in New Environments
Urzelai, J., & Floreano, D. (2001) · Evolutionary Computation · doi:10.1162/10636560152642887 · Cited by 99 · cited 1×
“results indicated that the evolved robots had the ability to adapt on-the-fly to changed environmental conditions (including spatial reorganization, textures and even robot morphologies) without incremental evolution [87].”
BackgroundSelf-citationComputational Models of Neuromodulation
Fellous, J., & Linster, C. (1998) · Neural Computation · doi:10.1162/089976698300017476 · Cited by 99 · cited 1×
“The existing evidence points to the combined action of evolved value systems [58] and neuromodulatory effects [2, 18].”
BackgroundProceedings of the 1998 IEEE International Conference on Evolutionary Computation [Book Review]
Kennedy, J. (1999) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.1999.771169 · Cited by 77
Evolving neuromodulatory topologies for reinforcement learning-like problems
Soltoggio, A., Durr, P., Mattiussi, C., & Floreano, D. (2007) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2007.4424781 · Cited by 74 · cited 1×
“solution during evolution, outperforming the results obtained with hand-designed value-based learning architectures [78].”
ResultSelf-citationExploring the T-Maze: Evolving Learning-Like Robot Behaviors Using CTRNNs
Blynel, J., & Floreano, D. (2003) · Lecture notes in computer science · doi:10.1007/3-540-36605-9_54 · Cited by 71 · cited 5×
“Floreano and Mattiussi [19] evolved networks of spiking neurons for solving a non-trivial vision-based navigation task.”
BackgroundInfluentialSelf-citationA comparison of matrix rewriting versus direct encoding for evolving neural networks
Siddiqi, A. A., & Lucas, S. M. (2002) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/icec.1998.699787 · Cited by 71 · cited 2×
“However, Siddiqi and Lucas [76] showed that the inferior performance of the direct representation in Kitano’s work did not result from the difference in the network representations but from different initial populations.”
BackgroundAcquiring evolvability through adaptive representations
Reisinger, J., & Miikkulainen, R. P. (2007) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/1276958.1277164 · Cited by 70 · cited 1×
“Reisinger and Miikkulainen [ 65 ] showed that an implicit encoding very similar to AGE outperforms NEAT on a complex board-game task.”
BackgroundEvolution of Plastic Control Networks
Floreano, D., & Urzelai, J. (2001) · Autonomous Robots · doi:10.1023/a:1012459627968 · Cited by 61 · cited 1×
“Floreano and Urzelai [ 22 ] also showed that a morphogenetic approach can greatly benefit from co-evolution of synaptic plasticity because the strengths of the growing connections are developed by learning rules that are coevolved with the developmental rules.”
BackgroundSelf-citationNeuroevolution with Analog Genetic Encoding
Dürr, P., Mattiussi, C., & Floreano, D. (2006) · Lecture notes in computer science · doi:10.1007/11844297_68 · Cited by 60 · cited 2×
“When compared to NEAT, AGE reported equal performance on a non-Markovian double-pole balancing problem [ 16 ], while both algorithms performed better than a developmental encoding (CE) and a coevolution method (ESP).”
MethodInfluentialSelf-citationNiv, Y., Joel, D., Meilijson, I., & Ruppin, E. (2002) · Adaptive Behavior · doi:10.1177/1059-712302-010001-01 · Cited by 54
Evolving spike-timing-dependent plasticity for single-trial learning in robots
Paolo, E. A. D. (2003) · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences · doi:10.1098/rsta.2003.1256 · Cited by 51 · cited 9×
“Saggie et al. [70] compared spiking neural networks with conventional static ANNs in a simple setup where an agent had to search food and avoid poison in a simulated grid world.”
MethodInfluentialAn Evolutionary Ecological Approach to the Study of Learning Behavior Using a Robot-Based Model
Tuci, E., Quinn, M., & Harvey, I. R. (2002) · Adaptive Behavior · doi:10.1177/1059712302919993004 · Cited by 49 · cited 1×
“Evolution of CTRNNs has been applied to difficult problems such as robot control [86].”
MethodA Neural Learning Classifier System with Self-Adaptive Constructivism for Mobile Robot Control
Hurst, J., & Bull, L. (2006) · Artificial Life · doi:10.1162/artl.2006.12.3.353 · Cited by 48 · cited 1×
“For example, Hurst and Bull [35] addressed the control of a simulated robot in a maze task.”
BackgroundNeuroevolution of an automobile crash warning system
Stanley, K. O., Kohl, N., Sherony, R., & Miikkulainen, R. P. (2005) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/1068009.1068340 · Cited by 48 · cited 1×
“Neuro-evolution of augmenting topologies (NEAT) has been applied to many problems such as pole balancing [79], robot control [80], computer games [66, 82] or an automobile crash warning system [81].”
MethodThe use of genetic algorithms for the development of sensorimotor control systems
Husbands, P., Harvey, I. R., Cliff, D., & Miller, G. F. (2005) · From Perception to Action Conference (PerAc) · doi:10.1109/fpa.1994.636088 · Cited by 46
Wulfram Gerstner, B. (1998) · The MIT Press eBooks · doi:10.7551/mitpress/5704.003.0005 · Cited by 45
The Evolution of Learning Algorithms for Artificial Neural NetworksPreprint
Baxter, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.01203 · Cited by 42
Evolving a learning algorithm for the binary perceptron
Fontanari, J. F., & Meir, R. (1991) · Network Computation in Neural Systems · doi:10.1088/0954-898x_2_4_002 · Cited by 42
Coevolving Strategies for General Game Playing
Reisinger, J., Bahçeci, E., Karpov, I., & Miikkulainen, R. P. (2007) · IEEE Conference on Computational Intelligence and Games (CIG) · doi:10.1109/cig.2007.368115 · Cited by 38 · cited 1×
“Neuro-evolution of augmenting topologies (NEAT) has been applied to many problems such as pole balancing [79], robot control [80], computer games [66, 82] or an automobile crash warning system [81].”
MethodGasNets and other evovalble neural networks applied to bipedal locomotion
Husbands, P., & McHale, G. (2004) · Figshare · Cited by 30
Evolving Developing Spiking Neural Networks
Federici, D. (2005) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2005.1554730 · Cited by 27 · cited 1×
“Federici [17] combined an integrate and fire neuron model with a correlation-based synaptic plasticity model and a developmental encoding.”
MethodA “Spike Interval Information Coding” representation for ATR’s CAM-Brain Machine (CBM)
Korkin, M., Nawa, N. E., & de GARIS, H. (1998) · Lecture notes in computer science · doi:10.1007/bfb0057627 · Cited by 24 · cited 1×
“[41] evolved spiking neural networks which could produce time-dependent waveforms, such as sinusoids.”
BackgroundWhat are we talking about? Modes of neuronal communication
Katz, P. S. (1999) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780198524243.003.0001 · Cited by 24 · cited 1×
“This effect is mediated by special neurotransmitters called neuromodulators [39].”
BackgroundReal-Time Learning in the NERO Video Game
Stanley, K. O., Cornelius, R., Miikkulainen, R. P., D’Silva, T., & Gold, A. (2005) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v1i1.18736 · Cited by 22 · cited 1×
“Neuro-evolution of augmenting topologies (NEAT) has been applied to many problems such as pole balancing [79], robot control [80], computer games [66, 82 ]o r an automobile crash warning system [81].”
MethodFrom Solitary to Collective Behaviours: Decision Making and Cooperation
Trianni, V., Ampatzis, C., Christensen, A. L., Tuci, E., Dorigo, M., & Nolfi, S. (2007) · Springer eBooks · doi:10.1007/978-3-540-74913-4_58 · Cited by 21 · cited 1×
“Evolved neural networks with direct encoding have also been applied to a variety of other problems such as game playing [13], data classification [12] or the control of robot swarms [85].”
BackgroundEvolution of analog networks using local string alignment on highly reorganizable genomes
Mattiussi, C., & Floreano, D. (2004) · NASA/DoD Conference on Evolvable Hardware · doi:10.1109/eh.2004.1310806 · Cited by 20 · cited 8×
“Saggie et al. [70] compared spiking neural networks with conventional static ANNs in a simple setup where an agent had to search food and avoid poison in a simulated grid world.”
MethodInfluentialSelf-citationer, & Gomi, T. (2001) · Lecture notes in computer science · doi:10.1007/3-540-45502-7 · Cited by 18
Mattiussi, C., Marbach, D., Dürr, P., & Floreano, D. (2008) · AI Magazine · doi:10.1609/aimag.v29i3.2156 · Cited by 17
Self-citationTotally model-free reinforcement learning by actor-critic Elman networks in non-Markovian domains
Mizutani, E., & Dreyfus, S. E. (2002) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.1998.687169 · Cited by 13 · cited 1×
“Redrawn from Mizutani and Dreyfus [49] mod”
Mattiussi, C., Dürr, P., & Floreano, D. (2007) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/1276958.1277205 · Cited by 10 · cited 1×
“[45], where the characters of the string are interpreted as a system of particles whose center of mass determines the encoded value.”
BackgroundSelf-citationStructure and dynamics of a gene network model incorporating small RNAs
Geard, N. L., & Wiles, J. (2003) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2003.1299575 · Cited by 10 · cited 1×
“Geard and Wiles [25] refined this model by complexifying the map that transforms a gene into a regulator protein, adding a further level of regulation which mimics the action of small RNA regulation in real genomes and defining regulation in terms of a weighted sum of regulator proteins effects.”
BackgroundGasNets and CTRNNs – A Comparison in Terms of Evolvability
Magg, S., & Philippides, A. O. (2006) · Lecture notes in computer science · doi:10.1007/11840541_38 · Cited by 8 · cited 1×
“This is in line with Magg and Philippides [43] whose results indicate that GasNets perform extremely well on tasks that require some kind of neural pattern generator or timer, while performing worse on tasks which do not require different time scales in the network.”
ResultArtificial genomes as models of gene regulation
Reil, T. (2003) · Elsevier eBooks · doi:10.1016/b978-012428765-5/50047-5 · Cited by 6
Spikes that count: rethinking spikiness in neurally embedded systems
Saggie, K., Keinan, A., & Ruppin, E. (2004) · Neurocomputing · doi:10.1016/j.neucom.2004.01.060 · Cited by 5 · cited 1×
“[70] compared spiking neural networks with conventional static ANNs in a simple setup where an agent had to search food and avoid poison in a simulated grid world.”
BackgroundGunderson, K. (1981) · Behavioral and Brain Sciences · doi:10.1017/s0140525x00000078 · Cited by 3
Research works printed but not linked: 9
- Ackley DH, Littman ML (1992) Interactions between learning and evolution. In: Langton C, Farmer J, Rasmussen S, Taylor C (eds) Artificial Life II: Proceedings volume of Santa Fe conference, vol XI. Addison Wesley, Redwood City, pp 487–510
- Belew RK, McInerney J, Schraudolph NN (1992) Evolving networks: using the genetic algorithm with connectionistic learning. In: Langton CG, Taylor C, Farmer JD, Rasmussen S (eds) Proceedings of the 2nd Conference on Artificial Life. Addison-Wesley, Reading, pp 511–548
- Dasdan A, Oflazer K (1993) Genetic synthesis of unsupervised learning algorithms. In: Proceedings of the 2nd Turkish symposium on artificial intelligence and ANNs. Department of Computer Engineering and Information Science, Bilkent University, Ankara
- Hebb DO (1949) The organisation of behavior. Wiley, New York
- Kitano H (1990) Designing neural networks by genetic algorithms using graph generation system. Complex Syst J 4:461–476
- Purves D (1994) Neural activity in the growth of the brain. Cambridge University Press, Cambridge
- Radcliffe NJ (1991) Form an analysis and random respectful recombination. In: Belew RK, Booker LB (eds) Proceedings of the 4th international conference on genetic algorithms. Morgan Kaufmann, San Mateo
- Sasaki T, Tokoro M (1997) Adaptation toward changing environments: Why Darwinian in nature?. In: Husbands P, Harvey I (eds) Proceedings of the 4th European conference on artificial life. MIT Press, Cambridge
- Sutton RS (1988) Learning to predict by the method of temporal difference. Machine Learn 3:9–44
Cited by
Learning Transferable Architectures for Scalable Image Recognition
Zoph, B., Vasudevan, V., Shlens, J., & Le, Q. V. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00907 · Cited by 6,249
A Survey of Autonomous Driving: Common Practices and Emerging Technologies
Yurtsever, E., Lambert, J., Carballo, A., & Takeda, K. (2020) · IEEE Access · doi:10.1109/access.2020.2983149 · Cited by 1,889
“Neuroevolution refers to using evolutionary algorithms to train artificial neural networks [70].”
BackgroundNeural Architecture Search: A Survey
Elsken, T., Metzen, J. H., & Hutter, F. (2018) · arXiv · doi:10.48550/arxiv.1808.05377 · Cited by 1,763
Automated Machine Learning: Methods, Systems, Challenges
(2019) · The Springer Series on Challenges in Machine Learning · doi:10.1007/978-3-030-05318-5 · Cited by 1,485
Miikkulainen, R., Liang, J., Meyerson, E., Rawal, A., Fink, D., Francon, O., Raju, B., Shahrzad, H., Navruzyan, A., Duffy, N., et al. (2019) · Artificial Intelligence in the Age of Neural Networks and Brain Computing · doi:10.1016/b978-0-12-815480-9.00015-3 · Cited by 760
Metadata
- Authors
- Floreano, D., Dürr, P., & Mattiussi, C.
- Affiliations
- École Polytechnique Fédérale de Lausanne (CH)
- Corresponding author
- Dürr, Peter
- Venue
- Evolutionary Intelligence
- Published
- 2008-01-10
- Volume
- 1
- Issue
- 1
- Pages
- 47-62
- ISSN
- 1864-5909 (ISSN-L)
- 1864-5917
- OpenAlex
- W2171658832
- Cited by
- 734
- References
- 101
- Citations by year
- 2026: 17 · 2025: 22 · 2024: 25 · 2023: 37 · 2022: 42 · 2021: 58 · 2020: 81 · 2019: 58 · 2018: 45 · 2017: 46 · 2016: 30 · 2015: 35 · 2014: 82 · 2013: 38 · 2012: 36
- FWCI
- 42.81
- Type
- journal article
- Language
- en
- Open access
- green
- infoscience.epfl.ch
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Evolutionary Intelligence (publishedVersion)
- reroDoc Digital Library (submittedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion, cc-by-nc-nd)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Evolutionary Algorithms and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Metaheuristic Optimization Algorithms Research
- Keywords
- neuroevolution, artificial neural networks, neural network architecture, learning algorithms, evolutionary search, neuron models, automatic neural network design
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.