Abstract
Most artificial neural networks have nodes that apply a simple static transfer function, such as a sigmoid or gaussian, to their accumulated inputs. This contrasts with biological neurons, whose transfer functions are dynamic and driven by a rich internal structure. Our artificial neural network approach, which we call state-enhanced neural networks, uses nodes with dynamic transfer functions based on n-dimensional real-valued internal state. This internal state provides the nodes with memory of past inputs and computations. The state update rules, which determine the internal dynamics of a node, are optimized by an evolutionary algorithm to fit a particular task and environment. We demonstrate the effectiveness of the approach in comparison to certain types of recurrent neural networks using a suite of partially observable Markov decision processes as test problems. These problems involve both sequence detection and simulated mice in mazes, and include four advanced benchmarks proposed by other researchers.
Similar content being viewed by others
References
Aberdeen D (2003) A (revised) survey of approximate methods for solving partially observable markov decision processes. Technical report, National ICT Australia, Canberra
Abraham A (2004) Meta learning evolutionary artificial neural networks. Neurocomputing 56:1–38
Aihara K, Takabe T, Toyoda M (1990) Chaotic neural networks. Phys Lett A 144(6):333–340
Astor J, Adami C (2000) A developmental model for the evolution of artificial neural networks. Artif Life 6(3):189–218
Asuncion A, Newman D (2007) UCI machine learning repository. http://www.ics.uci.edu/∼mlearn/MLRepository.html
Bakker B, Zhumatiy V, Gruener G, Schmidhuber J (2003) A robot that reinforcement-learns to identify and memorize important previous observations. In: Proceedings of the IEEE/RSJ international conference on intelligent robots and systems (IROS2003), pp 430–435
Baxter J (1992) The evolution of learning algorithms for artificial neural networks. In: Green D, Bossomaier T (eds) Complex systems. IOS Press, Amsterdam
Blynel J, Floreano D (2003) Exploring the t-maze: evolving learning-like robot behaviors using ctrnns. In: Proceedings of the second European workshop on evolutionary robotics, pp 593–604
Bongard J (2002) Evolving modular genetic regulatory networks. In: Proceedings of the 2002 congress on evolutionary computation, pp 1872–1877
Cangelosi A, Parisi D, Nolfi S (1994) Cell division and migration in a ’genotype’ for neural networks. Network 5:497–515
Chalmers D (1990) The evolution of learning: an experiment in genetic connectionism. In: Proceedings of the 1990 Connectionist Models Summer School, pp 81–90
Dellaert F, Beer R (1996) A developmental model for the evolution of complete autonomous agents. In: Proceedings of the fourth international conference on simulation of adaptive behavior, pp 393–401
D’Silva TRJ, Chrien M, Stanley K, Miikkulainen R (2005). Retaining learned behavior during real-time neuroevolution. In: Proceedings of the artificial intelligence and interactive digital entertainment conference (AIIDE)
Eggenberger-Hotz P, Gomez G, Pfeifer R (2002) Evolving the morphology of a neural network for controlling a foveating retina and its test on a real robot. In: Proceedings of the eighth international workshop on the synthesis and simulation of living systems (Artificial Life VIII), pp 243–251
Floreano D, Durr P, Mattiussi C (2008) Neuroevolution: from architectures to learning. Evol Intell 1(1):47–62
Floreano D, Mattiussi C (2001) Evolution of spiking neural controllers for autonomous vision-based robots. In: Gomi T (ed) Evolutionary robotics: from intelligent robotics to artificial life. Springer, Tokyo
Funahashi K, Nakamura Y (1993) Approximation of dynamical systems by continuous time recurrent neural networks. Neural Netw 6(6):801–806
Gers F, Schmidhuber J (2001) Lstm recurrent networks learn simple context free and context sensitive languages. IEEE Trans Neural Netw 12(6):1333–1340
Gerstner W, Kistler W (2002) Spiking neuron models: single neurons, populations, plasticity. Cambridge University Press, Cambridge
Gomez F, Miikkulainen R (1999) Solving non-markovian control tasks with neuroevolution. In: Proceedings of the international joint conference on artificial intelligence, pp 1356–1361
Gomez F, Schmidhuber J (2005) Co-evolving recurrent neurons learn deep memory POMDPs. In: Proceedings of the genetic and evolutionary computation conference (GECCO)
Gruau F (1995) Automatic definition of modular neural networks. Adapt Behav 3(2):151–183
Harp S, Samad T, Guha A (1989) Towards the genetic synthesis of neural networks. In: Proceedings of the third international conference on genetic algorithms, pp 360–369
Haykin S (1999) Neural networks: a comprehensive foundation. Prentice-Hall, Englewood Cliffs
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Hussain T (2004) Generic neural markup language: facilitating the design of theoretical neural network models. In: Proceedings of the IEEE international joint conference on neural networks, pp 235–242
Ichinose N, Aihara K, Kotani M (1993) An analysis on dynamics of pulse propagation networks. In: Proceedings of the international joint conference on neural networks, pp 2315–2318
Izhikevich E (2004) Which model to use for cortical spiking neurons?. IEEE Trans Neural Netw 15(5):1063–1070
Jakobi N (1995) Harnessing morphogenesis. In: International conference on information processing in cells and tissues, pp 29–41
Jakobi N (1998) Evolutionary robotics and the radical envelope-of-noise hypothesis. Adapt Behav 6(2):325–368
Kitano H (1990) Designing neural networks using genetic algorithms with graph generation system. Complex Syst 4:461–476
Kumar S, Bentley P (2003) Computational embryology: past, present and future. Springer, New York, pp 461–477
Luke S (2002) An evolutionary computation and genetic programming system. http://cs.gmu.edu/eclab/projects/ecj/docs/
McCallum A (1993) Overcoming incomplete perception with utile distinction memory. In: International conference on machine learning, pp 190–196
Montana D, Davis L (1989) Training feedforward neural networks using genetic algorithms. In: Proceedings of the international joint conference on artificial intelligence (IJCAI), pp 762–767
Montana D, VanWyk E, Brinn M, Montana J, Milligan S (2006) Genomic computing networks learn complex POMDPs. In: Proceedings of the genetic and evolutionary computation conference (GECCO), pp 233–234
Nolfi S, Miglino O, Parisi D (1994) Phenotypic plasticity in evolving neural networks. In: Proceedings of the internation conference from perception to action, pp 146–157
Osana Y, Hattori M, Hagiwara M (1996) Chaotic bidirectional associative memory. In: IEEE international conference on neural networks, pp 816–821
Pearlmutter B (1995) Gradient calculation for dynamic recurrent neural networks: a survey. IEEE Trans Neural Netw 6(5):1212–1228
Pollack M, Ringuette M (1990) Introducing the Tileworld: experimentally evaluating agent architectures. In: Proceedings of the eighth national conference on artificial intelligence, pp 183–189
Russel S, Norvig P (1995) Artificial intelligence: a modern approach. Prentice-Hall, Englewood Cliffs
Schmidhuber J, Wierstra D, Galiolo M, Gomez F (2007) Training recurrent networks by evolino. Neural Comput 19(3):757–779
Schmidhuber J, Wierstra D, Gomez F (2005) Evolino: hybrid neuroevolution/optimal linear search for sequence learning. In: Proceedings of the 19th international joint conference on artificial intelligence (IJCAI), pp 853–858
Stanley K, Miikkulainen R (2002) Evolving neural networks through augmenting topologies. Evol Comput 10(2):99–127
Stanley K, Miikkulainen R (2003) A taxonomy for artificial embryogeny. Artif Life 9(2):93–130
Watkins C, Dayan P (1992) Q-learning. Mach Learn 8(3):279–292
Whitley D (1989) Applying genetic algorithms to neural network learning. In: Proceedings of the seventh conference of the society of artificial intelligence and simulation of behavior, pp 137–144
Yamauchi B, Beer R (1994) Sequential behavior and learning in evolved dynamical neural networks. Adapt Behav 2(3):219–246
Yao X (1999) Evolving artificial neural networks. Proc IEEE 87(9):1423–1447
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Montana, D., VanWyk, E., Brinn, M. et al. Evolution of internal dynamics for neural network nodes. Evol. Intel. 1, 233–251 (2009). https://doi.org/10.1007/s12065-009-0017-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12065-009-0017-0