Neural Processing of Counting in Evolved Spiking and McCulloch-Pitts Agents

This article investigates the evolution of autonomous agents that perform a memory-dependent counting task. Two types of neurocontrollers are evolved: networks of McCulloch-Pitts neurons, and spiking integrate-and-fire networks. The results demonstrate the superiority of the spiky model in evolutionary success and network simplicity. The combination of spiking dynamics with incremental evolution leads to the successful evolution of agents counting over very long periods. Analysis of the evolved networks unravels the counting mechanism and demonstrates how the spiking dynamics are utilized. Using new measures of spikiness we find that even in agents with spiking dynamics, these are usually truly utilized only when they are really needed, that is, in the evolved subnetwork responsible for counting.

[1]  Wolfgang Maass,et al.  Networks of Spiking Neurons: The Third Generation of Neural Network Models , 1996, Electron. Colloquium Comput. Complex..

[2]  J G Fetterman,et al.  Numerosity discrimination: both time and number matter. , 1993, Journal of experimental psychology. Animal behavior processes.

[3]  E. Ruppin.  Evolutionary autonomous agents: A neuroscience perspective , 2002, Nature Reviews Neuroscience.

[4]  Ezequiel A. Di Paolo,et al.  Spike-Timing Dependent Plasticity for Evolved Robots , 2002, Adapt. Behav..

[5]  J. Deese.  The psychology of learning , 1952 .

[6]  Nick Jakobi,et al.  Evolutionary Robotics and the Radical Envelope-of-Noise Hypothesis , 1997, Adapt. Behav..

[7]  Isaac Meilijson,et al.  Localization of Function via Lesion Analysis , 2003, Neural Computation.

[8]  Wolfgang Maass,et al.  On Computation with Pulses , 2000, Electron. Colloquium Comput. Complex..

[9]  G Bugmann,et al.  Biologically plausible neural computation. , 1997, Bio Systems.

[10]  J. M. Bilbao,et al.  Contributions to the Theory of Games , 2005 .

[11]  Francesco Mondada,et al.  Evolution of homing navigation in a real mobile robot , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[12]  John R. Platt,et al.  Localization of position within a homogeneous behavior chain: Effects of error contingencies , 1971 .

[13]  Isaac Meilijson,et al.  Fair Attribution of Functional Contribution in Artificial and Biological Networks , 2004, Neural Computation.

[14]  Fetterman Jg,et al.  Numerosity discrimination: both time and number matter , 1993 .

[15]  Dario Floreano,et al.  Evolution of Spiking Neural Controllers for Autonomous Vision-Based Robots , 2001, EvoRobots.

[16]  Wofgang Maas,et al.  Networks of spiking neurons: the third generation of neural network models , 1997 .

[17]  Pattie Maes,et al.  Toward the Evolution of Dynamical Neural Networks for Minimally Cognitive Behavior , 1996 .

[18]  Dario Floreano,et al.  Active vision and feature selection in evolutionary behavioral systems , 2002 .

[19]  Yasuo Kuniyoshi,et al.  Embedded neural networks: exploiting constraints , 1998, Neural Networks.

[20]  Inman Harvey,et al.  Using a net to catch a mate: evolving CTRNNs for the dowry problem , 2002 .

[21]  L. Shapley.  A Value for n-person Games , 1988 .

[22]  Phil Husbands,et al.  Analyzing Evolved Fault-Tolerant Neurocontrollers , 2004 .

[23]  Risto Miikkulainen,et al.  Incremental Evolution of Complex General Behavior , 1997, Adapt. Behav..

[24]  Randall D. Beer,et al.  On the Dynamics of Small Continuous-Time Recurrent Neural Networks , 1995, Adapt. Behav..

[25]  Isaac Meilijson,et al.  Axiomatic Scalable Neurocontroller Analysis via the Shapley Value , 2006, Artificial Life.

[26]  Eytan Ruppin,et al.  Emergence of Memory-Driven Command Neurons in Evolved Artificial Agents , 2001, Neural Computation.