Artificial Neural Development for Pulsed Neural Network Design

The purchase and pricing options for this item are unavailable. Select items are only available as part of a subscription package. You may try again later or contact us for more information.
4 Author(s)

We propose the artificial neural development method that generates the three-dimensional multi-regional pulsed neural network arranged in three layers of the nerve area layer, the nerve sub-area layer, and the cell layer. In this method, the neural development process consists of the lirst genomecontrolled spatiotemporal generation of a neural network structure and the latter activity-dependent regulation of it. In the first process, by decoding a genome, 1)a nerve sub-arca is generated in each nerve area and neurons are produced in it, 2)axonal outgrowth target sub-areas are recognized according to the attraction and repulsion rule, and 3)synapse formation is controlled under the topology preservation projection rule between origin cells and target cells. In the latter process, 4)programmed cell death occurs under control of spiking activity and a neurotrophic factor, then 5)synaptic efficacy is regulated according to the spike-based hebbian rule and weakened synapses are eliminated as a result of competition of spiking activity. For design of genomes, the steady state genetic algorithm is introduced and it is applied to initial genomes partially designed manually. To evaluate our artificial neural development method, simulation experiments are conducted to generate a pulsed neural network of an animal-like robot (animat) which moves in an environment. We evolve and develop an animat's place recognition circuit that contains the place cell area The place recognition performance is evaluated in an environment where an animat comes into existence and in another environment where the animat enters after development. Through these experiments, we show our artificial neural development method is useful for generating a biologically realistic pulsed neural network of the animat