Unsupervised Spiking Neural Network with Dynamic Learning of Inhibitory Neurons.

A spiking neural network (SNN) is a type of artificial neural network that operates based on discrete spikes to process timing information, similar to the manner in which the human brain processes real-world problems. In this paper, we propose a new spiking neural network (SNN) based on conventional, biologically plausible paradigms, such as the leaky integrate-and-fire model, spike timing-dependent plasticity, and the adaptive spiking threshold, by suggesting new biological models; that is, dynamic inhibition weight change, a synaptic wiring method, and Bayesian inference. The proposed network is designed for image recognition tasks, which are frequently used to evaluate the performance of conventional deep neural networks. To manifest the bio-realistic neural architecture, the learning is unsupervised, and the inhibition weight is dynamically changed; this, in turn, affects the synaptic wiring method based on Hebbian learning and the neuronal population. In the inference phase, Bayesian inference successfully classifies the input digits by counting the spikes from the responding neurons. The experimental results demonstrate that the proposed biological model ensures a performance improvement compared with other biologically plausible SNN models.

Evolution of developmental canalization in networks of competing boolean nodes.

Developmental canalization, which leads to a reduction in the variation of phenotype expression relative to the complexity of the genome, has long been thought to be an important property of evolving biological systems. We demonstrate that a highly canalized state develops in the process of self-organization recently discovered in N-K Boolean networks that evolve based on a competition between the nodes. The model provides a simplified description of the evolution of genetic regulatory networks in developmental systems. The mechanism responsible for the evolution is shown to be a balance of two dynamical effects which compete to bring the network to a nonrandom critical steady state. Unlike other proposed evolutionary mechanisms that select for canalization, this mechanism does so while maintaining the system's capacity for further evolution in the steady state.