Compartmental spiking neuron model for pattern classification

One of the directions of development within the framework of the neuromorphic approach is the development of anatomically similar models of brain networks, taking into account the structurally complex structure of neurons and the adaptation of connections between them, as well as the development of learning algorithms for such models. In this work, we use the previously presented compartmental spike model of a neuron, which describes the structure (dendritic tree, soma, synapses) and behaviour (temporal and spatial signal summation, generation of action potential, stimulation and suppression of electrical activity) of a biological neuron. An algorithm for the structural organization of neuron models into a spike neural network is proposed for recognizing an arbitrary impulse pattern by introducing inhibitory synapses between trained neuron models. The dynamically adapting neuron models used are trained according to a previously proposed algorithm that automatically selects parameters such as soma size, dendrite length, and the number of synapses on each of the dendrites in order to induce a temporal response at the output depending on the input pattern encoded using a time window and temporal delays in the vector of single spikes arriving at a separate dendrite of a neuron. The developed algorithms are evaluated on the Iris dataset classification problem with four training examples from each class. As a result of the classification, separate disjoint clusters are formed, which demonstrates the applicability of the proposed spike neural network with a dynamically changing structure of elements in the problem of pattern recognition and classification.

Spike neural network as a controller in SDN network

The paper proposes a methodology for predicting packet flow at the data plane in smart SDN based on the intelligent controller of spike neural networks(SNN). This methodology is applied to predict the subsequent step of the packet flow, consequently reducing the overcrowding that might happen. The centralized controller acts as a reactive controller for managing the clustering head process in the Software Defined Network data layer in the proposed model. The simulation results show the capability of Spike Neural Network controller in SDN control layer to improve the (QoS) in the whole network in terms of minimizing the packet loss ratio and increased the buffer utilization ratio.

Spiking Neural Network (SNN) With Memristor Synapses Having Non-linear Weight Update

Among many artificial neural networks, the research on Spike Neural Network (SNN), which mimics the energy-efficient signal system in the brain, is drawing much attention. Memristor is a promising candidate as a synaptic component for hardware implementation of SNN, but several non-ideal device properties are making it challengeable. In this work, we conducted an SNN simulation by adding a device model with a non-linear weight update to test the impact on SNN performance. We found that SNN has a strong tolerance for the device non-linearity and the network can keep the accuracy high if a device meets one of the two conditions: 1. symmetric LTP and LTD curves and 2. positive non-linearity factors for both LTP and LTD. The reason was analyzed in terms of the balance between network parameters as well as the variability of weight. The results are considered to be a piece of useful prior information for the future implementation of emerging device-based neuromorphic hardware.

Convolutional Multi-Spike Neural Network as Intelligent System Prediction for Control Systems

The evolution in the field of Artificial Intelligent (AI) with its training algorithms make AI very important in different aspect of the life. The prediction problem of behavior of dynamical control system is one of the most important issue that the AI can be employed to solve it. In this paper, a Convolutional Multi-Spike Neural Network (CMSNN) is proposed as smart system to predict the response of nonlinear dynamical systems. The proposed structure mixed the advantages of Convolutional Neural Network (CNN) with Multi -Spike Neural Network (MSNN) to generate the smart structure. The CMSNN has the capability of training weights based on a proposed training algorithm. The simulation results demonstrated that the proposed structure has the ability to predict the response of dynamical systems more powerful than with the CNN. The proposed structure is more powerful than the CNN by 28.33% in terms of minimizing the root mean square error.

ПРОГРАММНЫЕ И АППАРАТНЫЕ РЕАЛИЗАЦИИ ОСНОВНЫХ КОМПОНЕНТ СПАЙКОВЫХ И ФОРМАЛЬНЫХ НЕЙРОННЫХ СЕТЕЙ

Разработаны Verilog-A-модели тормозного и возбуждающего нейронов с бипрямоугольной и битреугольной формами импульсов (спайков) и мемристивными синаптическими весами. Показана возможность сходимости весов в численном моделировании обучения по Хеббу нейрона на основе локальных правил модификации весов. Предложена схема нейросинаптического ядра для аппаратной реализации формальных и спайковых нейронных сетей на их основе. The paper presents Verilog-A models of excitatory and inhibitory neurons with birectangular and bitriangular shapes of spikes. Besides, it highlights the possibility of convergence of weights in the numerical simulation of a neuron Hebbian learning based on local weight updates rules, as well as offers schemes for the neurosynaptic core for the hardware implementation of formal and spike neural network algorithms.