Supervised Learning Algorithm for Multilayer Spiking Neural Networks with Long-Term Memory Spike Response Model

As a new brain-inspired computational model of artificial neural networks, spiking neural networks transmit and process information via precisely timed spike trains. Constructing efficient learning methods is a significant research field in spiking neural networks. In this paper, we present a supervised learning algorithm for multilayer feedforward spiking neural networks; all neurons can fire multiple spikes in all layers. The feedforward network consists of spiking neurons governed by biologically plausible long-term memory spike response model, in which the effect of earlier spikes on the refractoriness is not neglected to incorporate adaptation effects. The gradient descent method is employed to derive synaptic weight updating rule for learning spike trains. The proposed algorithm is tested and verified on spatiotemporal pattern learning problems, including a set of spike train learning tasks and nonlinear pattern classification problems on four UCI datasets. Simulation results indicate that the proposed algorithm can improve learning accuracy in comparison with other supervised learning algorithms.

Smartphone Sensor Accelerometer Data for Human Activity Recognition Using Spiking Neural Network

Recognizing human actions is a challenging task and actively research in computer vision community. The task of human activity recognition has been widely used in various application such as human monitoring in a hospital or public spaces. This work applied open dataset of smartphones accelerometer data for various type of activities. The analogue input data is encoded into the spike trains using some form of a rate-based method. Spiking neural network is a simplified form of dynamic artificial network. Therefore, this network is expected to model and generate action potential from the leaky integrate-and-fire spike response model. The leaning rule is adaptive and efficient to present synapse exciting and inhibiting firing neuron. The result found that the proposed model presents the state-of-the-art performance at a low computational cost.

Minimal Spiking Neuron for Solving Multilabel Classification Tasks

The multispike tempotron (MST) is a powersul, single spiking neuron model that can solve complex supervised classification tasks. It is also internally complex, computationally expensive to evaluate, and unsuitable for neuromorphic hardware. Here we aim to understand whether it is possible to simplify the MST model while retaining its ability to learn and process information. To this end, we introduce a family of generalized neuron models (GNMs) that are a special case of the spike response model and much simpler and cheaper to simulate than the MST. We find that over a wide range of parameters, the GNM can learn at least as well as the MST does. We identify the temporal autocorrelation of the membrane potential as the most important ingredient of the GNM that enables it to classify multiple spatiotemporal patterns. We also interpret the GNM as a chemical system, thus conceptually bridging computation by neural networks with molecular information processing. We conclude the letter by proposing alternative training approaches for the GNM, including error trace learning and error backpropagation.

Design a Different Structures Controller for Controlled Systems Using a Spiking Neural Network

The design and simulation of the Spiking Neural Network (SNN) are proposed in this paper to control a plant without and with load. The proposed controller is performed using Spike Response Model. SNNs are more powerful than conventional artificial neural networks since they use fewer nodes to solve the same problem. The proposed controller is implemented using SNN to work with different structures as P, PI, PD or PID like to control linear and nonlinear models. This controller is designed in discrete form and has three inputs (error, integral of error and derivative of error) and has one output. The type of controller, number of hidden nodes, and number of synapses are set using external inputs. Sampling time is set according to the controlled model. Social-Spider Optimization algorithm is applied for learning the weights of the SNN layers. The proposed controller is tested with different linear and nonlinear models and different reference signals. Simulation results proved the efficiency of the suggested controller to reach accurate responses with minimum Mean Squared Error, small structure and minimum number of epochs under no load and load conditions.

Reinforcement Learning Through Modulation of Spike-Timing-Dependent Synaptic Plasticity

The persistent modification of synaptic efficacy as a function of the relative timing of pre- and postsynaptic spikes is a phenomenon known as spike-timing-dependent plasticity (STDP). Here we show that the modulation of STDP by a global reward signal leads to reinforcement learning. We first derive analytically learning rules involving reward-modulated spike-timing-dependent synaptic and intrinsic plasticity, by applying a reinforcement learning algorithm to the stochastic spike response model of spiking neurons. These rules have several features common to plasticity mechanisms experimentally found in the brain. We then demonstrate in simulations of networks of integrate-and-fire neurons the efficacy of two simple learning rules involving modulated STDP. One rule is a direct extension of the standard STDP model (modulated STDP), and the other one involves an eligibility trace stored at each synapse that keeps a decaying memory of the relationships between the recent pairs of pre- and postsynaptic spike pairs (modulated STDP with eligibility trace). This latter rule permits learning even if the reward signal is delayed. The proposed rules are able to solve the XOR problem with both rate coded and temporally coded input and to learn a target output firing-rate pattern. These learning rules are biologically plausible, may be used for training generic artificial spiking neural networks, regardless of the neural model used, and suggest the experimental investigation in animals of the existence of reward-modulated STDP.