Optimizing the Neural Structure and Hyperparameters of Liquid State Machines Based on Evolutionary Membrane Algorithm

Abstract

As one of the important artificial intelligence fields, brain-like computing attempts to give machines a higher intelligence level by studying and simulating the cognitive principles of the human brain. A spiking neural network (SNN) is one of the research directions of brain-like computing, characterized by better biogenesis and stronger computing power than the traditional neural network. A liquid state machine (LSM) is a neural computing model with a recurrent network structure based on SNN. In this paper, a learning algorithm based on an evolutionary membrane algorithm is proposed to optimize the neural structure and hyperparameters of an LSM. First, the object of the proposed algorithm is designed according to the neural structure and hyperparameters of the LSM. Second, the reaction rules of the proposed algorithm are employed to discover the best neural structure and hyperparameters of the LSM. Third, the membrane structure is that the skin membrane contains several elementary membranes to speed up the search of the proposed algorithm. In the simulation experiment, effectiveness verification is carried out on the MNIST and KTH datasets. In terms of the MNIST datasets, the best test results of the proposed algorithm with 500, 1000 and 2000 spiking neurons are 86.8%, 90.6% and 90.8%, respectively. The best test results of the proposed algorithm on KTH with 500, 1000 and 2000 spiking neurons are 82.9%, 85.3% and 86.3%, respectively. The simulation results show that the proposed algorithm has a more competitive advantage than other experimental algorithms.

Time-Multiplexed Photonic Reservoir Computer for Recognition of Human Actions in Videos

“…With 600 nodes we report a classification accuracy of 90.83%. This is comparable to state-of-the-art algorithms that achieve accuracies that go from 86% to 98%, for network sizes going from thousands [8] to hundreds of millions [9] of neurons, implemented on noiseless digital processors. Our system is also particularly fast, with processing speeds exceeding the typical video frame rate of 25 fps by a factor of 6.…”

Design and Development of an Imitation Detection System for Human Action Recognition Using Deep Learning

“…Finally, Liu et al [ 45 ] introduced a learning algorithm that utilizes an evolutionary membrane algorithm to optimize the neural structure and hyperparameters of a liquid-state machine. To verify its effectiveness, the algorithm was tested on the MNIST and KTH datasets through simulation experiments.…”

A Method for Predicting the Academic Performances of College Students Based on Education System Data

“…Compared with other first-generation and second-generation artificial neural networks, the third-generation spiking neural network can simulate almost all functions more efficiently by using fewer neuron models and structures, and its computing power and efficiency are significantly improved. Although the spiking neural network model has not been developed for a long time, it has shown good learning ability in many fields, including biological signal processing [28], robot control [29], image recognition [30], etc. All of these applications show that the spiking neural network has great practical significance and is worthy of in-depth study.…”