Artificial Neuron–Glia Networks Learning Approach Based on Cooperative Coevolution

Abstract

Artificial Neuron-Glia Networks (ANGNs) are a novel bio-inspired machine learning approach. They extend classical Artificial Neural Networks (ANNs) by incorporating recent findings and suppositions about the way information is processed by neural and astrocytic networks in the most evolved living organisms. Although ANGNs are not a consolidated method, their performance against the traditional approach, i.e. without artificial astrocytes, was already demonstrated on classification problems. However, the corresponding learning algorithms developed so far strongly depends on a set of glial parameters which are manually tuned for each specific problem. As a consequence, previous experimental tests have to be done in order to determine an adequate set of values, making such manual parameter configuration time-consuming, error-prone, biased and problem dependent. Thus, in this article, we propose a novel learning approach for ANGNs that fully automates the learning process, and gives the possibility of testing any kind of reasonable parameter configuration for each specific problem. This new learning algorithm, based on coevolutionary genetic algorithms, is able to properly learn all the ANGNs parameters. Its performance is tested on 5 classification problems achieving significantly better results than ANGN and competitive results with ANN approaches.

Deep Artificial Neural Networks and Neuromorphic Chips for Big Data Analysis: Pharmaceutical and Bioinformatics Applications

“…Moreover, the RNASA-IMEDIR group from the University of A Coruña developed an Artificial Neuron-Glia Network (ANGN) incorporating two different types of processing elements: artificial neurons and artificial astrocytes. This extends classical ANN by incorporating recent findings and suppositions regarding the way information is processed via neural and astrocytic networks in the most evolved living organisms [145,146,147,148,149]. In our opinion, neurons are specialized in transmission and information processing, whereas glial cells in processing and modulation.…”

Meta‐heuristic multi‐ and many‐objective optimization techniques for solution of machine learning problems

“…The mean square error and the number of hidden nodes of the network were optimized using the branch‐and‐bound algorithm. Garcia‐Pedrajas, Hervas‐Martinez, and Muñoz‐Perez () presented a cooperative coevolutive model (Mesejo, Ibanez Enrique Fernandez‐Blanco, Cedron, Pazos, & Porto‐Pazos, ) to handle MOP. The algorithm is an adaptation of NSGA to evolutionary programming, where the main idea is to evolve a population of subnetworks or modules and a population of networks concurrently.…”

Physics‐based search and optimization: Inspirations from nature

“…where x i ( t ) represents a candidate solution at iteration t , f i is the fitness function value of x i ( t ), and N is the population size. This operator is different from selection operator used in many other optimization algorithms such as genetic algorithms (GA); (Lee, & Arditi, ; Paris, Pedrino, & Nicoletti, ; Bolourchi, Masri, & Aldraihem, ; Park, Oh, & Park, ), genetic programming (Rashidi & Ranjitkar, ; Mesejo et al, ), or particle swarm optimization (PSO) (Zeng, Xu, Wu, & Shen, ; Shabbir & Omenzetter, ).…”