A Collective Intelligence Based Differential Evolution Algorithm for Optimizing the Structure and Parameters of a Neural Network

Abstract

In this paper, a Self-learning Collective Intelligence Differential Evolution (SLCIDE) algorithm was proposed to optimize both the architecture and parameters of a Feedforward Neural Network (FNN). In order to improve the exploration-exploitation capability, a new Collective Intelligence (CI) based mutation operator was proposed by mixing some promising donor vectors in the current population. Besides, a self-learning mechanism which was designed to adaptively select m top ranked donor vectors was developed by using a widely used unsupervised learning method, k-means. As a result, the proposed approach can be more adaptive and statistically powerful on versatile problems. Then, we evaluated the performances of the proposed SLCIDE approach by studying some numerical optimization problems of CEC 2013 with D = 30 and D = 50. Further, the proposed SLCIDE method was applied to train a FNN on four most popular datasets, resulting in very competitive performances. The comprehensive experimental results have demonstrated that the presented SLCIDE method obtain better results compared with other state-of-the-art algorithms. INDEX TERMS Evolutionary artificial neural network, global optimization, collective intelligence (CI), differential evolution (DE).

Convergence Track Based Adaptive Differential Evolution Algorithm (CTbADE)

“…This research measured the convergence speed and accuracy, using three different mutation strategies and control parameters to adapt the dynamic rate of exploitation and exploration. To optimize the structure and parameters of neural networks, a collective intelligent based DE algorithm is presented in [44]. In this work mutation parameters based on collective intelligence were used to enhance the exploitation and the exploration capability of DE algorithms by utilizing promising donor vectors by taking m top ranked donor vectors.…”

Many-Objective Quantum-Inspired Particle Swarm Optimization Algorithm for Placement of Virtual Machines in Smart Computing Cloud

“…Intelligent virtual machines contain some pre-trained domain models based mainly on convolutional neural network (CNN) and long short term memory (LSTM) ANNs [ 24 , 25 ]. Several virtual machines can run on a host, but they can migrate from the source computer to the destination regarding the Pareto-optimal solution obtained by the MQPSO.…”