A Comparative Analysis of Simplification and Complexification in the Evolution of Neural Network Topologies
نویسندگان
چکیده
Approaches to evolving the architectures of artificial neural networks have involved incrementally adding topological features (complexification), removing features (simplification), or both. We will present a comparative study of these dynamics, focusing on the domains of XOR and Tic-Tac-Toe, using NEAT (NeuroEvolution of Augmenting Topologies) as the starting point. Experimental comparisons are done using complexification, simplification, and a blend of both. Analysis of the effects of each approach on the variation, complexity, and fitness of the evolving populations demonstrates that algorithms employing both complexification and simplification dynamics search more efficiently and produce more compact solutions.
منابع مشابه
Comparative Analysis of Neural Network Training Methods in Real-time Radiotherapy
Background: The motions of body and tumor in some regions such as chest during radiotherapy treatments are one of the major concerns protecting normal tissues against high doses. By using real-time radiotherapy technique, it is possible to increase the accuracy of delivered dose to the tumor region by means of tracing markers on the body of patients.Objective: This study evaluates the accuracy ...
متن کاملEntrepreneurship policy and innovative indicators of industrial companies: Evaluation by MCDM and ANN Methods
The present paper presented a methodology for prioritizing the innovative and entrepreneurial indicators using Multi Criteria Decision Making (MCDM) and Artificial Neural Networks (ANNs), taking into account three individual, organizational and cultural dimensions simultaneously in decision making procedure. This methodology has two main advantages: first, the speed of operation in the accounti...
متن کاملCompetitive Coevolution through Evolutionary Complexification
Two major goals in machine learning are the discovery of complex multidimensional solutions and continual improvement of existing solutions. In this paper, we argue that complexification, i.e. the incremental elaboration of solutions through adding new structure, achieves both these goals. We demonstrate the power of complexification through the NeuroEvolution of Augmenting Topologies (NEAT) me...
متن کاملA comparative analysis of two neural network predictions for performance and emissions in a biodiesel fuelled diesel Engine
متن کامل
A Differential Evolution and Spatial Distribution based Local Search for Training Fuzzy Wavelet Neural Network
Abstract Many parameter-tuning algorithms have been proposed for training Fuzzy Wavelet Neural Networks (FWNNs). Absence of appropriate structure, convergence to local optima and low speed in learning algorithms are deficiencies of FWNNs in previous studies. In this paper, a Memetic Algorithm (MA) is introduced to train FWNN for addressing aforementioned learning lacks. Differential Evolution...
متن کامل