A Novel Chemical Reaction Optimization Algorithm for Higher Order Neural Network Training

نویسندگان

  • K. K. SAHU
  • SIBARAMA PANIGRAHI
  • H. S. BEHERA
چکیده

In this paper, an application of a novel chemical reaction optimization (CRO) algorithm for training higher order neural networks (HONNs), especially the Pi-Sigma Network (PSN) has been presented. In contrast to basic CRO algorithms, the proposed CRO algorithm used to train HONN possesses two modifications. The reactant size (population size) remains fixed throughout all the iteration, which makes it easier to implement; and adaptive chemical reactions followed by a strictly greedy reversible reaction have been used which assist to reach the global minima in less number of iterations. The performance of proposed algorithm for HONN training is evaluated through a well-known neural network training benchmark i.e. to classify the parity-p problems. The results obtained from the proposed algorithm to train HONN have been compared with results from the following algorithms: basic CRO algorithm and the two most popular variants of differential evolution algorithm (DE/rand/1/bin and DE/best/1/bin). It is observed that the application of the proposed CRO algorithm to HONN training (CRO-HONNT) performs statistically better than that of other algorithms.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Modeling and Optimization of β-Cyclodextrin Production by Bacillus licheniformis using Artiï‌cial Neural Network and Genetic Algorithm

Background: The complexity of the fermentation processes is mainly due to the complex nature of the biological systems which follow the life in a non-linear manner. Joined performance of artificial neural network (ANN) and genetic algorithm (GA) in finding optimal solutions in experimentation has found to be superior compared to the statistical methods. Range of applications of β-cyclodextrin (...

متن کامل

A novel hybrid chemical reaction optimization algorithm with adaptive differential evolution mutation strategies for higher order neural network training

In this paper, an application of a hybrid Chemical Reaction Optimization (CRO) algorithm with adaptive Differential Evolution (DE) mutation strategies for training Higher Order Neural Networks (HONNs), especially the Pi-Sigma Network (PSN) is presented. Contrasting to traditional CRO algorithms, the reactant size (population size) remains fixed throughout all iterations, which makes it easier t...

متن کامل

A Comparison Between GA and PSO Algorithms in Training ANN to Predict the Refractive Index of Binary Liquid Solutions

A total of 1099 data points consisting of alcohol-alcohol, alcohol-alkane, alkane-alkane, alcohol-amine and acid-acid binary solutions were collected from scientific literature to develop an appropriate artificial neural network (ANN) model. Temperature, molecular weight of the pure components, mole fraction of one component and the structural groups of the components were used as input paramet...

متن کامل

Identification of Wind Turbine using Fractional Order Dynamic Neural Network and Optimization Algorithm

In this paper, an efficient technique is presented to identify a 2500 KW wind turbine operating in Kahak wind farm, Qazvin province, Iran. This complicated system dealing with wind behavior is identified by using a proposed fractional order dynamic neural network (FODNN) optimized with evolutionary computation. In the proposed method, some parameters of FODNN are unknown during the process of i...

متن کامل

A Hybrid Optimization Algorithm for Learning Deep Models

Deep learning is one of the subsets of machine learning that is widely used in Artificial Intelligence (AI) field such as natural language processing and machine vision. The learning algorithms require optimization in multiple aspects. Generally, model-based inferences need to solve an optimized problem. In deep learning, the most important problem that can be solved by optimization is neural n...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2013