Evolutionary Approach for Construction of the RBF Network Architecture

2014 ◽  
Author(s):  
Samuel Montero-Hernandez ◽  
Wilfrido Gomez-Flores
Keyword(s):  
Network Architecture ◽  
Evolutionary Approach ◽  
Rbf Network

scholarly journals Realization of Generalized RBF Network

2017 ◽  
Vol 1 (1) ◽  
pp. 1-16
Author(s):  
N.K. Lee ◽  
D. Wang
Keyword(s):  
Network Architecture ◽  
Sequence Data ◽  
Rbf Neural Network ◽  
Learning Criterion ◽  
Features Selection ◽  
Neural Network Architecture ◽  
Criterion Function ◽  
Rbf Network ◽  
Design And Implementation ◽  
Protein Sequence Data

This paper aims at developing techniqus for design and implementation of neural classifiers. Based on our previous study on generalized RBF neural network architecture and learning criterion function for parameter optimization, this work addresses two realization issues, i.e. supervised input features selection and genetic computation techniques for tuning classifiers. A comparative study on classifiation performance is carried on by a set of protein sequence data.

scholarly journals Modification os RBF Network Architecture

2017 ◽  
Vol 17 (1) ◽  
pp. 87 ◽  
Author(s):  
Mohd Yusoff Mashor
Keyword(s):  
Network Architecture ◽  
Rbf Network

Modification os RBF Network Architecture

Multilayered GMDH-Type Neural Network with Radial Basis Functions and its Application to 3-Dimensional Medical Image Recognition of the Liver

2007 ◽  
Vol 11 (1) ◽  
pp. 96-104 ◽  
Author(s):  
Tadashi Kondo ◽  
◽  
Junji Ueno ◽  
Abhijit S. Pandya ◽  
Keyword(s):  
Neural Network ◽  
Image Recognition ◽  
Network Architecture ◽  
Prediction Error ◽  
Medical Image ◽  
Basis Functions ◽  
Rbf Network ◽  
3 Dimensional ◽  
Medical Image Recognition ◽  
Neural Network Algorithm

In this paper, a Group Method of Data Handling (GMDH)-type neural network algorithm with radial basis functions (RBF) is proposed. The proposed algorithm generates optimum RBF network architectures fitting the complexity of nonlinear systems using heuristic self-organization. The number of hidden layers, the number of neurons in hidden layers and relevant input variables are selected by minimizing prediction error defined as Akaike’s Information Criterion (AIC). Various nonlinear combinations of variables are initially generated in each layer and only relevant combinations are selected based on AIC. Hence, the optimum RBF network architecture fitting the complexity of the nonlinear system is obtained. We apply the GMDH-type neural network algorithm with RBF to 3-dimensional medical image recognition of the liver, showing that this algorithm is very easy and useful in 3-dimensional medical image recognition of the liver because the neural network architecture is automatically organized to minimize prediction error based on AIC.

Cognitive gadgets: A provocative but flawed manifesto

2019 ◽  
Vol 42 ◽  
Author(s):  
Marco Del Giudice
Keyword(s):  
Theory Of Mind ◽  
Cultural Differences ◽  
Twin Studies ◽  
Cross Cultural ◽  
Evolutionary Approach ◽  
Genetic Inheritance ◽  
Double Standards ◽  
Cross Cultural Differences ◽  
Cherry Picking ◽  
Dichotomous Thinking

Abstract The argument against innatism at the heart of Cognitive Gadgets is provocative but premature, and is vitiated by dichotomous thinking, interpretive double standards, and evidence cherry-picking. I illustrate my criticism by addressing the heritability of imitation and mindreading, the relevance of twin studies, and the meaning of cross-cultural differences in theory of mind development. Reaching an integrative understanding of genetic inheritance, plasticity, and learning is a formidable task that demands a more nuanced evolutionary approach.

Sign in / Sign up

Export Citation Format

Share Document