Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Eduardo Masato Iyoda is active.

Publication


Featured researches published by Eduardo Masato Iyoda.


brazilian symposium on neural networks | 1998

Feedforward neural network initialization: an evolutionary approach

L.N. de Castro; Eduardo Masato Iyoda; F.J. Von Zuben; Ricardo Ribeiro Gudwin

The initial set of weights to be used in supervised learning for multilayer neural networks has a strong influence in the learning speed and in the quality of the solution obtained after convergence. An inadequate initial choice of the weight values may cause the training process to get stuck in a poor local minimum or to face abnormal numerical problems. There are several proposed techniques that try to avoid both local minima and numerical instability, only by means of a proper definition of the initial set of weights. This paper focuses on the application of genetic algorithms (GA) as a tool to analyze the space of weights, in order to achieve good initial conditions for supervised learning. GAs almost-global sampling compliments connectionist local search techniques well, and allows one to find some very important characteristics in the initial set of weights for multilayer networks. The results presented are compared, for a set of benchmarks, with that produced by other approaches found in the literature.


international symposium on neural networks | 1999

Evolutionary hybrid composition of activation functions in feedforward neural networks

Eduardo Masato Iyoda; F.J. Von Zuben

Considering computational algorithms available in the literature, associated with supervised learning in feedforward neural networks, a wide range of distinct approaches can be identified While the adjustment of the connection weights represents an omnipresent stage, the algorithms differ in three basic aspects: the technique chosen to determine the dimension of the multilayer neural network, the procedure adopted to determine the activation function of each neuron, and the kind of composition of the hidden activations used to produce the output. The advanced learning algorithms are designed to treat all these three aspects during learning, guiding to dedicated solutions. In this paper, an evolutionary hybrid learning algorithm is presented to deal simultaneously with these three aspects. The essence of this approach is the existence of a search procedure based on a synergy between genetic algorithms and conjugate gradient optimization.


congress on evolutionary computation | 1999

Evolutionary design of neurofuzzy networks for pattern classification

Eduardo Masato Iyoda; L.N. de Castro; Fernando Gomide; F.J. Von Zuben

We consider a neural network based fuzzy system model whose basic processing unit consists of two types of generic logic (OR and AND) neurons. The net is structured into a multilayer topology and trained by a competitive learning algorithm, together with a genetic algorithm approach to select the most suitable triangular norms and co-norms that model the logic neurons. The main features of the system include: automatic rule generation and selection, learning capability, processing time independent of the input space partition, and automatic selection of the t-norms and s-norms that model the basic logic operators (OR, AND) encountered in the theory of fuzzy sets. Four benchmark problems are considered to compare the performance of the proposed method with those produced by alternative strategies.


Journal of Advanced Computational Intelligence and Intelligent Informatics | 2004

Solving Truck Delivery Problems Using Integrated Evaluation Criteria Based on Neighborhood Degree and Evolutionary Algorithm

Fangyan Dong; Kewei Chen; Eduardo Masato Iyoda; Hajime Nobuhara; Kaoru Hirota

To solve a real-world truck delivery and dispatch problem (TDDP) that involves multiple mutually conflicting objectives, such as running and loading costs, a concept of neighborhood degree (ND) and an integrated evaluation criteria (IEC) of the solution based on ND are proposed. The IEC makes the weight setting easier than by using conventional methods. To find a high-quality solution to a TDDP in practical computational time, an evolutionary algorithm is proposed. It involves 3 components: (i) a simulated annealing (SA)-based method for finding an optimal or a suboptimal route for each vehicle; (ii) an evolutionary computation (EC)-based method for finding an optimal schedule for a group of vehicles; and (iii) threshold-based evolutionary operations, utilizing the ND concept. The TDDP viewed from real-world application is formulated and the proposed algorithm is implemented on a personal computer using C++. The proposed algorithm is evaluated in 2 experiments involving real-world data representative of the TDDP, and applied to food product delivery to a chain of 46 convenience stores in Saitama Prefecture. In the 2 experiments, our proposed algorithm resulted in a better schedule (with 80%-90% shorter computational time) than a schedule produced by an expert. By incorporating application-specific evaluation criteria, the proposed algorithm is applied to problems such as homedelivery of parcels or mail, and to problems of multidepot delivery and dispatch.


4. Congresso Brasileiro de Redes Neurais | 2016

Redes Neurais Construtivas: Uma Abordagem Comparativa

Leandro Nunes de Castro; Eduardo Masato Iyoda; Eurípedes Pinheiro; Fernando J. Von Zuben

Until recently, the determination of a proper dimension for an artificial neural network in a given application task usually involved only the designer’s experience in implementing trial and error procedures. Nowadays, automatic design of neural network architectures is becoming part of the training process, by means of a more efficient exploration of the available information for supervised learning. Among the already proposed alternatives to automatic design, this paper emphasizes methods founded on the constructive paradigm. We chose three constructive algorithms for comparison: A* heuristic search (A*), CascadeCorrelation with different activation functions (CASCOR) and Projection Pursuit Learning (PPL). A brief review of these constructive strategies in the solution of regression problems is presented, and their performance in terms of the parsimony of the resultant architecture is verified in benchmark problems.


Computer-Aided Engineering | 2002

Hybrid neural networks: An evolutionary approach with local search

Eduardo Masato Iyoda; Fernando J. Von Zuben


한국지능시스템학회 국제학술대회 발표논문집 | 2003

Automatic Parameter Tuning for Simulated Annealing based on Threading Technique and its Application to Traveling Salesman Problem

Fangyan Dong; Eduardo Masato Iyoda; Kewei Chen; Hajime Nobuhara; Kaoru Hirota


Journal of Advanced Computational Intelligence and Intelligent Informatics | 2002

Sigma-Pi Cascade Extended Hybrid Neural Network

Eduardo Masato Iyoda; Kaoru Hirota; Fernando J. Von Zuben


Archive | 2000

Inteligencia computacional no projeto automatico de redes neurais hibridas e redes neurofuzzy heterogeneas

Eduardo Masato Iyoda; Fernando J. Von Zuben


Journal of Advanced Computational Intelligence and Intelligent Informatics | 2004

Translated Multiplicative Neuron: An Extended Multiplicative Neuron that can Translate Decision Surfaces

Eduardo Masato Iyoda; Hajime Nobuhara; Kaoru Hirota

Collaboration


Dive into the Eduardo Masato Iyoda's collaboration.

Top Co-Authors

Avatar

Kaoru Hirota

Tokyo Institute of Technology

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar

F.J. Von Zuben

State University of Campinas

View shared research outputs
Top Co-Authors

Avatar

Kewei Chen

Tokyo Institute of Technology

View shared research outputs
Top Co-Authors

Avatar

L.N. de Castro

State University of Campinas

View shared research outputs
Top Co-Authors

Avatar

Fangyan Dong

Beijing University of Technology

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Shin-ichi Yoshida

Tokyo Institute of Technology

View shared research outputs
Top Co-Authors

Avatar

Fernando Gomide

State University of Campinas

View shared research outputs
Researchain Logo
Decentralizing Knowledge