Bioinformatics with soft computing

Mitra, Sushmita; Hayashi, Yuzo

doi:10.1109/tsmcc.2006.879384

Cited by 96 publications

(26 citation statements)

References 118 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For instance, the least square methods like the Gauss-Newton and LM works only if the cost function is the sum of squared error. The Newton method has to compute a Hessian matrix (7), which has to be positive definite and computing the Hessian matrix (7) can be hard and expensive. Similarly, the Quasi-Newton and CG methods need to use a line-search method that sometimes can be expensive.…”

Section: Comments On Conventional Approachesmentioning

confidence: 99%

“…Moreover, it is the structure of an FNN that makes it a universal function approximator, which has the capabilities of approximating any continuous function [2]. Therefore, a wide range of problems is solved by the FNNs, such as pattern recognition [3], clustering and classification [4], function approximation [5], control [6], bioinformatics [7], signal processing [8], speech processing [9], etc.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Metaheuristic design of feedforward neural networks: A review of two decades of research

Ojha

Abraham

Snel

2017

Engineering Applications of Artificial Intelligence

441

154

View full text Add to dashboard Cite

Over the past two decades, the feedforward neural network (FNN) optimization has been a key interest among the researchers and practitioners of multiple disciplines. The FNN optimization is often viewed from the various perspectives: the optimization of weights, network architecture, activation nodes, learning parameters, learning environment, etc. Researchers adopted such different viewpoints mainly to improve the FNN's generalization ability. The gradient-descent algorithm such as backpropagation has been widely applied to optimize the FNNs. Its success is evident from the FNN's application to numerous real-world problems. However, due to the limitations of the gradient-based optimization methods, the metaheuristic algorithms including the evolutionary algorithms, swarm intelligence, etc., are still being widely explored by the researchers aiming to obtain generalized FNN for a given problem. This article attempts to summarize a broad spectrum of FNN optimization methodologies including conventional and metaheuristic approaches. This article also tries to connect various research directions emerged out of the FNN optimization practices, such as evolving neural network (NN), cooperative coevolution NN, complex-valued NN, deep learning, extreme learning machine, quantum NN, etc. Additionally, it provides interesting research challenges for future research to cope-up with the present information processing era.

show abstract

Section: Comments On Conventional Approachesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Metaheuristic design of feedforward neural networks: A review of two decades of research

Ojha

Abraham

Snel

2017

Engineering Applications of Artificial Intelligence

441

154

View full text Add to dashboard Cite

show abstract

“…The main aim of soft computing is that computation, reasoning and decision-making should exploit the tolerance for approximation, imprecision, uncertainty, and partial truth to obtain low-cost, low-precision solutions [7]. SC provides the means to build intelligent machines, solve nonlinear problems, and represent ambiguity in human behavior with uncertainty in real life.…”

Section: Basic Features Of Scmentioning

confidence: 99%

Soft Computing: an Introduction

et al. 2018

View full text Add to dashboard Cite

Soft computing (SC) is a newly emerging multidisciplinary field. It is a collection of computational techniques, such as expert systems, fuzzy logic, neural networks, and evolutionary algorithms, which provide information processing capabilities to solve complex practical problems. The major benefit of SC lies in its ability to tolerate imprecision, uncertainty, partial truth, and approximation in processing imprecise and inaccurate information and simulating human decision making at low cost. This paper provides a brief introduction on soft computing.

show abstract

“…Soft computing paradigm like fuzzy sets (FS), artificial neural networks (ANN) and support vector machines (SVMs) is used in Bioinformatics [7].…”

Section: Convolutional Neural Networkmentioning

confidence: 99%