scispace - formally typeset
Search or ask a question
Topic

Soft computing

About: Soft computing is a research topic. Over the lifetime, 6710 publications have been published within this topic receiving 118508 citations.


Papers
More filters
Journal ArticleDOI
TL;DR: A deep learning approach capable to address the limitations of traditional forecasting approaches and show accurate predictions is proposed, and the empirical results show that the proposed DLSTM model outperforms other standard approaches.

471 citations

Journal ArticleDOI
TL;DR: It is shown that these proposed Bio-inspired Imprecise Computational blocks (BICs) can be exploited to efficiently implement a three-layer face recognition neural network and the hardware defuzzification block of a fuzzy processor.
Abstract: The conventional digital hardware computational blocks with different structures are designed to compute the precise results of the assigned calculations. The main contribution of our proposed Bio-inspired Imprecise Computational blocks (BICs) is that they are designed to provide an applicable estimation of the result instead of its precise value at a lower cost. These novel structures are more efficient in terms of area, speed, and power consumption with respect to their precise rivals. Complete descriptions of sample BIC adder and multiplier structures as well as their error behaviors and synthesis results are introduced in this paper. It is then shown that these BIC structures can be exploited to efficiently implement a three-layer face recognition neural network and the hardware defuzzification block of a fuzzy processor.

458 citations

Journal ArticleDOI
24 Apr 1998
TL;DR: In my perception, in coming years, the design, construction and utilization of information/intelligent systems will become the primary focus of science and technology, and I/IS systems will be a dominant presence in the authors' daily lives.
Abstract: We are living in a world which is undergoing profound changes brought about by rapid advances in science and technology. Among such changes, the most visible are those that relate to what is popularly referred to as the information revolution. The artifacts of this revolution are all around us: the e-mail, the world wide web, the cellular phone; the fax; and the desktop computer, among many others. Linked to the information revolution is another revolution — the intelligent systems revolution. The manifestations of this revolution are not as obvious as those of the information revolution because they involve, for the most part, not new products but higher MIQ (Machine IQ) of existing systems, products and devices. Among the familiar examples are smart appliances, smart cameras, smart robots and smart software for browsing, diagnosis, fraud detection and quality control. The information and intelligent systems revolutions are in a symbiotic relationship. Intelligence requires information and vice-versa. The confluence of intelligent systems and information systems leads to intelligent information systems. In this sense, the union of information systems, intelligent systems and intelligent information systems constitutes what might be referred to as information/intelligent systems, or I/IS for short. In my perception, in coming years, the design, construction and utilization of information/intelligent systems will become the primary focus of science and technology, and I/IS systems will become a dominant presence in our daily lives. When we take a closer look at information/intelligent systems what we see is the increasingly important role of soft computing (SC) in their conception, design and utilization. Basically, soft computing is an association of computing methodologies which includes as its principal members fuzzy

455 citations

Book ChapterDOI
01 Jan 2008
TL;DR: This chapter provides two recent algorithms for evolutionary optimization – well known as particle swarm optimization (PSO) and differential evolution (DE), inspired by biological and sociological motivations and can take care of optimality on rough, discontinuous and multimodal surfaces.
Abstract: Since the beginning of the nineteenth century, a significant evolution in optimization theory has been noticed. Classical linear programming and traditional non-linear optimization techniques such as Lagrange’s Multiplier, Bellman’s principle and Pontyagrin’s principle were prevalent until this century. Unfortunately, these derivative based optimization techniques can no longer be used to determine the optima on rough non-linear surfaces. One solution to this problem has already been put forward by the evolutionary algorithms research community. Genetic algorithm (GA), enunciated by Holland, is one such popular algorithm. This chapter provides two recent algorithms for evolutionary optimization – well known as particle swarm optimization (PSO) and differential evolution (DE). The algorithms are inspired by biological and sociological motivations and can take care of optimality on rough, discontinuous and multimodal surfaces. The chapter explores several schemes for controlling the convergence behaviors of PSO and DE by a judicious selection of their parameters. Special emphasis is given on the hybridizations of PSO and DE algorithms with other soft computing tools. The article finally discusses the mutual synergy of PSO with DE leading to a more powerful global search algorithm and its practical applications.

426 citations

Journal ArticleDOI
TL;DR: This paper presents a survey of state-of-the-art work in all aspects of approximate computing and highlights future research challenges in this field.
Abstract: As one of the most promising energy-efficient computing paradigms, approximate computing has gained a lot of research attention in the past few years. This paper presents a survey of state-of-the-art work in all aspects of approximate computing and highlights future research challenges in this field.

420 citations


Network Information
Related Topics (5)
Fuzzy logic
151.2K papers, 2.3M citations
90% related
Artificial neural network
207K papers, 4.5M citations
86% related
Optimization problem
96.4K papers, 2.1M citations
84% related
Feature extraction
111.8K papers, 2.1M citations
82% related
Cluster analysis
146.5K papers, 2.9M citations
81% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2023159
2022270
2021319
2020332
2019313
2018348