J ehoshua Bruck IBM Research Division Almaden Research Center San Jose, CA 95120-6099 An important issue in neural computation is the dynamic range of weights in the neural networks. Many experimental results on learning indicate that the weights in the networks can grow prohibitively large with the size of the inputs. Here we address this issue by studying the tradeoffs between the depth and t...

There is a tremendous interest in the development of the evolutionary computation techniques as they are well suited 10 deal with optimization of functions containing a large number of variables. This paper presents a brief review of evolutionary computing techniqucs. It also discusses briefly the hybridization of evolutionary computation and neural networks and presents ;I solution of a classi...

We show that neural networks with three-times continuously differentiable activation functions are capable of computing a certain family of n-bit boolean functions with two gates, whereas networks composed of binary threshold functions require at least omega(log n) gates. Thus, for a large class of activation functions, analog neural networks can be more powerful than discrete neural networks, ...

Spiking neural P system is a computing device recently introduced as a bridge between spiking neural nets and membrane computing. In this paper we focus on normal forms of these systems while preserving their computational power. We show that certain combinations of existing normal forms are possible without loss of computational power, thus answering partially open problems stated in [3,8]. We...

The hybrid fuzzy differential equations have a wide range of applications in science and engineering. We consider the problem of finding their numerical solutions by using a novel hybrid method based on fuzzy neural network. Here neural network is considered as a part of large field called neural computing or soft computing. The proposed algorithm is illustrated by numerical examples and the re...

in order to improve the level of intelligence, availability, being on demand, convenience, information and humanization of rural public transportation systems, they are more willing to use modern information and communicative technologies. in addition to management services, intelligent transportation systems can provide passengers, drivers, travel agencies and other institutions with other ser...

Soft Computing is an emerging field that consists of complementary elements of fuzzy logic, neural computing and evolutionary computation. Soft computing techniques have found wide applications. One of the most important applications is edge detection for image segmentation. The process of partitioning a digital image into multiple regions or sets of pixels is called image segmentation. Edge is...

bearing capacity prediction of shallow foundation is one of the most important problems in geotechnical engineering practices, with a wide variety range of methods which have been introduced to forecast it accurately. recently, soft computing methods such as artificial neural networks (anns) and support vector machines (svms) have been used for prediction of the ultimate bearing capacity of sha...