In this paper we apply Particle Swarm Optimization (PSO) algorithm to the training process of a Multilayer Perceptron (MLP) on the problem of localizing a mobile GSM network terminal inside a building. The localization data includes the information about the average GSM and WiFi signals in each of the given (x,y,floor) coordinates from more than two thousand points inside a five story building....

A new scheme of knowledge encoding in a fuzzy multilayer perceptron (MLP) using rough set-theoretic concepts is described. Crude domain knowledge is extracted from the data set in the form of rules. The syntax of these rules automatically determines the appropriate number of hidden nodes while the dependency factors are used in the initial weight encoding. The network is then refined during tra...

In this paper, we present a new class of quasi-Newton methods for an effective learning in large multilayer perceptron (MLP)-networks. The algorithms introduced in this work, named LQN, utilize an iterative scheme of a generalized BFGS-type method, involving a suitable family of matrix algebras L. The main advantages of these innovative methods are based upon the fact that they have an O(nlogn)...

n M In this paper we present a hybrid multilayer perceptron (MLP)/hidde arkov model (HMM) speaker-independent continuous-speech recognib tion system, in which the advantages of both approaches are combined y using MLPs to estimate the state-dependent observation probabilities p of an HMM. New MLP architectures and training procedures are resented which allow the modeling of multiple distributio...

GR2 is a hybrid knowledge-based system consisting of a Multilayer Perceptron (MLP) and a rule-based system for hybrid knowledge representations and reasoning. Knowledge embedded in the trained MLP is extracted in the form of general (production) rules — a natural format of abstract knowledge representation. The rule extraction method integrates Black-box and Open-box techniques, obtaining featu...

As learning methods of a multilayer perceptron (MLP), we have the BP algorithm, Newton’s method, quasiNewton method, and so on. However, since the MLP search space is full of crevasse-like forms having a huge condition number, it is unlikely for such usual existing methods to perform efficient search in the space. This paper proposes a new search method which utilizes eigen vector descent and l...

Overfitting in multilayer perceptron (MLP) training is a serious problem. The purpose of this study is to avoid overfitting in on-line learning. To overcome the overfitting problem, we have investigated feeling-of-knowing (FOK) using self-organizing maps (SOMs). We propose MLPs with FOK using the SOMs method to overcome the overfitting problem. In this method, the learning process advances acco...

Reducing the computational complexity is desired in speech coding algorithms. In this paper, three neural gain predictors are proposed which can function as backward gain adaptation module of low delay-code excited linear prediction (LD-CELP) G.728 encoder, recommended by International Telecommunication Union-Telecom sector (ITU-T, formerly CCITT). Elman, multilayer perceptron (MLP) and fuzzy A...

A multilayer perceptron (MLP) artificial neural network (NN) was trained with Monte Carlo data to detect b-jets. A variety of NNs were tested to maximize performance. The best NN was run on data with different reconstruction options. It was found that a simple MLP NN with 6 variables and 6 hidden neurons performed better than using only a decay length significance cut for detecting b-jets. The ...

An approach for invariant clustering and recognition of objects (situation) in dynamic environment is proposed. This approach is based on the combination of clustering by using unsupervised neural network (in particular ART-2) and preprocessing of sensor information by using forward multilayer perceptron (MLP) with error back propagation (EBP) which supervised by clustering neural network. Usin...