We present a theoretical analysis of a version of the LAPART adaptive inferencing neural network. Our main result is a proof that the new architecture, called LAPART 2, converges in two passes through a fixed training set of inputs. We also prove that it does not suffer from template proliferation. ...

A nonlinear multivariate analysis, artificial autoassociative neural network (AANN), was applied to bioprocess fault detection. In an optimal production process of a recombinant yeast with a temperature controllable expression system, faults in test cases with faulty temperature sensors and plasmid instability of recombinant cells could be detected by the AANN. ...

Predicting conditional probability densities with neural networks requires complex (at least two-hidden-layer) architectures, which normally leads to rather long training times. By adopting the RVFL concept and constraining a subset of the parameters to randomly chosen initial values (such that the EM-algorithm can be applied), the training process can be ...

We propose a new approach for leave-one-out cross-validation of neural-network classifiers called "cross-validation with active pattern selection" (CV/APS). In CV/APS, the contribution of the training patterns to network learning is estimated and this information is used for active selection of CV patterns. On the tested examples, the computational cost of ...

Persistence is one of the most common characteristics of real-world time series. In this work we investigate the process of learning persistent dynamics by neural networks. We show that for chaotic times series the network can get stuck for long training periods in a trivial minimum of the error function ...

In this paper, fuzzy inference models for pattern classifications have been developed and fuzzy inference networks based on these models are proposed. Most of the existing fuzzy rule-based systems have difficulties in deriving inference rules and membership functions directly from training data. Rules and membership functions are obtained from experts. ...

This paper describes how the SGOCE paradigm has been used to evolve developmental programs capable of generating recurrent neural networks that control the behavior of simulated insects. This paradigm is characterized by an encoding scheme, an evolutionary algorithm, syntactic constraints, and an incremental strategy that are described in turn. The ...

A Neural integrated Fuzzy conTroller (NiF-T) which integrates the fuzzy logic representation of human knowledge with the learning capability of neural networks is developed for nonlinear dynamic control problems. NiF-T architecture comprises of three distinct parts: (1) Fuzzy logic Membership Functions (FMF), (2) a Rule Neural Network (RNN), and (3) ...

A tight bound on the generalization performance of concept learning is shown by a novel approach. Unlike existing theories, the new approach uses no assumption on large sample size as in Bayesian approach and does not consider the uniform learnability as in the VC dimension analysis. We analyze the generalization ...

In this paper, the local minima-free conditions of the outer-supervised feedforward neural networks (FNN) based on batch-style learning are studied by means of the embedded subspace method. It is proven that only if the rendition that the number of the hidden neurons is not less than that of the training ...

In this work, a probabilistic model is established for recurrent networks. The expectation-maximization (EM) algorithm is then applied to derive a new fast training algorithm for recurrent networks through mean-field approximation. This new algorithm converts training a complicated recurrent network into training an array of individual feedforward neurons. These neurons ...

A 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 ...

University admissions and business personnel offices use a limited number of resources to process an ever-increasing quantity of student and employment applications. Application systems are further constrained to identify and acquire, in a limited time period, those candidates who are most likely to accept an offer of enrolment or employment. ...

We present a training approach using concepts from the theory of stochastic learning automata that eliminates the need for computation of gradients. This approach also offers the flexibility of tailoring a number of specific training algorithms based on the selection of linear and nonlinear reinforcement rules for updating automaton action ...

In two experiments we investigated the role of continuous concurrent visual feedback in the learning of discrete movement tasks. During practice the learner's actions either were or were not displayed on-line during the action; in both conditions the participant received kinematic feedback about errors afterward. Learning was evaluated in retention ...

Training of artificial neural networks is normally a time consuming task due to iterative search imposed by the implicit nonlinearity of the network behaviour. In this work, three improvements to "batch-mode" offline training methods, gradient-based or gradient-free, are proposed. For nonlinear multilayer perceptrons (NMLP) with linear output layers, a method ...

This paper synthesises three diverse approaches to the study of consciousness in a description of an existing program of work in Artificial Neuroconsciousness. The three approaches are drawn from automata theory ([Aleksander, 1995][Aleksander, 1996]), psychology ([Karmiloff-Smith, 1992]; [Clark Karmiloff-Smith, 1993]) and philosophy ([Searle, 1992]).Previous work on bottom-level sensory-motor tasks from ...

A new structure and training method for multilayer neural networks is presented. The proposed method is based on cascade training of subnetworks and optimizing weights layer by layer. The training procedure is completed in two steps. First, a subnetwork, m inputs and n outputs as the style of training samples, ...

In this study, a proposition of simultaneous training of the neural network (multilayer perceptron) and adaptive preprocessing unit is presented. This cooperation enables the network to affect the preprocessing and as a consequence to vary the locations of pattern vectors in a feature space. Thus, during the learning process the ...

In this paper, a neural network based generalized software system is presented for automatic analysis of electrocardiograms (ECGs). The proposed system is capable of intuitively diagnosing the disease from the ECG using the knowledge acquired from the training. A modified decision based neural network which converges in a finite amount ...

OBJECTIVE: Numerous studies in the occupational therapy literature have investigated the effects of added-purpose (multidimensional, goal-oriented) occupation on performance. Motor learning research has demonstrated that factors that enhance performance measures do not necessarily enhance motor learning. This study examined the effects of both added-purpose and meaningful occupation on motor learning. ...

The purpose of this study was to compare the performance of fundamental gross motor skills by 10 girls and 10 boys, 7 yr. old, with learning disabilities. Their skills were assessed on the Test of Gross Motor Development. The boys achieved significantly higher mean scores than the girls on the ...

An artificial neural network (ANN) was developed to investigate whether hoof wall deformation could be used to determine ground reaction forces (GRF) in horses. The ANN was taught this relationship under certain conditions and was able to generalise this knowledge to conditions for which it was not trained before. To ...

In contrast to conventional multilayered feedforward networks which are typically trained by iterative gradient search methods, an optimal interpolative (OI) net can be trained by a noniterative least squares algorithm called RLS-OI. The basic idea of RLS-OI is to use a subset of the training set, whose inputs are called ...

A fast training algorithm is developed for two-layer feedforward neural networks based on a probabilistic model for hidden representations and the EM algorithm. The algorithm decomposes training the original two-layer networks into training a set of single neurons. The individual neurons are then trained via a linear weighted regression algorithm. ...

The contextual layered associative memory (CLAM) has been developed as a self-generating structure which implements a probabilistic encoding scheme. The training algorithms are geared towards the unsupervised generation of a layerable associative mapping ([Thacker and Mayhew, 1989]). We show here that the resulting structure will support layers which can be ...

Query-based learning (QBL) has been introduced for training a supervised network model with additional queried samples. Experiments demonstrated that the classification accuracy is further increased. Although QBL has been successfully applied to supervised neural networks, it is not suitable for unsupervised learning models without external supervisors. In this paper, an ...

Training recurrent neural networks to perform certain tasks is known to be difficult. The possibility of adding synaptic delays to the network properties makes the training task more difficult. However, the disadvantage of tough training procedure is diminished by the improved network performance. During our research of training neural networks ...

Evolutionary artificial neural networks (EANN) are a new paradigm that refers to a special class of artificial neural networks (ANN) in which evolution is another fundamental form of adaptation in addition to learning. Evolution can be introduced at various levels of ANN. It can be used to evolve weights, architectures ...

This paper analyzes parallel implementation of the backpropagation training algorithm on a heterogeneous transputer network (i.e., transputers of different speed and memory) connected in a pipelined ring topology. Training-set parallelism is employed as the parallelizing paradigm for the backpropagation algorithm. It is shown through analysis that finding the optimal allocation ...

This paper describes elements necessary for a general-purpose low-cost very large scale integration (VLSI) neural network. By choosing a learning algorithm that is tolerant of analog nonidealities, the promise of high-density analog VLSI is realized. A 64-synapse, 8-neuron proof-of-concept chip is described. The synapse, which occupies only 4900 mum(2) in ...

Total hip arthroplasty (THA) is one of the major breakthroughs in modern orthopedics this century. Since its introduction in the early 1960s by Sir J. Charnley, it has become the most common form of arthroplasty. The art of performing THA has developed to a large extent, yet with the inevitable ...

Backpropagation-through-time (BPTT) is the temporal extension of backpropagation which allows a multilayer neural network to approximate an optimal state-feedback control law provided some prior knowledge (Jacobian matrices) of the process is available. In this paper, a simplified version of the BPTT algorithm is proposed which more closely respects the principle ...

In applying the neural network to the classification problem in pharmacology, we adopt an extended back-propagation (EBP) learning which adjusts the parameters appearing in an activation function, as well as the weights. The results of simulations show that such an extended learning speeds up the learning process as compared with ...

This paper introduces a hybrid system termed cascade adaptive resonance theory mapping (ARTMAP) that incorporates symbolic knowledge into neural-network learning and recognition. Cascade ARTMAP, a generalization of fuzzy ARTMAP, represents intermediate attributes and rule cascades of rule-based knowledge explicitly and performs multistep inferencing. A rule insertion algorithm translates if-then symbolic ...

This paper proposes a framework for constructing and training radial basis function (RBF) neural networks. The proposed growing radial basis function (GRBF) network begins with a small number of prototypes, which determine the locations of radial basis functions. In the process of training, the GRBF network gross by splitting one ...

In this paper, we show that noise injection into inputs in unsupervised learning neural networks does not improve their performance as it does in supervised learning neural networks. Specifically, we show that training noise degrades the classification ability of a sparsely connected version of the Hopfield neural network, whereas the ...

Bayesian inferencing as a machine learning technique was evaluated for identifying pre-crash activity and crash type from accident narratives describing 3,686 motor vehicle crashes. It was hypothesized that a Bayesian model could learn from a computer search for 63 keywords related to accident categories. Learning was described in terms of ...

Previous studies have shown that leopard frogs, Rana pipiens, use tongue prehension to capture small prey and jaw prehension to capture large prey. After hypoglossal nerve transection, the frogs fail to open their mouths when attempting to feed on small prey, but open their mouths and capture large prey. Here, ...

An intensive early intervention program was evaluated through determining child gains made by 44 children with special needs in cognition, gross-motor, fine-motor, receptive language, and expressive language domains. Gains were examined for the total group and two subgroups based upon their delays at pretesting. Analyses comparing actual to predicted posttest ...

The back-propagation learning algorithm for multi-layered neural networks, which is often successfully used in practice, appears very time consuming even for small network architectures or training tasks. However, no results are yet known concerning the complexity of this algorithm. Blum and Rivest proved that training even a three-node network is ...

This paper demonstrates how a feedforward network with constant connection matrices may be used to train a Hopfield style network for pattern recognition. The connection matrix of the Hopfield style network is asymmetric and its diagonal is non-zero. The Hopfield style network referred to as a GDHN is trained to ...

The universal asymptotic scaling laws proposed by Amari et al. are studied in large scale simulations using a CM5. Small stochastic multilayer feedforward networks trained with backpropagation are investigated. In the range of a large number of training patterns t, the asymptotic generalization error scales as 1/t as predicted. For ...

Two studies were conducted to examine the relations between Marcia's four identity statuses and Allport and Ross' four religious orientations. Study 1 was conducted among 38 Mormon and 47 non-Mormon high school students living in a predominantly Mormon Utah community. Study 2 was conducted among 102 Jewish high school students ...

In the construction of neural networks involving associative recall, information is sometimes best encoded with a local representation. Moreover, a priori knowledge can lead to a natural selection of connection weights for these networks. With predetermined and fixed weights, standard learning algorithms that work by altering connection strengths are unable ...

The authors developed and tested 12 neural networks of different architectures to make lower-third-molar treatment-planning decisions, using a software-based neural network (Neudesk 1.2, Neural Computer Sciences, Southampton, UK). Network training was undertaken using clinical histories from 119 patients (with 238 lower third molars) referred for treatment planning (79 females and ...

The purpose of this article is to understand that the reason so many programs fall short in addressing and improving competitiveness is that their single focus is on information technology, to instill in our minds that there are many other elements of change that need to be considered (behavior being ...

This paper examines the implementation of projection pursuit regression (PPR) in the context of machine learning and neural networks. We propose a parametric PPR with direct training which achieves improved training speed and accuracy when compared with nonparametric PPR. Analysis and simulations are done for heuristics to choose good initial ...

In this paper, we present two learning mechanisms for artificial neural networks (ANN's) that can be applied to solve classification problems with binary outputs. These mechanisms are used to reduce the number of hidden units of an ANN when trained by the cascade-correlation learning algorithm (CAS). Since CAS adds hidden ...

Four different neural network algorithms, binary adaptive resonance theory (ART1), self-organizing map, learning vector quantization and back-propagation, were compared in the diagnosis of acute appendicitis with different parameter groups. The results show that supervised learning algorithms learning vector quantization and back-propagation were better than unsupervised algorithms in this medical decision ...