This paper illustrates the applicability of neural networks in classifying events using Space Acceleration Measurement System (SAMS) data. Computer programs have been written in the MATLAB environment for the following purposes: automatic retrieval of SAMS data from NASA CDROM disks, computation of power spectral densities for SAMS data and construction ...

This paper presents a neural-network architecture and an instant learning algorithm that rapidly decides the weights of the designed single-hidden layer neural network. For an n-dimensional N-pattern training set, with a constant bias, a maximum of N-r-1 hidden nodes is required to learn the mapping within a given precision (where ...

This paper discusses the Delta-rule and training of min-max neural networks by developing a differentiation theory for min-max functions, the functions containing min (wedge) and/or max (V) operations. We first prove that under certain conditions all min-max functions are continuously differentiable almost everywhere in the real number field R and ...

In this paper, we describe a method which enables us to study the average generalization performance of learning directly via hypothesis testing inequalities. The resulting theory provides a unified viewpoint of average-case learning curves of concept learning and regression in realistic learning problems not necessarily within the Bayesian framework. The ...

How to learn new knowledge without forgetting old knowledge is a key issue in designing an incremental-learning neural network. In this paper, we present a new incremental learning method for pattern recognition, called the "incremental backpropagation learning network", which employs bounded weight modification and structural adaptation learning rules and applies ...

This paper presents an unsupervised learning scheme for initializing the internal representations of feedforward neural networks, which accelerates the convergence of supervised learning algorithms. It is proposed in this paper that the initial set of internal representations can be formed through a bottom-up unsupervised learning process applied before the top-down ...

Following a cerebro-vascular accident, motor deficits are usually associated with a selective atrophy of fast fatiguable muscle fibers. The reduction of output torque in spastic patients is considered to be caused by unfused twitches resulting from the reduction in the motor unit firing rate. To regain control of a paretic ...

23 athletes were asked to complete the Learning Styles Inventory first focusing on classroom learning, then on learning in their sport. Analysis indicated that learning styles shift across cognitive and motor settings. As a result, to ensure the validity of the results, giving respondents a particular focus when taking the ...

During 1983-1992, a total of 5831 deaths in the United States were attributed to motor-vehicle collisions with trains. During that same period, Kansas had the third highest death rate in the United States from motor-vehicle collisions with trains, and the annual rate for the state (0.8 per 100,000 persons) was ...

The two-layer radial basis function network, with fixed centers of the basis functions, is analyzed within a stochastic training paradigm. Various definitions of generalization error are considered, and two such definitions are employed in deriving generic learning curves and generalization properties, both with and without a weight decay term. The ...

This study investigated changes in knee extensor and flexor strength of 17 mildly involved adolescents with cerebral palsy in response to an eight-week isokinetic strength-training program. Peak torque and work were used as strength outcome measures. Subsequent changes in gross motor function and walking efficiency were evaluated. The significant strength ...

This paper addresses the structure and an associated on-line learning algorithm of a feedforward multilayer connectionist network for realizing the basic elements and functions of a traditional fuzzy logic controller. The proposed Fuzzy Adaptive Learning Control Network (FALCON) can be contrasted with the traditional fuzzy logic control systems in their ...

We report on the construction of neural networks for determining whether pediatric patients requiring transport to a tertiary care center should be moved by air or by ground. The networks were based on the functional-link net architecture. In two experiments, feedforward supervised-learning neural nets were trained with examples of an ...

We here present a parallel implementation of artificial neural networks on the connection machine CM-5 and compare it with other parallel implementations on SIMD and MIMD architectures. This parallel implementation was developed with the goal of efficiently training large neural networks with huge training pattern sets for applications in molecular ...

Two machine learning techniques were evaluated for automatic design of a rule-based control of functional electrical stimulation (FES) for locomotion of spinal cord injured humans. The task was to learn the invariant characteristics of the relationship between sensory information and the FES-control signal by using off-line supervised training. Sensory signals ...

The effects of human speech on a fine, continuous, and open motor skill were examined. A tape of auditory human radio traffic was injected into a tank gunnery simulator during each training session for 4 wk. of training for 3 hr. a week. The dependent variables were identification time, fire ...

Training set parallelism and network based parallelism are two popular paradigms for parallelizing a feedforward (artificial) neural network. Training set parallelism is particularly suited to feedforward neural networks with backpropagation learning where the size of the training set is large in relation to the size of the network. This paper ...

Traditional cardiac auscultation involves a great deal of interpretive skill. Neural networks were trained as phonocardiographic classifiers to determine their viability in this rôle. All networks had three layers and were trained by backpropagation using only the heart sound amplitude envelope as input. The main aspect of the study was ...

The optimal interpolative (OI) classification network is extended to include fault tolerance and make the network more robust to the loss of a neuron. The OI net has the characteristic that the training data are fit with no more neurons than necessary. Fault tolerance further reduces the number of neurons ...

A novel algorithm is presented which supplements the training phase in feedforward networks with various forms of information about desired learning properties. This information is represented by conditions which must be satisfied in addition to the demand for minimization of the usual mean square error cost function. The purpose of ...

Discusses the learning problem of neural networks with self-feedback connections and shows that when the neural network is used as associative memory, the learning problem can be transformed into some sort of programming (optimization) problem. Thus, the rather mature optimization technique in programming mathematics can be used for solving the ...

Parts I-III of this series established signs of disturbed motor performance--the "psychotic motor syndrome" (PMS)--in schizophrenic and endogenous depressed patients, which was not found in neurotic/reactive depressed nor healthy persons. Part IV yielded EEG signs of concomitant brain dysfunction in these patients, which were demonstrated by other (SPECT/PET) neuroimaging methods ...

Learning from examples plays a central role in artificial neural networks. The success of many learning schemes is not guaranteed, however, since algorithms like backpropagation may get stuck in local minima, thus providing suboptimal solutions. For feedforward networks, optimal learning can be achieved provided that certain conditions on the network ...

This paper studies the sampling strategies for the Expert Network (EexNet), a statistical learning system used for patient record classification at the Mayo Clinic. The goal is to achieve high accuracy classification at an affordable computational cost in very large applications. The learning curves of ExpNet were observed with respect ...

Collision identification between convex polyhedra is a major research focus in computer-aided manufacturing and path planning for robots. This paper presents a collision-identification neural network (CINN) to identify possible collisions between two convex polyhedra. It consists of a modified Hamming net and a constraint subnet. The modified Hamming net is ...

A technique for evaluating the learning capability and optimizing the feature space of a class of higher-order neural networks is presented. It is shown that supervised learning can be posed as an optimization problem in which inequality constraints are used to code the information contained in the training patterns and ...

Learning disability is characterised by a discrepancy between achievement and assessed intellectual ability. Children with this problem commonly (but not invariably) show impaired motor proficiency, as assessed by such instruments as the Bruininks-Oseretsky Test of motor proficiency. It has been hypothesised that poor motor performance and/or poor social skills lead ...

In this paper we present results of simulations performed assuming both forward and backward computation are done on-chip using analog components. Aspects of analog hardware studied are component variability, limited voltage ranges, components (multipliers) that only approximate the computations in the backpropagation algorithm, and capacitive weight decay. It is shown ...

As compared with providing extrinsic feedback on each of a set of practice trials, reducing the feedback frequency in various ways facilitates long-term retention. One explanation is that frequent feedback operates proactively on the subsequent trial, inducing excessive variability that degrades learning. We tested this view by giving or not ...

The aim of this research was to evaluate the comfort of a passenger seat for a new type of bus. A fuzzy set model of a multistage comfort scale (MCS) was adopted for the assessment of comfort, together with the techniques of human back shape and EMG measurements as well ...

A major bottleneck in building expert systems is the process of acquiring the required knowledge in the form of production rules. A novel class of neural networks is proposed to articulate the knowledge it learned from a set of examples. It provides an appealing solution to the problem of knowledge ...

This paper describes the design of a Microsoft Excel Program which interactively creates attractive and outstanding survival curves. This program enables medical researchers to easily create quality presentation graphs of survival curves and obtain high quality slides and prints, which can be inserted in papers or used directly at medical ...

This article addresses implications for the practice of occupational therapy when that therapy is guided by theories of motor learning. In occupational therapy, clients must learn or relearn motor skills through the use of activities. The occupational therapist must present activities in a manner that elicits the retention and transfer ...

Motor program theory has provided physical therapists with one approach to understanding how the brain controls movement. Analogous with computer programs that specify the operations of computer hardware, motor programs are thought to contain commands for muscles that allow movements to occur without the need for continuous peripheral feedback. A ...

Expert systems (ESs) are computer programs designed to make decisions in a manner similar to the way human experts make them. There are many forms of ESs, ranging from those that are given specific If-Then rules to those that are capable of deriving their own rules. Some ESs use neural ...

We report the use of an artificial neural network to analyze the fingerprint region of Fourier-transform infrared (ir) spectra of oligosaccharides for the presence of sulfate groups. This assay can rapidly and nondestructively detect the presence of sulfate in as little as 1 nmol (approximately 2 micrograms) of a glycoprotein-derived ...

A computational model of programmed cell death (PCD) in the nervous system is described. A neurobiologically realisable method for identifying and removing the least useful cells from a network is developed, and it is shown by simulation that an artificial neural network can solve difficult problems efficiently if it is ...

Kohonen's learning vector quantization (LVQ) is an efficient neural network based technique for pattern recognition. The performance of the method depends on proper selection of the learning parameters. Over-training may cause a degradation in recognition rate of the final classifier. In this paper we introduce constrained learning vector quantization (CLVQ). ...

This paper proposes a new type of neural network called the Dynamic Threshold Neural Network (DTNN) which is theoretically and experimentally superior to a conventional sigmoidal multilayer neural network in classification capability. Given a training set containing 4k + 1 patterns in Rn, to successfully learn this training set, the ...

The teaching of oxygen transport by hemoglobin is supported by a graphic depiction of the sigmoid O2 dissociation curve of hemoglobin. However, a reconstruction of the same curve into an alternate paradigm, the "O2-carrying flask," affords a visual demonstration of the significance of its sigmoid shape and the implications of ...

For neural networks to develop good internal representations for pattern mapping, noise in the training set data must be controlled. Because of the many difficulties associated with manually validating training data, we have focused on using decision table techniques as a practical, domain-independent means of optimizing training set formulation. Decision ...

Understanding the afferent neural system of the knee is considered to be vital to rehabilitation planning. An intricate relationship exists involving the afferent neural receptors in the inert and contractile tissues of the knee. Traditional rehabilitation strategies may not exploit this extensive afferent neural system. Closed kinetic chain functional training ...

The successful strategies of second-year medical students were electronically captured from computer-based simulations in immunology and infectious disease and were used to train artificial neural networks for the rapid classification of subsequent students' and experts' strategies on these problems. Such networks could categorize problem solutions of other students as successful ...

An iterative learning algorithm called PRLAB is described for the discrete bidirectional associative memory (BAM). Guaranteed recall of all training pairs is ensured by PRLAB. The proposed algorithm is significant in many ways. Unlike many existing iterative learning algorithms, PRLAB is not based on the gradient descent technique. It is ...

OBJECTIVES: Occupational therapy authors frequently emphasize the importance of the use of objects in the development of motor skill. This study investigated the use of object-produced visual input in learning control of flexion and extension of an above-elbow training prosthesis. METHOD: Fifty-two male college students were randomly assigned to two ...

Determining the architecture of a neural network is an important issue for any learning task. For recurrent neural networks no general methods exist that permit the estimation of the number of layers of hidden neurons, the size of layers or the number of weights. We present a simple pruning heuristic ...

Contextual interference effects in motor learning usually were not found when the tasks to be learned presumably required the same generalized motor program (GMP) and differed only with regard to the movement parameters (see Lee, Wulf, & Schmidt, 1992; Magill & Hall, 1990). Thus, tasks requiring different motor programs (e.g., ...

In this paper, an analogue, cascadable, CMOS chip set for artificial neural networks is presented. The chip set (a synapse chip and a neuron chip) offer on-chip back-propagation learning in a fully parallel, layered, feedforward network of arbitrary size and topology. The learning scheme is implemented with no extra circuits ...

A computational procedure (program) is defined to generate control signals for the motoneuron pools of agonist and antagonist muscles that will move a limb segment from one stationary position to another. The program accounts for the ability to move different distances with different inertial loads and for the influence of ...

Backpropagation neural networks are a computer-based pattern-recognition method that has been applied to the interpretation of clinical data. Unlike rule-based pattern recognition, backpropagation networks learn by being repetitively trained with examples of the patterns to be differentiated. We describe and analyze the phenomenon of overtraining in backpropagation networks. Overtraining refers ...