The conference materials contain 213 papers. The following topics are dealt with: vision and image processing;neuralnetwork algorithms;enterprise modeling and simulation;knowledge-based systems;telerobotics;decision-...
详细信息
ISBN:
(纸本)0879425970
The conference materials contain 213 papers. The following topics are dealt with: vision and image processing;neuralnetwork algorithms;enterprise modeling and simulation;knowledge-based systems;telerobotics;decision-support systems;adaptive and learning systems;knowledge engineering frameworks;autonomous systems;telecommunications;cognitive modeling and learning systems;team coordination and decision making;fuzzy logic theory and applications;automation in manned systems;software internationalization;human-computer cooperation;manual control;neuralnetwork vision;concurrent engineering and manufacturing systems;robotic systems;visual programming and advanced user interfaces;neuralnetwork hardware;computer-aided systems engineering;AI for space applications;adaptation;cognitive modeling and human-computer integration;enterprise modeling and simulation;expert decision systems;team performance and distributed problem solving;biological cybernetics.
Based on the assumption that most probability densities in real life can be approximated by a mixture of Gaussian densities, the authors propose a set of algorithms for training a multilayered perceptron as a parallel...
详细信息
ISBN:
(纸本)0879425563
Based on the assumption that most probability densities in real life can be approximated by a mixture of Gaussian densities, the authors propose a set of algorithms for training a multilayered perceptron as a parallel distributedprocessingnetwork (PDP) to estimate various probability densities and serve as a Bayes classifier. The effectiveness of a PDP density estimator was measured in terms of the relative difference between the target probability density function and the network output representing the estimation. The classification rate of the PDP network was effectively identical to that of the Bayes classifier.
Two conditions for reducing the number of learning iterations in back-propagation artificial neuralnetworks are introduced. The first condition is to scale the target output so that it falls within a small range (...
详细信息
Two conditions for reducing the number of learning iterations in back-propagation artificial neuralnetworks are introduced. The first condition is to scale the target output so that it falls within a small range (±0.1) of the point at which the slope of the nonlinear activation function of the output node is maximum. This point is 0.5 for the sigmoid function. The second condition is to learn the input patterns selectively, not sequentially, until the error is reduced below the desired limit. Introducing the techniques does not affect the memory retention or generalization capabilities of such networks. The application of these concepts to the classical XOR learning algorithm problem resulted in a reduction in the number of learning iterations by a factor of 7 over the results published by D. E. Rumelhart et al. (Parallel distributedprocessing, vol. 1, chap. 8, Cambridge, MIT Press).
NN (neuralnetwork) controller characteristics are clarified by comparison with the adaptive control theory. The authors explain the classification of the NN controller architecture and the dynamic NN structure. A com...
详细信息
ISBN:
(纸本)0818620617
NN (neuralnetwork) controller characteristics are clarified by comparison with the adaptive control theory. The authors explain the classification of the NN controller architecture and the dynamic NN structure. A comparison between the NN controller and the adaptive controller shows that the framework of a linear two-layer NN controller is the same as that of the adaptive controller, and that the nonlinear three-layer NN (PDP, or parallel distributedprocessing type) is a nonlinear extension of the adaptive control. The stability characteristics of the NN control system, which shows the robustness effect of the generalized delta rule, the plant and the NN mapping function, are treated. Finally, NN controller experiments are demonstrated using a force control servomechanism. Experimental results suggest that the nonlinear sigmoid function of the NN can compensate for the nonlinear plant effect.
A three-layer neuralnetwork is trained to perform spectral estimation. Excellent performance is found through computer simulations. When compared with an equivalent length radix-2 fast Fourier transform, the neural n...
详细信息
A three-layer neuralnetwork is trained to perform spectral estimation. Excellent performance is found through computer simulations. When compared with an equivalent length radix-2 fast Fourier transform, the neuralnetwork has the following advantages: (1) the neuralnetwork can suppress the signal magnitude in sidelobes without widening the mainlobe; (2) the neuralnetwork completes its computation in two stages regardless of the number of input signal samples; (3) the number of input signal samples does not need to be an integer power of two; and (4) the neuralnetwork still generates valid results even if there are 25% broken interconnects uniformly distributed between the output layer and the hidden layer or between the hidden layer and the input layer. An application example of using a three-layer neuralnetwork for moving target detection is also included.< >
Based on the strong analogy between neuralnetworks and distributed diagnosis models, diagnostic algorithms are presented which are similar to the learning algorithm used in neuralnetworks. Diagnostic implications of...
Based on the strong analogy between neuralnetworks and distributed diagnosis models, diagnostic algorithms are presented which are similar to the learning algorithm used in neuralnetworks. Diagnostic implications of convergence theorems proved by the Lyapunov function are also discussed. Regarding diagnosis process as a recalling process in the associative memory, a diagnostic method of associative diagnosis is also presented. A good guess of diagnosis is given as a key to recalling the correct diagnosis. The authors regard the distributed diagnosis as an immune network model, a novel PDP (parallel distributedprocessing) model. This models the recognition capability emergent from cooperative recognition of interconnected units
The application of parallel distributedprocessing (neuralnetworks) to the problem of adaptive control is examined. Focusing on the backpropagation paradigm, a general form of a controller consistent with neural netw...
The application of parallel distributedprocessing (neuralnetworks) to the problem of adaptive control is examined. Focusing on the backpropagation paradigm, a general form of a controller consistent with neuralnetworks is developed and combined with linear least-squares parameter-estimation techniques to suggest a structure for neuralnetwork adaptive controllers. This neuralnetwork adaptive control structure is then applied to a number of estimation problems using the longitudinal motion of the A-4 aircraft as a model
It is shown that firing intervals in a temporal-coded spike train can be decoded by a multilayered time-delayed neuralnetwork. The serially coded firing intervals of a spike train can be converted into a spatially di...
It is shown that firing intervals in a temporal-coded spike train can be decoded by a multilayered time-delayed neuralnetwork. The serially coded firing intervals of a spike train can be converted into a spatially distributed topographical map from which the interspike-interval and bandwidth information can be extracted. This network can be used to decode multiplexed pulse-coded signals embedded serially in the incoming spike train into parallel-distributed topographically mapped channels. The two-dimensionally distributed output neuron array can also be used to extract the variance (or inaccuracy) tolerance of the incoming firing interspike intervals. This mapping can also be used to characterize the underlying stochastic processes in the firing of the incoming spike train. Thus, the proposed network represents an implementation of a signal-processing scheme for code conversion using time for computing and coding that does not require learning
Based on the assumption that most probability densities in real life can be approximated by a mixture of Gaussian densities, the authors propose a set of algorithms for training a multilayered perceptron as a parallel...
详细信息
Based on the assumption that most probability densities in real life can be approximated by a mixture of Gaussian densities, the authors propose a set of algorithms for training a multilayered perceptron as a parallel distributedprocessingnetwork (PDP) to estimate various probability densities and serve as a Bayes classifier. The effectiveness of a PDP density estimator was measured in terms of the relative difference between the target probability density function and the network output representing the estimation. The classification rate of the PDP network was effectively identical to that of the Bayes classifier.< >
Highly interconnected networks of relatively simple processing elements are shown to be very effective in solving difficult optimization problems. Problems that fall into the broad category of finding a least-cost pat...
Highly interconnected networks of relatively simple processing elements are shown to be very effective in solving difficult optimization problems. Problems that fall into the broad category of finding a least-cost path between two points, given a distributed and sometimes complex cost map, are studied. A neurallike architecture and associated computational rules are proposed for the solution of this class of optimal path-finding problems in two- and higher-dimensional spaces. The proposed algorithm is local in nature and is very well suited for highly parallel, fine-grained, and distributed architectures. Also described is a collective multilayer neurallike architecture, characterized by speed of convergence, scalability, and guaranteed convergence to optimal solutions
暂无评论