Bounds on the number of samples needed for neural learning.

The relationship between the number of hidden nodes in a neural network, the complexity of a multiclass discrimination problem, and the number of samples needed for effect learning are discussed. Bounds for the number of samples needed for effect learning are given. It is shown that Omega(min (d,n) M) boundary samples are required for successful classification of M clusters of samples using a two-hidden-layer neural network with d-dimensional inputs and n nodes in the first hidden layer.     

K-winner networks.

A special class of mutually inhibitory networks is analyzed, and parameters for reliable K-winner performance are presented. The network dynamics are modeled using interactive activation, and results are compared with the sigmoid model. For equal external inputs, network parameters that select the units with the larger initial activations (the network converges to the nearest stable state) are derived. Conversely, for equal initial activations, networks that select the units with larger external inputs (the network converges to the lowest energy stable state) are derived. When initial activations are mixed with external inputs, anomalous behavior results. These discrepancies are analyzed with several examples. Restrictions on initial states are derived which ensure accurate K-winner performance when unequal external inputs are used.     

Intelligent identification and control for autonomous guided vehicles using adaptive fuzzy-based algorithms

Fuzzy logic was first suggested as the mechanism by which humans drive cars. This paper addresses the use of fuzzy logic and algorithms towards the intelligent autonomous motion control of land vehicles. To cope with vehicle complexities, internal parametric changes, and with unpredictable environmental effects, the controllers that are presented, whilst heuristic in nature, are self-organizing or self-learning in that they generate automatically by observation an experiential rule base that models the vehicle, and via an appropriate performance index an optimal control rule base that is robust to large parametric changes. The methodology presented is applicable to any complex process which is too difficult to model or control using conventional methods, or which has relied on the experience of a human operator. An overview of fuzzy logic and static fuzzy logic control (akin to expert systems) is provided, together with illustrative examples.     

Making99Mo in reactors

Conclusions This comparison of two ways of making⁹⁹Mo shows that there is good scope for making it in any area. If there is a thermal reactor having a high flux, one can make⁹⁹Mo from⁹⁸Mo, and in that case, even irradiation in a high flux makes it favorable to use highly enriched⁹⁸Mo and unblocked targets, which raises the specific activity and thus increases the working life in the^99mTc generator.If there is a thermal reactor with low flux or if there is a fast reactor it is best to make⁹⁹Mo from uranium fission products. The target can be highly enriched²³⁵U, which if necessary can be reused, or low-enriched uranium.There are no essential constraints on making⁹⁹Mo, and the production is mainly based on technological tasks.Translated from Atomnaya Énergiya, Vol. 67, No. 2, pp. 104–108, August, 1989.     

Comparing VVR-M reactor fuel assembly heat technological capabilities

Translated from Atomnaya Énergiya, Vol. 67, No. 2, pp. 97–100, August, 1989.     

Tube-shaping unit — A way of improving the quality of shaped tubes

Lenin Dnepropetrovsk Pipe Plant. Translated from Metallurg, No. 8, p. 39, August, 1989.     

General formalism for the study of nonlinear pulse propagation in optical fibres

A general formalism for the study of nonlinear pulse propagation in optical fibres is presented. It is then applied to study the time evolution of a Gaussian laser pulse in a fibre with cubic and fifth-order nonlinearity in the index of refraction. The results are presented and discussed.