Using recurrent neural networks for adaptive communication channelequalization

Nonlinear adaptive filters based on a variety of neural network models have been used successfully for system identification and noise-cancellation in a wide class of applications. An important problem in data communications is that of channel equalization, i.e., the removal of interferences introduced by linear or nonlinear message corrupting mechanisms, so that the originally transmitted symbols can be recovered correctly at the receiver. In this paper we introduce an adaptive recurrent neural network (RNN) based equalizer whose small size and high performance makes it suitable for high-speed channel equalization. We propose RNN based structures for both trained adaptation and blind equalization, and we evaluate their performance via extensive simulations for a variety of signal modulations and communication channel models. It is shown that the RNN equalizers have comparable performance with traditional linear filter based equalizers when the channel interferences are relatively mild, and that they outperform them by several orders of magnitude when either the channel's transfer function has spectral nulls or severe nonlinear distortion is present. In addition, the small-size RNN equalizers, being essentially generalized IIR filters, are shown to outperform multilayer perceptron equalizers of larger computational complexity in linear and nonlinear channel equalization cases.     

Connectivity and performance tradeoffs in the cascade correlationlearning architecture

The cascade correlation is a very flexible, efficient and fast algorithm for supervised learning. It incrementally builds the network by adding hidden units one at a time, until the desired input/output mapping is achieved. It connects all the previously installed units to the new unit being added. Consequently, each new unit in effect adds a new layer and the fan-in of the hidden and output units keeps on increasing as more units get added. The resulting structure could be hard to implement in VLSI, because the connections are irregular and the fan-in is unbounded. Moreover, the depth or the propagation delay through the resulting network is directly proportional to the number of units and can be excessive. We have modified the algorithm to generate networks with restricted fan-in and small depth (propagation delay) by controlling the connectivity. Our results reveal that there is a tradeoff between connectivity and other performance attributes like depth, total number of independent parameters, and learning time.     

MEETING THE IT CHALLENGES OF BUSINESS The Changing Mandate for MBAs

What is the implication for business when information technology (IT) changes in the workplace without a commensurate change in the composition of business programs educating tomorrow's employees? A survey of MBA graduates forms the basis of this article on the IT skills needed in the marketplace.     

Approximation of the optimal-time problem for controlled differential inclusions

Translated from Kibernetika i Sistemnyi Analiz, No. 3, pp. 172–176, May–June, 1994     

Suitable fixation condition for rat liver using microwave irradiation and its application to the immunohistochemistry of glutamate dehydrogenase

In 50 patients auditory threshold and brain stem evoked potential studies were carried out before and after myelography. Due to the analysis of amplitudes and latencies of auditory brain stem measurements, significant functional disorders of the hearing organ and the auditory pathway could be demonstrated. In most of the patients these functional disorders were found to be subclinical, whereas 12 patients showed alterations extending from a subjectively slight hearing loss to an audiometrically objectified acute hearing loss depending on its intensity in each case. The reasons of these functional disorders could not be clarified. An open cochlear aqueduct through which perilymph enters the subarachnoidal space leading to a secondary endolymphatic hydrops can be considered as the cause in cases where manifest symptoms develop. The changes in brain stem audiometry can be additionally explained by changes in osmolality of the inner ear fluids which may lead to the development of an endolymphatic hydrops.     

Modified surface-active monomers for adhesive bonding to dentin

PMGDM, a PMDM-type adhesive monomer, was synthesized from pyromellitic dianhydride and glycerol dimethacrylate. Only the para isomer of PMDM, a solid, is used in dental adhesives. The adhesive monomer PMGDM is a liquid and consists of a mixture of para- and meta isomers. This study shows that PMGDM has several advantages over PMDM. For example, the adhesive can be applied at a greater thickness, and additives and/or additional initiators for improved curing can be incorporated. Use of the liquid monomer PMGDM also provided a convenient means of varying the thickness of the adhesive layer between dentin and composite. The adhesive bonds were tested in both shear and tensile modes. PMDM was used as the control. The reliability of the bonds, as judged from the Weibull modulus and Weibull characteristic strength, was improved by (1) use of more concentrated solutions of PMGDM adhesive, (2) use of an adhesive thickness of about 25 microns, and (3) modification of PMGDM with a diluent monomer which is expected to enhance the degree of cure and/or the dentin-wetting properties of the adhesive resin.