A feedforward Sigma-Pi neural network with a single hidden layer of m neurons is given by mSigma(j=1) cjg (nPi(k=1) xk-thetak(j)/lambdak(j)) where cj, thetak(j), lambdak are elements of R. In this paper, we investigate the approximation of arbitrary functions f: Rn-->R by a Sigma-Pi neural network in the Lp norm. An Lp locally integrable function g(t) can approximate any given function, if and ...

− The solving of least square systems is a useful operation in neurocomputational modeling of learning, pattern matching, and pattern recognition. In these last two cases, the solution must be obtained on-line, thus the time required to solve a system in a plausible neural architecture is critical. This paper presents a recurrent network of Sigma-Pi neurons, whose solving time increases at most...

A set of sigma-pi units randomly connected to two input vectors forms a disorganized type of hetero-associative memory related to convolutionand matrix-based associative memories. Associations are represented as patterns of activity rather than connection strengths. Decoding the associations requires another network of sigma-pi units, with connectivity dependent on the encoding network. Learnin...

Using data collected with the CLEO detector operating at the CESR e+e- collider at sqrt[s]=3.97-4.26 GeV, we investigate 15 charmonium decay modes of the psi(4040), psi(4160), and Y(4260) resonances. We confirm, at 11 sigma significance, the BABAR Y(4260)-->pi+pi- J/psi discovery, make the first observation of Y(4260)--> pi(0)pi(0) J/psi (5.1 sigma), and find the first evidence for Y(4260)-->K+...

Electronic structures of trans- and cis-dichloroethylenes and tetrachloroethylene were studied using symmetry-adapted cluster configuration interaction theory. Basis sets up to the aug-cc-pVTZ of Dunning, Jr., augmented with appropriate Rydberg functions were used for the calculations. The results derived in the present study show good agreement with the available experimental values. In all ca...

We report an observation of new bottom baryons produced in pp collisions at the Tevatron. Using 1.1 fb(-1) of data collected by the CDF II detector, we observe four Lambda b 0 pi+/- resonances in the fully reconstructed decay mode Lambda b 0-->Lambda c + pi-, where Lambda c+-->pK* pi+. We interpret these states as the Sigma b(*)+/- baryons and measure the following masses: m Sigma b+=5807.8 -2....

In this contribution, we study the class of Higher-Order Neural Networks, especially Pi-Sigma Networks. The performance of Pi-Sigma Networks is considered through well known neural network training problems. In our experiments, for the training process, we used Evolutionary Algorithms and more specifically the Differential Evolution algorithm. Preliminary results suggest that this training proc...