This chapter aims to further explore the capabilities of the Higher Order Neural Networks class and especially the Pi-Sigma Neural Networks. The performance of Pi-Sigma Networks is evaluated through several well known neural network training benchmarks. In the experiments reported here, Distributed Evolutionary Algorithms are implemented for Pi-Sigma neural networks training. More specifically,...

In this paper, we study the class of Higher-Order Neural Networks and especially the Pi-Sigma Networks. The performance of Pi-Sigma Networks is evaluated through several well known Neural Network Training benchmarks. In the experiments reported here, Distributed Evolutionary Algorithms are implemented for Pi-Sigma neural networks training. More specifically the distributed versions of the Diffe...

This paper proposes and demonstrates a framework for Sigma-Pi networks such that the combinatorial increase in product terms is avoided. This is achieved by only implementing a subset of the possible product terms (sub-net Sigma-Pi). Application of a dynamic weight pruning algorithm enables redundant weights to be removed and replaced during the learning process, hence permitting access to a la...

Sigma-Pi-Sigma neural networks (SPSNNs) as a kind of high-order neural networks can provide more powerful mapping capability than the traditional feedforward neural networks (Sigma-Sigma neural networks). In the existing literature, in order to reduce the number of the Pi nodes in the Pi layer, a special multinomial Ps is used in SPSNNs. Each monomial in Ps is linear with respect to each partic...

We study the pole properties of $\Lambda(1405)$ in a model-independent manner by applying Uniformized Mittag-Leffler expansion proposed our previous paper. The resonant energy, width and residues are determined expanding observable as sum resonant-pole pairs under an appropriate parameterization which expresses to be single-valued, fitting it experimental data invariant-mass distribution $\pi^+...

Abstract Using electron-positron annihilation data samples corresponding to an integrated luminosity of 4.5 fb , collected by the BESIII detector in energy region between 4599.53\; \,{\rm{MeV}} and 4698.82\; we report first observations Cabibbo-suppressed decays \Lambda_c^+\to n\pi^+\pi^0 n\pi^+\pi^-\pi^+ Cabibbo-favored decay nK^-\pi^+\pi^+ with statistical significances 7....

We reported a new way for estimating filtration variables: K(filtration coefficient), Ppmv (perimicrovascular pressure) and sigma (protein reflection coefficient), from 3 different measurements of weight gain at two protein concentrations of perfusate (Cmv) and at two vascular pressures (Pvasc). We used the Starling equation for calculating those variables using two different formulas which exp...