Abstract To solve the problems of whale optimization algorithm (WOA) with slow convergence speed, low accuracy, and poor global search ability, a multistrategy hybrid adaptive (MHWOA) was proposed. In this algorithm, logistic–tent chaos used to initialize population, which could make population distribution more random uniform. The opposition-based learning strategy adopted expand individuals c...

INTRODUCTION Malaria is endemic in the Brazilian Amazon region, with different risks for each region. The City of Cantá, State of Roraima, presented one of the largest annual parasite indices in Brazil for the entire study period, with a value always greater than 50. The present study aimed to use an artificial neural network to predict the incidence of malaria in this city in order to assist h...

We study the power of deep neural networks (DNNs) with sigmoid activation function. Recently, it was shown that DNNs approximate any d-dimensional, smooth function on a compact set rate order W?p?d, where W is number nonzero weights in network and p smoothness Unfortunately, these rates only hold for special class sparsely connected DNNs. ask ourselves if we can show same approximation simpler ...

The objective of this study was to evaluate the growth curve 525 monthly body weight data 19 males (n=313) and 8 females (n=212) swamp buffaloes (Bubalus b. carabanensis), from birth slaughter age (25 months). nonlinear models used were: logistic, Gompertz, Von Bertalanffy Brody. parameters were estimated by NLIN procedure, criteria adjustment given Akaike’s information criterion (AIC), Bayesia...

Among deciduous species, the peach tree (Prunus persica [L.] Batsch.) is of great importance in high tropics. However, growth behavior this fruit for different cultivated varieties unknown. So, adjustment to double sigmoid curves assumed all even though type have been reported many cultivar. This has led misinterpretation information, impeding decision-making terms management. Non-linear regres...

This paper examines the circuit complexity of feedforward neural networks having sigmoid activation function. The starting point is the complexity class NN defined in [18]. First two additional complexity classes NN∆ k and NN∆,ε k having less restrictive conditions (than NN) concerning fan-in and accuracy are defined. We then prove several relations among these three classes and well establishe...

We describe a general technique for estimating the intractable quantities that occur in a wide variety of largescale probabilistic models. The technique transforms intractable sums into integrals which are subsequently approximated via saddle point methods. When applied to sigmoid and noisy-OR networks, the technique yields a generic mean-field approximation as well as a second order Gaussian a...

It is demonstrated that any realistic model of quintessence should be based on Supergravity since, when the scalar field is on tracks today, Q ≈ m Pl. This improves the agreement between theoretical predictions and the current observations. In particular, a generic property is that ratio ωQ ≡ pQ/ρQ is pushed towards −1. A string-inspired model is proposed where the potential is given by V (Q) =...

Phone verification approach to mispronunciation detection using a combination of Neural Network (NN) and Support Vector Machine (SVM) has been shown to yield improved verification performance. This approach uses a NN to predict the HMM state posterior probabilities. The average posterior probability vectors computed over each phone segment are used as input features to a SVM back-end to generat...

-An array of sigmoidal tension gashes from the Idaho-Wyoming thrust belt changes laterally into a continuous vein. Detailed mechanical twin analysis was used to determine the strain variation in the optically and chemically homogeneous blocky calcite filling. In the continuous portion of the vein complex, the shortening axes are parallel to the vein boundary. However, the orientation of the sho...