in this paper, the artificial neural network (ann) approach is applied for forecasting groundwater level fluctuation in aghili plain,southwest iran. an optimal design is completed for the two hidden layers with four different algorithms: gradient descent withmomentum (gdm), levenberg marquardt (lm), resilient back propagation (rp), and scaled conjugate gradient (scg). rain,evaporation, relative...

We establish connections between the problem of learning a two-layers neural network with good generalization error and tensor decomposition. We consider a model with input x ∈ R, r hidden units with weights {wi}1≤i≤r and output y ∈ R, i.e., y = ∑r i=1 σ(〈x,wi〉), where 〈·, ·〉 denotes the scalar product and σ the activation function. First, we show that, if we cannot learn the weights {wi}1≤i≤r ...

Anisotropy in the mechanical response of materials with microstructure is common and yet difficult to assess model. To construct accurate models given only stress-strain data, we employ classical representation theory, novel neural network layers, L1 regularization. The proposed tensor-basis can discover both type orientation anisotropy provide an model stress response. method demonstrated data...

This paper proposes a new architecture — Attentive Tensor Product Learning (ATPL) — to represent grammatical structures in deep learning models. ATPL is a new architecture to bridge this gap by exploiting Tensor Product Representations (TPR), a structured neural-symbolic model developed in cognitive science, aiming to integrate deep learning with explicit language structures and rules. The key ...

To date, most convolutional neural network architectures output predictions by flattening 3rd-order activation tensors, and applying fully-connected output layers. This approach has two drawbacks: (i) we lose rich, multi-modal structure during the flattening process and (ii) fully-connected layers require many parameters. We present the first attempt to circumvent these issues by expressing the...

information on nitrate in groundwater resources requires periodic measurements are accurate. despite the measure in some areas due to sensitive social and health community are not reported. therefore, be informed of the status of each area of water quality, modeling is essential. the purpose of this study was the application of artificial neural network method for estimating nitrate and compare...

in this paper, a recurrent fuzzy-neural network (rfnn) controller with neural network identifier in direct control model is designed to control the speed and exhaust temperature of the gas turbine in a combined cycle power plant. since the turbine operation in combined cycle unit is considered, speed and exhaust temperature of the gas turbine should be simultaneously controlled by fuel command ...