hidden layer

In networks training, connecting weight variables and hidden layer outputs can be optimized alternately.

This paper proposes a method which can determine the suitable structure in the hidden layer of a neural network.

Input layer performs import of samples, hidden layer extracts model characters of samples and output layer presents classification results.

model beautiful, hidden layer plate structure synchronization performance is excellent.

Yet with little damage the result is relatively low. To resolve the problem, augmenting node of hidden layer or number of hidden layer.

Through the analysis of character features, confirm the input layer, hidden layer and the License of output layer units.

BP neural network topology, including the input layer (input), hidden layer (hide layer) and output layer (output layer).

The selected text is actually contained in a hidden layer, separate from the document image.

First, the usual ways that are employed to choose the number of RBFNN's hidden layer nodes are analyzed and compared.

This is because the only parameters that are adjusted in the learning process are the linear mapping from hidden layer to output layer.

Its hidden layer and output layer are composed of process neuron and the hidden layer function consists of wavelet function.

For the above reasons, the extended Kalman filter is proposed as RBF learning algorithm, and the biradial function is used in hidden layer.

Toggling layer visibility no longer makes a hidden layer active.

This algorithm looks the hidden layer structure as controll gene, and the hidden layer location and width as parameters gene.

This model includes the input layer, hidden layer and output layer.

The key factor that influences the performance of RBFNN is the choice of hidden layer center.

The consequence study of searching the higher order information of atmospheric refraction by the hidden layer units of BP neural network

A Hidden-layer-structure-adaptive Neural Network Used in Underwater Acoustic Target Recognition

An Optimization Algorithm on the Number of Hidden Layer Nodes in Feed-forward Neural Network

Lp Simultaneous Approximation by Neural Networks with One Hidden Layer

The Analysis and Application of Redundancy on Hidden-Layer Neurons Under Universal Faults

Nonlinear System Identification Using BPWA Based Single Hidden-layer Feedforward Neural Networks

Use of trial and error method to determine the hidden layers and the number of hidden layer neurons;

A Hidden Layer Training Algorithm for Three-Layered Feedforward Neural Networks Based on Energy Space Approaching Strategy

Hidden Layer Performance Evaluation for Feedforward Neural Networks Based on Hidden Layer Growing Strategy

Study on Hidden Layer Evaluation for Feed-Forward Neural Networks

Transformers Fault Diagnosis Based on Fuzzy BP Network Using Optimization Algorithm for Hidden Layer Nodes

Research and application of process neural network with two hidden-layer based on expansion of basis function

A hidden layer evaluation method for feedforward neural networks based on subspace analysis

Hidden-layer Redundancy Method of RBF Neural Networks

Optimization of Hidden Layer Units of BP Neural Network

Discussion about Hidden-layer Structure of Electrode Property Prediction System Based on ANN

A BP Neural Network Based on Adjusting Hidden Layer Units