Results 181 to 190 of about 639,551 (228)

The hidden‐layer problem revisited

GEOPHYSICS, 1984
Analysis of refraction seismic data falls into two classes: traditional head‐wave analysis, in which discrete “first arrivals” are mapped in terms of traveltime and distance, and modern waveform analysis, in which the time series recorded at each seismometer is considered in its entirety.
I. J. Won, Michael Bevis
openaire   +1 more source

A step towards the frontier between one-hidden-layer and two-hidden-layer neural networks

Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan), 2005
This paper addresses the exact realization of functions, from the d-dimensional affine space to {0,1}, by feedforward multilayer neural networks of threshold units. A classification of the network architectures, according to their number of hidden layers, points out the difficulty of locating the frontier between dichotomies which can be realized with ...
M. Cosnard, P. Koiran, H. Paugam-Moisy
openaire   +1 more source

THE HIDDEN LAYER PROBLEM

Geophysical Prospecting, 1962
AbstractFor a given refraction time‐distance curve, the range in thickness for a hidden intermediate layer is given together with the effect the layer has on the total thickness of the two layers above the recorded refractor.
openaire   +1 more source

Emotion classification using hidden layer outputs

2012 International Symposium on Innovations in Intelligent Systems and Applications, 2012
Neural network (NN) with Multi-Layer Perceptron (MLP) is a supervised learning algorithm composed of artificial neurons. Multilayer NN is capable of solving nonlinear classification problems such as emotion identification by using facial expressions that is presented in this paper.
Mine Altinay Gunler, Hakan Tora
openaire   +1 more source

Feedback Stabilization Using Two-Hidden-Layer Nets

1991 American Control Conference, 1991
The representational capabilities of one-hidden-layer and two-hidden-layer nets consisting of feedforward interconnections of linear threshold units are compared. It is remarked that for certain problems two hidden layers are required, contrary to what might be in principle expected from the known approximation theorems.
openaire   +2 more sources

The hidden-layer model of hippocampus

Neurocomputing, 2003
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Fellenz, Winfried A., Taylor, John G.
openaire   +1 more source

How many hidden layers and nodes?

International Journal of Remote Sensing, 2009
The question of how many hidden layers and how many hidden nodes should there be always comes up in any classification task of remotely sensed data using neural networks. Until today there has been no exact solution. A method of shedding some light to this question is presented in this paper. A near-optimal solution is discovered after searching with a
openaire   +1 more source

Generalized Single-Hidden Layer Feedforward Networks

2013
In this paper, we propose a novel generalized single-hidden layer feedforward network (GSLFN) by employing polynomial functions of inputs as output weights connecting randomly generated hidden units with corresponding output nodes. The main contributions are as follows.
Ning Wang, Min Han, Guifeng Yu, Meng Joo Er, Fanchao Meng, Shulei Sun   +5 more
openaire   +1 more source

Modular expansion of the hidden layer in Single Layer Feedforward neural Networks

2016 International Joint Conference on Neural Networks (IJCNN), 2016
We present a neural network architecture and a training algorithm designed to enable very rapid training, and that requires low computational processing power, memory and time. The algorithm is based on a modular architecture, which expands the output weights layer constructively, so that the final network can be visualised as a Single Layer ...
Migel D. Tissera, Mark D. McDonnell
openaire   +2 more sources

The hidden layer in seismic prospecting

Geologiska Föreningen i Stockholm Förhandlingar, 1974
Abstract One condition which has to be fulfilled in seismic-refraction prospecting is an increasing velocity distribution. But even if this condition is met, one intermediate layer may pass undetected. When such a situation occurs, with a hidden layer, it can give rise to considerable errors in the depth determination.
openaire   +1 more source