-
Chapter and Conference Paper
On Speeding up the Levenberg-Marquardt Learning Algorithm
A new approach to the practical realizations of calculations to the Levenberg-Marquardt learning algorithm is presented. The proposed solutions aim to effectively reduce the high computational load of the LM a...
-
Chapter and Conference Paper
A Fast Learning Algorithm for the Multi-layer Neural Network
In this paper, the computational improvement for the scaled Givens rotation-based training algorithms is presented. Application of the scaled rotations boosts the algorithm significantly due to the elimination...
-
Chapter and Conference Paper
A Novel Approach to the GQR Algorithm for Neural Networks Training
In this paper, a novel approach to the GQR algorithm is presented. The idea revolves around batch training for the feedforward neural networks. The core of this paper contains a mathematical explanation for th...
-
Chapter and Conference Paper
A New Computational Approach to the Levenberg-Marquardt Learning Algorithm
A new parallel computational approach to the Levenberg-Marquardt learning algorithm is presented. The proposed solution is based on the AVX instructions to effectively reduce the high computational load of thi...
-
Chapter and Conference Paper
A New Variant of the GQR Algorithm for Feedforward Neural Networks Training
This paper presents an application of the scaled Givens rotations in the process of feedforward artificial neural networks training. This method bases on the QR decomposition. The paper describes mathematical ...
-
Chapter and Conference Paper
Modification of Learning Feedforward Neural Networks with the BP Method
The backpropagation (BP) algorithm is a worldwide used method for learning neural networks. The BP has a low computational load. Unfortunately, this method converges relatively slowly. In this paper a new appr...
-
Chapter and Conference Paper
Fast Conjugate Gradient Algorithm for Feedforward Neural Networks
The conjugate gradient (CG) algorithm is a method for learning neural networks. The highest computational load in this method is directional minimization. In this paper a new modification of the conjugate grad...
-
Chapter and Conference Paper
A New Algorithm with a Line Search for Feedforward Neural Networks Training
A new algorithm for feedforward neural networks training is presented. Its core is based on the Givens rotations and QR decomposition (GQR) with an application of a line search method. Similar algorithms based...
-
Chapter and Conference Paper
Realizations of the Statistical Reconstruction Method Based on the Continuous-to-Continuous Data Model
The presented paper describes a successfully parallel implementation of the statistical reconstruction method based on the continuous-to-continuous model using both CPU and GPU hardware approaches. Data were o...
-
Chapter and Conference Paper
Modifications of the Givens Training Algorithm for Artificial Neural Networks
The Givens algorithm is a supervised training method for neural networks. This paper presents several optimization techniques that could be applied on the top of the Givens algorithm. First, the classic varian...
-
Chapter and Conference Paper
The Parallel Modification to the Levenberg-Marquardt Algorithm
The paper presents a parallel approach to the Levenberg-Marquardt algorithm (also called LM or LMA). The first section contains the mathematical basics of the classic LMA. Then the parallel modification to LMA...
-
Chapter and Conference Paper
Parallel Realizations of the Iterative Statistical Reconstruction Algorithm for 3D Computed Tomography
The presented paper describes a parallel realization of an approach to the reconstruction problem for 3D spiral x-ray tomography. The reconstruction problem is formulated taking into consideration the statisti...
-
Chapter and Conference Paper
Parallel Levenberg-Marquardt Algorithm Without Error Backpropagation
This paper presents a new parallel architecture of the Leven-berg-Marquardt (LM) algorithm for training fully connected feedforward neural networks, which will also work for MLP but some cells will stay empty....
-
Chapter and Conference Paper
Parallel Implementation of the Givens Rotations in the Neural Network Learning Algorithm
The paper describes a parallel feed-forward neural network training algorithm based on the QR decomposition with the use of the Givens rotation. The beginning brings a brief mathematical background on Givens r...
-
Chapter and Conference Paper
Application of the Givens Rotations in the Neural Network Learning Algorithm
This paper presents application of Givens rotations in the process of learning feedforward artificial neural network. This approach is based on QR decomposition. The paper describes mathematical background tha...
-
Chapter and Conference Paper
A New Proposition of the Activation Function for Significant Improvement of Neural Networks Performance
An activation function is a very important part of an artificial neuron model. Multilayer neural networks can properly work only when these functions are nonlinear. A simple approximation of an often applied h...
-
Chapter and Conference Paper
Parallel Learning of Feedforward Neural Networks Without Error Backpropagation
A parallel architecture of the steepest descent algorithm for training fully connected feedforward neural networks is presented. This solution is based on a new idea of learning neural networks without error b...
-
Chapter and Conference Paper
Parallel Approach to the Levenberg-Marquardt Learning Algorithm for Feedforward Neural Networks
A parallel architecture of the Levenberg-Marquardt algorithm for training a feedforward neural network is presented. The proposed solution is based on completely new parallel structures to effectively reduce h...
-
Chapter and Conference Paper
The Parallel Approach to the Conjugate Gradient Learning Algorithm for the Feedforward Neural Networks
This paper presents the parallel architecture of the conjugate gradient learning algorithm for the feedforward neural networks. The proposed solution is based on the high parallel structures to speed up learni...
-
Chapter and Conference Paper
Parallel Approach to Learning of the Recurrent Jordan Neural Network
This paper presents the parallel architecture of the Jordan network learning algorithm. The proposed solution is based on the high parallel three dimensional structures to speed up learning performance. Detail...
