Pareto selection of neural network approximation subject to virtual leave-one-out criteria and application to defect centers identification in semi-insulating materials

2006 ◽  
Author(s):  
Stanislaw Jankowski ◽  
Maciej Ojczyk
Keyword(s):  
Neural Network ◽  
Insulating Materials ◽  
Defect Centers ◽  
Virtual Leave One Out ◽  
Leave One Out ◽  
Selection Of

Selection of Neural Network for Crime Time Series Prediction by Virtual Leave-One-Out Tests

2019 ◽  
pp. 117-133
Author(s):  
Stanisław Jankowski ◽  
Zbigniew Szymański ◽  
Zbigniew Wawrzyniak ◽  
Paweł Cichosz ◽  
Eliza Szczechla ◽  
...  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Time Series Prediction ◽  
Virtual Leave One Out ◽  
Leave One Out ◽  
Selection Of

IMPLEMENTATION OF NEURAL NETWORK METHOD TO INVESTIGATE DEFECT CENTERS IN SEMI-INSULATING MATERIALS

2002 ◽  
Vol 16 (28n29) ◽  
pp. 4449-4454 ◽  
Author(s):  
S. JANKOWSKI ◽  
M. WIERZBOWSKI ◽  
P. KAMINSKI ◽  
M. PAWLOWSKI
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Learning Process ◽  
Two Dimensional ◽  
Insulating Materials ◽  
Arrhenius Plots ◽  
Defect Centers ◽  
Dimensional Approximation ◽  
Network Method ◽  
Transient Spectroscopy

A neural network (NN) method has been proposed as a new algorithm for extraction of defect centers parameters in semi-insulating materials from experimental data obtained by photoinduced transient spectroscopy (PITS). The new algorithm is applied to investigate irradiation-induced defect centers in high resistive silicon. The folds on the PITS spectral surface formed due to the presence of defect levels are best fitted with a two-dimensional approximation function with implementation of the NN learning process. As a result, the Arrhenius plots for defect centers are obtained and the parameters of these centers are determined.

scholarly journals Methods for Preventing Visual Attacks in Convolutional Neural Networks Based on Data Discard and Dimensionality Reduction

2021 ◽  
Vol 11 (11) ◽  
pp. 5235
Author(s):  
Nikita Andriyanov
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Inference ◽  
Recognition Accuracy ◽  
Network Architectures ◽  
Reduced Dimensions ◽  
Different Types ◽  
Rectangular Area ◽  
Noise Impulse ◽  
Selection Of

The article is devoted to the study of convolutional neural network inference in the task of image processing under the influence of visual attacks. Attacks of four different types were considered: simple, involving the addition of white Gaussian noise, impulse action on one pixel of an image, and attacks that change brightness values within a rectangular area. MNIST and Kaggle dogs vs. cats datasets were chosen. Recognition characteristics were obtained for the accuracy, depending on the number of images subjected to attacks and the types of attacks used in the training. The study was based on well-known convolutional neural network architectures used in pattern recognition tasks, such as VGG-16 and Inception_v3. The dependencies of the recognition accuracy on the parameters of visual attacks were obtained. Original methods were proposed to prevent visual attacks. Such methods are based on the selection of “incomprehensible” classes for the recognizer, and their subsequent correction based on neural network inference with reduced image sizes. As a result of applying these methods, gains in the accuracy metric by a factor of 1.3 were obtained after iteration by discarding incomprehensible images, and reducing the amount of uncertainty by 4–5% after iteration by applying the integration of the results of image analyses in reduced dimensions.

scholarly journals Adaptive Control Structure with Neural Data Processing Applied for Electrical Drive with Elastic Shaft

Energies ◽  
2021 ◽  
Vol 14 (12) ◽  
pp. 3389
Author(s):  
Marcin Kamiński ◽  
Krzysztof Szabat
Keyword(s):  
Neural Network ◽  
Adaptive Control ◽  
Dynamic Properties ◽  
Experimental Studies ◽  
Drive System ◽  
Particle Swarm Optimizer ◽  
The Neural Network ◽  
Control Concept ◽  
Constant Coefficients ◽  
Selection Of

This paper presents issues related to the adaptive control of the drive system with an elastic clutch connecting the main motor and the load machine. Firstly, the problems and the main algorithms often implemented for the mentioned object are analyzed. Then, the control concept based on the RNN (recurrent neural network) for the drive system with the flexible coupling is thoroughly described. For this purpose, an adaptive model inspired by the Elman model is selected, which is related to internal feedback in the neural network. The indicated feature improves the processing of dynamic signals. During the design process, for the selection of constant coefficients of the controller, the PSO (particle swarm optimizer) is applied. Moreover, in order to obtain better dynamic properties and improve work in real conditions, one model based on the ADALINE (adaptive linear neuron) is introduced into the structure. Details of the algorithm used for the weights’ adaptation are presented (including stability analysis) to perform the shaft torque signal filtering. The effectiveness of the proposed approach is examined through simulation and experimental studies.

Sign in / Sign up

Export Citation Format

Share Document