Vol 25, No 3 (2016)
- Year: 2016
- Articles: 9
- URL: https://journals.rcsi.science/1060-992X/issue/view/12236
Article
The nature of unsupervised learning in deep neural networks: A new understanding and novel approach
Abstract
Over the last decade, the deep neural networks are a hot topic in machine learning. It is breakthrough technology in processing images, video, speech, text and audio. Deep neural network permits us to overcome some limitations of a shallow neural network due to its deep architecture. In this paper we investigate the nature of unsupervised learning in restricted Boltzmann machine. We have proved that maximization of the log-likelihood input data distribution of restricted Boltzmann machine is equivalent to minimizing the cross-entropy and to special case of minimizing the mean squared error. Thus the nature of unsupervised learning is invariant to different training criteria. As a result we propose a new technique called “REBA” for the unsupervised training of deep neural networks. In contrast to Hinton’s conventional approach to the learning of restricted Boltzmann machine, which is based on linear nature of training rule, the proposed technique is founded on nonlinear training rule. We have shown that the classical equations for RBM learning are a special case of the proposed technique. As a result the proposed approach is more universal in contrast to the traditional energy-based model. We demonstrate the performance of the REBA technique using wellknown benchmark problem. The main contribution of this paper is a novel view and new understanding of an unsupervised learning in deep neural networks.
Training with noise as a method to increase noise resilience of neural network solution of inverse problems
Abstract
Inverse problems constitute a special class of problems, which consist in reconstruction of parameters of an object by the data of indirect measurements, which are affected by these parameters. Many inverse problems are ill-posed (incorrect), i.e., characterized by nonuniqueness and/or instability of the solution. Improvement in the stability of the solution of inverse problems is a very topical problem; one of the ways to solve it is the use of artificial neural networks. In the present study, at the example of a model 5-parameter inverse problem it is demonstrated that adding noise to the training set when training neural networks allows one to improve resilience of the neural network solution to noise in input data, with various distribution and intensity of noise.
Comparative analysis of optical 2D codes using (n, w, λa, λc) optical orthogonal codes for optical CDMA
Abstract
Hybrid two dimensional (2D) wavelength-hopping time-spreading coding techniques have been focused now days for Optical Code Division Multiple Access (OCDMA) systems to increase the capacity of system. In this paper, design and comparative analysis of five different 2D coding techniques has been performed. These codes use Synchronized Quadratic Congruence sequences (SQC), Prime Code sequences (PC), Synchronized Prime Sequences (SPS) and One-Coincidence Frequency Hopping Code (OCFHC) for wavelength hopping and (n, w, λa, λc) one dimensional optical orthogonal codes for time spreading respectively along with Extended Reed Solomon (E-RS) codes. It has been observed that SQC/OOC code inspite of having larger value of cross correlation than other codes under consideration, out performs due to its ability to support a larger code weight. The comparison on the basis of BER shows that irrespective of the increase in number of hits due to higher code weight, SQC/OOC provides better code performance and hence supports large number of users in the system. The results are reported on the basis of maximum auto- and cross correlation function, cardinality and bit error rate (BER).
A technique for optimizing the structure of an optical trap to rotate multiple microobjects
Abstract
We discuss a technique for designing diffractive optical elements (DOE) that generate vortex beam superposition with a desired number and configuration of optical traps. Several modifications of the approach are proposed. Some configurations of the DOE-aided optical trap arrays with a predetermined pattern of intensity minima and maxima for trapping transparent and opaque microobjects are calculated. Results of a real experiment on optically trapping, rotating, and displacing in a controlled manner multiple microparticles in the optical beam generated by the designed DOE have been reported.
Development and investigation of a hierarchical compression algorithm for storing hyperspectral images
Abstract
The characteristics of SpecTIR and AVIRIS 16-bit hyperspectral images are analyzed. The requirements for compression of such images are formulated. The aspects of using the hierarchical compression algorithm in hyperspectral images storage are studied. Spectral component approximation algorithms are considered that allow both an increased compression ratio and retrieval of particular components. Interpolation algorithms are considered and a rank interpolator is offered for hyperspectral images compression. Real 16-bit hyperspectral images are used in computational experiments to investigate the efficiency of the proposed algorithms. The best parameters of these algorithms are found experimentally and general recommendations on how to tune the proposed hierarchical compression algorithm to suit hyperspectral images storage problems are given.
Paradoxical images and counterintuitive technical solutions in holography in the context of civil projects
Abstract
The results in the sphere of innovative developments concerning specific holographic optical elements are summarized. They are unrivalled in the classical optics and can be implemented only through holographic technologies. Their common feature is creation of specific wafefronts for recording holograms used in civil devices.
Calculation of regularization parameter in the problem of blur removal in digital image
Abstract
The use of special digital image processing for removal of the blur which results quite often from a mutual relative motion of the optical sensor and object during the exposure is considered. The problem of blur removal from a digital image belongs to the class of incorrect problems, which means that it is impossible to obtain an exact solution resistant to small perturbations in the input data. Therefore, special methods should be invoked. The use of the Tikhonov regularization methods for solving the problem of blur removal from a digital image is demonstrated.
Optical analysis of aortic implants
Abstract
This work presents the results of experimental studies of aortic implants using Raman spectroscopy method (RS). The features of Raman spectra of aortic implants, made by two different protocols, were obtained. Were introduced optical coefficients that allow to monitor the content of main components in aortic implants during manufacturing process and to assess the quality of their processing.
Universal energy consumption forecasting system based on neural network ensemble
Abstract
Problems of neural network forecasting system, invariant to type of energy consumption schedule are solved. Minimum length input vector structure is explained; neural network ensemble structures are determined; selection of the most effective neural network types in the ensemble is held. Original three-level structure of neural network ensemble is developed. Its high forecasting capability makes network perspective for solving information statistical analysis problems.