Book chapter
Tensorizing neural networks
Deep neural networks currently demonstrate state-of-the-art performance in several domains.At the same time, models of this class are very demanding in terms of computational resources. In particular, a large amount of memory is required by commonly used fully-connected layers, making it hard to use the models on low-end devices and stopping the further increase of the model size. In this paper we convert the dense weight matrices of the fully-connected layers to the Tensor Train format such that the number of parameters is reduced by a huge factor and at the same time the expressive power of the layer is preserved.In particular, for the Very Deep VGG networks we report the compression factor of the dense weight matrix of a fully-connected layer up to 200000 times leading to the compression factor of the whole network up to 7 times.
In book
The issues of information support based on the use of artifical neural networks for the rapid recognition of odors using devices such as "elecronic nose" are considered. The variants the reducing the test sampl for an artifical neural network are proposed with the aim of increasing the stabilutyof computatijns and the speed of calculations. A method for the rapid recognition of odors in the presence of background odors is proposed.
This article discusses the features of the spatial processes of fast and accurate positioning
of points on the external surface of the object using the manipulation robot when executing
the sequence of technical operations. Considered, pregenerating digital models of the
external surfaces of the object. The quality of obtaining the coordinates of the points of
an object's surface, determines the accuracy of positioning the surface of an object in the
working zone. Simulation of positioning the moving points on the surface of the body in
the working zone of a robotic system to capture the object is determined relative to a
fixed point of another object, with respect to which positioning is to perform technical
operation. When it is not sufficiently accurate and fast positioning then it is required a
new surface model of an object and positioning the technical points on the surface. The
simulation in MATLAB making a conclusion about the possibility of application of fuzzy
controller for fast and accurate correction values of a small deviations from the coordinates
of selected technical points of the surface of an object in the given vectors in its orientation
and approach to the fixed point of another object.
Nowadays there is a large amount of demographic data which should be analysed and interpreted. From accumulated demographic data, more useful information can be extracted by applying modern methods of data mining. The aim of this study is to compare the methods of classification of demographic data by customizing the SVM kernels using various similarity measures. Since demographers are interested in sequences without discontinuity, formulas for such sequences similarity measures were derived. Then they were used as kernels in the SVM method, which is the novelty of this study. Recurrent neural network algorithms, such as SimpleRNN, GRU and LSTM, are also compared. The best classification result with SVM method is obtained using a special kernel function in SVM by transforming sequences into features, but recurrent neural network outperforms SVM.
The issues of information support based on the use of artifical neural networks for the rapid recognition of odors using devices such as "elecronic nose" are considered. The variants the reducing the test sampl for an artifical neural network are proposed with the aim of increasing the stabilutyof computatijns and the speed of calculations. A method for the rapid recognition of odors in the presence of background odors is proposed.
This book constitutes the refereed proceedings of the 6th IAPR TC3 International Workshop on Artificial Neural Networks in Pattern Recognition, ANNPR 2014, held in Montreal, QC, Canada, in October 2014. The 24 revised full papers presented were carefully reviewed and selected from 37 submissions for inclusion in this volume. They cover a large range of topics in the field of learning algorithms and architectures and discussing the latest research, results, and ideas in these areas.
The description of technical, methodical and software solutions aimed at creating a measuring device for neural network recognition of a wide class of chemical substances based on semiconductor multisensor matrices.
This book constitutes the proceedings of the 23rd International Symposium on Foundations of Intelligent Systems, ISMIS 2017, held in Warsaw, Poland, in June 2017. The 56 regular and 15 short papers presented in this volume were carefully reviewed and selected from 118 submissions. The papers include both theoretical and practical aspects of machine learning, data mining methods, deep learning, bioinformatics and health informatics, intelligent information systems, knowledge-based systems, mining temporal, spatial and spatio-temporal data, text and Web mining. In addition, four special sessions were organized; namely, Special Session on Big Data Analytics and Stream Data Mining, Special Session on Granular and Soft Clustering for Data Science, Special Session on Knowledge Discovery with Formal Concept Analysis and Related Formalisms, and Special Session devoted to ISMIS 2017 Data Mining Competition on Trading Based on Recommendations, which was launched as a part of the conference.
The medium-term forecasting of the sea ice extent has been carried out by determining of the relationship between incoming solar radiation and the sea ice extent in the Northern Hemisphere. Different methods of the statistic and neural modeling have been used. Forecast shows that the main factor determining the variation of the maximum and minimum sea ice extent in the medium-term scale is the variability of solar radiation arrived at the top of the atmosphere. Evaluation of the medium-term forecasts of the sea ice extent demonstrates the effectiveness of using the averaged results of the regression analysis and neural network modeling.
The first part of the issue gives general information about foreign exchange market (FOREX), review of forecasting foreign exchange rate is given. In addition we will consider the new model of nonlinear analysis to give a broader theoretical basis to the research - an artificial neural network (ANN).The nonlinear analysis and the ANN is still improving, but even now the researchers notice evident advantages of the method.