Pub. online:5 Aug 2022Type:Research ArticleOpen Access
Journal:Informatica
Volume 16, Issue 2 (2005), pp. 159–174
Abstract
The more realistic neural soma and synaptic nonlinear relations and an alternative mean field theory (MFT) approach relevant for strongly interconnected systems as a cortical matter are considered. The general procedure of averaging the quenched random states in the fully-connected networks for MFT, as usually, is based on the Boltzmann Machine learning. But this approach requires an unrealistically large number of samples to provide a reliable performance. We suppose an alternative MFT with deterministic features instead of stochastic nature of searching a solution a set of large number equations. Of course, this alternative theory will not be strictly valid for infinite number of elements. Another property of generalization is an inclusion of the additional member in the effective Hamiltonian allowing to improve the stochastic hill-climbing search of the solution not dropping into local minima of the energy function. Especially, we pay attention to increasing of neural networks retrieval capability transforming the replica-symmetry model by including of different nonlinear elements. Some results of numerical modeling as well as the wide discussion of neural systems storage capacity are presented.
Pub. online:23 Mar 2020Type:Research ArticleOpen Access
Journal:Informatica
Volume 31, Issue 1 (2020), pp. 65–88
Abstract
A large number of modern mobile devices, embedded devices and smart home devices are equipped with a voice control. Automatic recognition of the entire audio stream, however, is undesirable for the reasons of the resource consumption and privacy. Therefore, most of these devices use a voice activation system, whose task is to find the specified in advance word or phrase in the audio stream (for example, Ok, Google) and to activate the voice request processing system when it is found. The voice activation system must have the following properties: high accuracy, ability to work entirely on the device (without using remote servers), consumption of a small amount of resources (primarily CPU and RAM), noise resistance and variability of speech, as well as a small delay between the pronunciation of the key phrase and the system activation. This work is a systematic literature review on voice activation systems that satisfy the above properties. We describe the principle of various voice activation systems’ operation, the characteristic representation of sound in such systems, consider in detail the acoustic modelling and, finally, describe the approaches used to assess the models’ quality. In addition, we point to a number of open questions in this problem.
Journal:Informatica
Volume 25, Issue 3 (2014), pp. 401–414
Abstract
We propose an adaptive inverse control scheme, which employs a neural network for the system identification phase and updates its weights in online mode. The theoretical basis of the method is given and its performance is illustrated by means of its application to different control problems showing that our proposal is able to overcome the problems generated by dynamic nature of the process or by physical changes of the system which originate important modifications in the process. A comparative experimental study is presented in order to show the more stable behavior of the proposed method in several working ranks.
Journal:Informatica
Volume 19, Issue 4 (2008), pp. 477–486
Abstract
In this paper we propose and analyze a multilayer perceptron-like model with matrix inputs. We applied the proposed model to the financial time series prediction problem, compared it with the standard multilayer perceptron model, and got fairly good results.
Journal:Informatica
Volume 18, Issue 2 (2007), pp. 203–216
Abstract
In this paper, the information theory interpreted as the neural network systems of the brain is considered for information conveying and storing. Using the probability theory and specific properties of the neural systems, some foundations are presented. The neural network model proposed and computational experiments allow us to draw a conclusion that such an approach can be applied in storing, coding, and transmission of information.
Journal:Informatica
Volume 18, Issue 1 (2007), pp. 79–102
Abstract
The objective of this research is to construct parallel models that simulate the behavior of artificial neural networks. The type of network that is simulated in this project is the counterpropagation network and the parallel platform used to simulate that network is the message passing interface (MPI). In the next sections the counterpropagation algorithm is presented in its serial as well as its parallel version. For the latter case, simulation results are given for the session parallelization as well as the training set parallelization approach. Regarding possible parallelization of the network structure, there are two different approaches that are presented; one that is based to the concept of the intercommunicator and one that uses remote access operations for the update of the weight tables and the estimation of the mean error for each training stage.
Journal:Informatica
Volume 15, Issue 4 (2004), pp. 551–564
Abstract
Text categorization – the assignment of natural language documents to one or more predefined categories based on their semantic content – is an important component in many information organization and management tasks. Performance of neural networks learning is known to be sensitive to the initial weights and architecture. This paper discusses the use multilayer neural network initialization with decision tree classifier for improving text categorization accuracy. Decision tree from root node until a final leave is used for initialization of each single unit. Growing decision trees with increasingly larger amounts of training data will result in larger decision tree sizes. As a result, the neural networks constructed from these decision trees are often larger and more complex than necessary. Appropriate choice of certainty factor is able to produce trees that are essentially constant in size in the face of increasingly larger training sets. Experimental results support the conclusion that error based pruning can be used to produce appropriately sized trees, which are directly mapped to optimal neural network architecture with good accuracy. The experimental evaluation demonstrates this approach provides better classification accuracy with Reuters‐21578 corpus, one of the standard benchmarks for text categorization tasks. We present results comparing the accuracy of this approach with multilayer neural network initialized with traditional random method and decision tree classifiers.
Journal:Informatica
Volume 15, Issue 3 (2004), pp. 337–362
Abstract
This paper develops a representation of multi‐model based controllers by using artificial intelligence typical structures. These structures will be neural networks, genetic algorithms and fuzzy logic. The interpretation of multimodel controllers in an artificial intelligence frame will allow the application of each specific technique to the design of improved multimodel based controllers. The obtained artificial intelligence based multimodel controllers are compared with classical single model based ones. It is shown through simulation examples that a transient response improvement can be achieved by using multiestimation based techniques. Furthermore, a method for synthesizing multimodel based neural network controllers from already designed single model based ones is presented. The proposed methodology allows to extend the existing single model based neural controllers to multimodel based ones, extending the applicability of this kind of techniques to a more general type of controllers. Also, some applications of genetic algorithms and fuzzy logic to multimodel controller design are proposed. Thus, the mutation operation from genetic algorithms inspires a robustness test which consists of a random modification of the estimates which is used to select the estimates leading to the better identification performance towards parameterizing online the adaptive controller. Such a test is useful for plants operating in a noisy environment. The proposed robustness test improves the selection of the plant model used to parameterize the adaptive controller in comparison to classical multimodel schemes where the controller parameterization choice is basically taken based on the identification accuracy of each model. Moreover, the fuzzy logic approach suggests new ideas to the design of multiestimation structures which can be applied to a broad variety of adaptive controllers such as robotic manipulator controller design.
Journal:Informatica
Volume 14, Issue 1 (2003), pp. 95–110
Abstract
It is a complex non‐linear problem to predict mechanical properties of concrete. As a new approach, the artificial neural networks can extract rules from data, but have difficulties with convergence by the traditional algorithms. The authors defined a new convex function of the grand total error and deduced a global optimization back‐propagation algorithm (GOBPA), which can solve the local minimum problem. For weights' adjustment and errors' computation of the neurons in various layers, a set of formulae are obtained by optimizing the grand total error function over a simple output space instead of a complicated weight space. Concrete strength simulated by neural networks accords with the data of the experiments on concrete, which demonstrates that this method is applicable to concrete properties' prediction meeting the required precision. Computation results show that GOBPA performs better than a linear regression analysis.
Journal:Informatica
Volume 13, Issue 4 (2002), pp. 485–500
Abstract
This paper presents model-based forecasting of the Lithuanian education system in the period of 2001–2010. In order to obtain satisfactory forecasting results, development of models used for these aims should be grounded on some interactive data mining. The process of the development is usually accompanied by the formulation of some assumptions to background methods or models. The accessibility and reliability of data sources should be verified. Special data mining of data sources may verify the assumptions. Interactive data mining of the data, stored in the system of the Lithuanian teachers' database, and that of other sources representing the state of the education system and demographic changes in Lithuania was used. The models cover the estimation of data quality in the databases, analysis of the flow of teachers and pupils, clustering of schools, the model of dynamics of the pedagogical staff and pupils, and the quality analysis of teachers. The main results of forecasting and integrated analysis of the Lithuanian teachers' database with other data reflecting the state of the education system and demographic changes in Lithuania are presented.