Informacja

Drogi użytkowniku, aplikacja do prawidłowego działania wymaga obsługi JavaScript. Proszę włącz obsługę JavaScript w Twojej przeglądarce.

English (EN)·Polski (PL)·Yкраїнський (UK)
Przejdź do strony domowej biblioteki Centralna Biblioteka Wojskowa Link otwiera się w nowym oknie Logo biblioteki Prolib Integro - strona głównaCentralna Biblioteka Wojskowa

Wyszukujesz frazę "learning network" wg kryterium: Temat

  Lista filtrów

Dostawca treści

Wyrównaj
Wyświetlanie 1-15 z 160
Tytuł:
Restoration of Remote Satellite Sensing Images using Machine and Deep Learning : a Survey
Autorzy:
Abdellaoui, Meriem
Benabdelkader, Souad
Assas, Ouarda
Powiązania:
https://bibliotekanauki.pl/articles/31339413.pdf
Data publikacji:
2023
Wydawca:
Szkoła Główna Gospodarstwa Wiejskiego w Warszawie. Instytut Informatyki Technicznej
Tematy:
image restoration
remote sensing images
artificial intelligence
AI
machine learning
ML
deep learning
DL
convolutional neural network
CNN
Opis:
Remote sensing satellite images are affected by different types of degradation, which poses an obstacle for remote sensing researchers to ensure a continuous and trouble-free observation of our space. This degradation can reduce the quality of information and its effect on the reliability of remote sensing research. To overcome this phenomenon, the methods of detecting and eliminating this degradation are used, which are the subject of our study. The original aim of this paper is that it proposes a state of art of recent decade (2012-2022) on advances in remote sensing image restoration using machine and deep learning, identified by this survey, including the databases used, the different categories of degradation, as well as the corresponding methods. Machine learning and deep learning based strategies for remote sensing satellite image restoration are recommended to achieve satisfactory improvements.
Źródło:
Machine Graphics & Vision; 2023, 32, 2; 147-167
1230-0535
2720-250X
Pojawia się w:
Machine Graphics & Vision
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Evaluating the performance of Extreme Learning Machine technique for ore grade estimation
Autorzy:
Abuntori, Clara Akalanya
Al-Hassan, Sulemana
Mireku-Gyimah, Daniel
Ziggah, Yao Yevenyo
Powiązania:
https://bibliotekanauki.pl/articles/1839059.pdf
Data publikacji:
2021
Wydawca:
Główny Instytut Górnictwa
Tematy:
extreme learning machine
artificial intelligence
artificial neural network
grade estimation
kriging
ELM
sztuczna inteligencja
sztuczna sieć neuronowa
Opis:
Due to the complex geology of vein deposits and their erratic grade distributions, there is the tendency of overestimating or underestimating the ore grade. These estimated grade results determine the profitability of mining the ore deposit or otherwise. In this study, five Extreme Learning Machine (ELM) variants based on hard limit, sigmoid, triangular basis, sine and radial basis activation functions were applied to predict ore grade. The motive is that the activation function has been identified to play a key role in achieving optimum ELM performance. Therefore, assessing the extent of influence the activation functions will have on the final outputs from the ELM has some scientific value worth investigating. This study therefore applied ELMas ore grade estimator which is yet to be explored in the literature. The obtained results from the five ELM variants were analysed and compared with the state-of-the-art benchmark methods of Backpropagation Neural Network (BPNN) and Ordinary Kriging (OK). The statistical test results revealed that the ELM with sigmoid activation function (ELM-Sigmoid) was the best among all the other investigated methods (ELM-Hard limit, ELM-Triangular basis, ELM-Sine, ELM-Radial Basis, BPNN and OK). This is because the ELM-sigmoid produced the lowest MAE (0.0175), MSE (0.0005) and RMSE (0.0229) with highest R2 (91.93%) and R (95.88%) respectively. It was concluded that ELM-Sigmoid can be used by field practitioners as a reliable alternative ore grade estimation technique.
Źródło:
Journal of Sustainable Mining; 2021, 20, 2; 56-71
2300-1364
2300-3960
Pojawia się w:
Journal of Sustainable Mining
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
An attempt at applying machine learning in diagnosing marine ship engine turbochargers
Autorzy:
Adamkiewicz, Andrzej
Nikończuk, Piotr
Powiązania:
https://bibliotekanauki.pl/articles/2200936.pdf
Data publikacji:
2022
Wydawca:
Polska Akademia Nauk. Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne PAN
Tematy:
machine learning
compressor diagnosis
marine ship engine
operational decision
neural
network
Opis:
The article presents a diagnosis of turbochargers in the supercharging systems of marine engines in terms of maintenance decisions. The efficiency of turbocharger rotating machines was defined. The operating parameters of turbocharging systems used to monitor the correct operation and diagnose turbochargers were identified. A parametric diagnostic test was performed. Relationships between parameters for use in machine learning were selected. Their credibility was confirmed by the results of the parametric test of the turbocharger system and the main engine, verified by the coefficient of determination. A particularly good fit of the describing functions was confirmed. As determinants of the technical condition of a turbocharger, the relationship between the rotational speed of the engine shaft, the turbocharger rotor assembly and the charging air pressure was assumed. In the process of machine learning, relationships were created between the rotational speed of the engine shaft and the boost pressure, and the indicator of the need for maintenance. The accuracy of the maintenance decisions was confirmed by trends in changes in the efficiency of compressors.
Źródło:
Eksploatacja i Niezawodność; 2022, 24, 4; 795--804
1507-2711
Pojawia się w:
Eksploatacja i Niezawodność
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Roles of Music-Making in the Process of Cross-Cultural Adaptation: A Case of International Students in Wrocław
Autorzy:
Alptekin, Emre Can
Powiązania:
https://bibliotekanauki.pl/articles/2196932.pdf
Data publikacji:
2022-10-06
Wydawca:
Komisja Nauk Filologicznych Polskiej Akademii Nauk, Oddział we Wrocławiu
Tematy:
music-making
sociocultural adaptation
psychological adjustment
culture learning theory
social network
cross-cultural transition
Opis:
With the intensifying flow of academically motivated people between countries, the significance of research on cross-cultural adaptation increases. Although the problems and difficulties caused by cultural differences have been researched extensively, this research focused on a common practice among different cultures: participative music making in an intercultural context. Therefore, the current study explores how participative music-making shapes international students’ cross-cultural experiences in Wroclaw. For this purpose, the relevance between international students’ cross-cultural adaptation and music-making as a social activity in Poland is examined. The required data were gathered through in-depth interviews with six students from various countries who made music as a collective activity during their transnational accommodation. The collected data is analysed by the inductive coding approach to explore the commonalities in the international students’ experiences. Findings concluded that collective music making shapes music-maker students’ cross-cultural experiences by not merely helping them gain a specific social network but also contributing to their financial income and mood states, and finally, privileged behaviour by the host country members towards these students.
Źródło:
Academic Journal of Modern Philology; 2022, 15; 21-32
2299-7164
2353-3218
Pojawia się w:
Academic Journal of Modern Philology
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Arabic and American Sign Languages Alphabet Recognition by Convolutional Neural Network
Autorzy:
Alshomrani, Shroog
Aljoudi, Lina
Arif, Muhammad
Powiązania:
https://bibliotekanauki.pl/articles/2023675.pdf
Data publikacji:
2021
Wydawca:
Stowarzyszenie Inżynierów i Techników Mechaników Polskich
Tematy:
convolutional neural network
deep learning
American sign language
Arabic sign language
sieć neuronowa
głębokie uczenie
amerykański język migowy
arabski język migowy
Opis:
Hearing loss is a common disability that occurs in many people worldwide. Hearing loss can be mild to complete deafness. Sign language is used to communicate with the deaf community. Sign language comprises hand gestures and facial expressions. However, people find it challenging to communicate in sign language as not all know sign language. Every country has developed its sign language like spoken languages, and there is no standard syntax and grammatical structure. The main objective of this research is to facilitate the communication between deaf people and the community around them. Since sign language contains gestures for words, sentences, and letters, this research implemented a system to automatically recognize the gestures and signs using imaging devices like cameras. Two types of sign languages are considered, namely, American sign language and Arabic sign language. We have used the convolutional neural network (CNN) to classify the images into signs. Different settings of CNN are tried for Arabic and American sign datasets. CNN-2 consisting of two hidden layers produced the best results (accuracy of 96.4%) for the Arabic sign language dataset. CNN-3, composed of three hidden layers, achieved an accuracy of 99.6% for the American sign dataset.
Źródło:
Advances in Science and Technology. Research Journal; 2021, 15, 4; 136-148
2299-8624
Pojawia się w:
Advances in Science and Technology. Research Journal
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Development of Speaker Voice Identification Using Main Tone Boundary Statistics for Applying To Robot-Verbal Systems
Autorzy:
Amirgaliyev, Yedilkhan
Musabayev, Timur
Yedilkhan, Didar
Wojcik, Waldemar
Amirgaliyeva, Zhazira
Powiązania:
https://bibliotekanauki.pl/articles/963938.pdf
Data publikacji:
2020
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
speaker voice identification
voice interface (FXO)
human being
human-robot interaction
HRI
speech recognition
statistics of voice fundamental tone
computer-aided learning
neural network
Opis:
Hereby there is given the speaker identification basic system. There is discussed application and usage of the voice interfaces, in particular, speaker voice identification upon robot and human being communication. There is given description of the information system for speaker automatic identification according to the voice to apply to robotic-verbal systems. There is carried out review of algorithms and computer-aided learning libraries and selected the most appropriate, according to the necessary criteria, ALGLIB. There is conducted the research of identification model operation performance assessment at different set of the fundamental voice tone. As the criterion of accuracy there has been used the percentage of improperly classified cases of a speaker identification.
Źródło:
International Journal of Electronics and Telecommunications; 2020, 66, 3; 583-588
2300-1933
Pojawia się w:
International Journal of Electronics and Telecommunications
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Hybrid predictions of the homogenous properties’ market value with the use of ann
Prognozowanie wartości rynkowej jednorodnych nieruchomości hybrydowym modelem z wykorzystaniem sztucznych sieci neuronowych
Autorzy:
Anysz, Hubert
Podwórna, Monika
Ibadov, Nabi
Lennerts, Kunibert
Dikarev, Kostiantyn
Powiązania:
https://bibliotekanauki.pl/articles/1852660.pdf
Data publikacji:
2021
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
wycena nieruchomości
sieć neuronowa sztuczna
perceptron wielowarstwowy
podejście porównawcze
uczenie maszynowe
model hybrydowy
real estate valuation
artificial neural network
multilayer perceptron
comparative approach
machine learning
hybrid model
Opis:
The homogenous properties – as flats are – have the set of key features that characterizes them. The area of a flat, the number of rooms and storey number where it is located, the technical state of a building, and the state of the vicinity of the blocks of flats assessed. The database comprises 222 flats with their transaction prices on the secondary estate market. The analysed flats are located in a certain quarter of Wrocław city in Poland. The database is large enough to apply machine learning for successful price predictions. Their close locations significantly lower the influence of clients’ assessments of the attractiveness of the location on the flat’s price. The hybrid approach is applied, where classifying precedes the solution of the regression problem. Dependently on the class of flats, the mean absolute percentage error achieved through the calculations presented in the article varies from 4,4 % to 7,8 %. In the classes of flats where the number of cases doesn’t allow for machine predicting, multivariate linear regression is applied. The reliable use of machine learning tools has proved that the automated valuation of homogenous types of properties can produce price predictions with the error low enough for real applications.
Wycena nieruchomości jest złożonym procesem. Rzeczoznawca majątkowy musi być biegły zarówno w naukach ekonomicznych, prawnych, jak i technicznych. W praktyce często zdarzają się przypadki, w których konieczne jest poznanie zakresu wartości nieruchomości w krótkim czasie. Zautomatyzowane modele wyceny (AVM) są kwestionowane przez praktyków, ale nie oznacza to, że nie należy szukać nowych metod wyceny, innych niż te określone w Rozporządzeniu Rady Ministrów z dnia 21 września 2004 r. w sprawie wyceny nieruchomości i sporządzania operatu szacunkowego. Do określenia wartości rynkowej nieruchomości zdefiniowanej w Ustawie z dnia 21 sierpnia 1997 r o gospodarce nieruchomościami, jako „szacunkowa kwota, jaką w dniu wyceny można uzyskać za nieruchomość w transakcji sprzedaży zawieranej na warunkach rynkowych pomiędzy kupującym a sprzedającym, którzy mają stanowczy zamiar zawarcia umowy, działają z rozeznaniem i postępują rozważnie oraz nie znajdują się w sytuacji przymusowej”, najczęściej stosowaną metodą wyceny jest podejście porównawcze polegające na szacowaniu wartości na podstawie ostatnich danych sprzedaży innych podobnych nieruchomości na rynku lokalnym. Takie podejście wymaga aktywnego, rozwiniętego oraz w miarę stabilnego rynku. Rzeczoznawca majątkowy analizuje ceny transakcyjne nieruchomości, które w wystarczającym stopniu są podobne do nieruchomości wycenianej. Analiza atrybutów nieruchomości polega na badaniu nieruchomości pod względem trwałych cech, które mają znaczący wpływ na wartość, w szczególności lokalizację obiektu, jego powierzchnię, położenie w budynku, stan techniczny. W pracy przenalizowano próbkę 222 nieruchomości lokalowych, które były przedmiotem obrotu na wrocławskim rynku wtórnym. Lokalny rynek nieruchomości przyjęto jako nieruchomości lokalowe o powierzchni użytkowej z przedziału od 15 do 95 m2, w budynkach o stanie dobry lub średnim, z obrębu Grabiszyn dzielnicy Fabryczna miasta Wrocław. W pracy przyjęto dwuletni okres analizy, ze względu na w miarę stabilny rynek w okresie 2013-2014 nie uwzględniono czynnika czasu - przyjęto zerowy trend czasowy dla transakcji wolnorynkowych.
Źródło:
Archives of Civil Engineering; 2021, 67, 1; 285-301
1230-2945
Pojawia się w:
Archives of Civil Engineering
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Combining fuzzy and cellular learning automata methods for clustering wireless sensor network to increase life of the network
Autorzy:
Aramideh, J
Jelodar, H
Powiązania:
https://bibliotekanauki.pl/articles/957968.pdf
Data publikacji:
2014
Wydawca:
Stowarzyszenie Inżynierów i Techników Mechaników Polskich
Tematy:
wireless sensor network
clustering
fuzzy logic
cellular learning automata
Opis:
Wireless sensor networks have attracted attention of researchers considering their abundant applications. One of the important issues in this network is limitation of energy consumption which is directly related to life of the network. One of the main works which have been done recently to confront with this problem is clustering. In this paper, an attempt has been made to present clustering method which performs clustering in two stages. In the first stage, it specifies candidate nodes for being head cluster with fuzzy method and in the next stage, the node of the head cluster is determined among the candidate nodes with cellular learning automata. Advantage of the clustering method is that clustering has been done based on three main parameters of the number of neighbors, energy level of nodes and distance between each node and sink node which results in selection of the best nodes as a candidate head of cluster nodes. Connectivity of network is also evaluated in the second part of head cluster determination. Therefore, more energy will be stored by determining suitable head clusters and creating balanced clusters in the network and consequently, life of the network increases.
Źródło:
Advances in Science and Technology. Research Journal; 2014, 8, 24; 1-8
2299-8624
Pojawia się w:
Advances in Science and Technology. Research Journal
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Towards a new deep learning algorithm based on GRU and CNN: NGRU
Autorzy:
Atassi, Abdelhamid
el Azami, Ikram
Powiązania:
https://bibliotekanauki.pl/articles/2141895.pdf
Data publikacji:
2020
Wydawca:
Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Automatyki i Pomiarów
Tematy:
Convolutional Neural Network
CNN
Gated Recurrent Unit
GRU
SemEval
Twitter
word2vec
Keras
TensorFlow
Adadelta
Adam
soft-max
deep learning
Opis:
This paper describes our new deep learning system based on a comparison between GRU and CNN. Initially we start with the first system which uses Convolutional Neural Network (CNN) which we will compare with the second system which uses Gated Recurrent Unit (GRU). And through this comparison we propose a new system based on the positive points of the two previous systems. Therefore, this new system will take the right choice of hyper-parameters recommended by the authors of both systems. At the final stage we propose a method to apply this new system to the dataset of different languages (used especially in socials networks).
Źródło:
Journal of Automation Mobile Robotics and Intelligent Systems; 2020, 14, 4; 45-47
1897-8649
2080-2145
Pojawia się w:
Journal of Automation Mobile Robotics and Intelligent Systems
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Industrial Application of Deep Neural Network for Aluminum Casting Defect Detection in Case of Unbalanced Dataset
Autorzy:
Awtoniuk, Michał
Majerek, Dariusz
Myziak, Artur
Gajda, Cyprian
Powiązania:
https://bibliotekanauki.pl/articles/2204946.pdf
Data publikacji:
2022
Wydawca:
Stowarzyszenie Inżynierów i Techników Mechaników Polskich
Tematy:
machine learning
deep neural network
classification
casting defect
casting defect detection
Opis:
We have developed a deep neural network for casting defect detection. The approach is original because it assumes the use of data related to the casting manufacturing process, i.e. measurement signals from the casting machine, rather than data describing the finished casting, e.g. images. The defects are related to the production of car engine heads made of silumin. In the current research we focused on the detection of defects related to the leakage of the casting. The data came from production plant in Poland. The dataset was unbalanced. It included nearly 38,500 observations, of which only 4% described a leak event. The work resulted in a deep network consisting of 22 layers. We assessed the classification accuracy using a ROC curve, an AUC index and a confusion matrix. The AUC value was 0.97 and 0.949 for the learning and testing dataset, respectively. The model allowed for an ex-post analysis of the casting process. The analysis was based on Shapley values. This makes it possible not only to detect the occurrence of a defect but also to give potential reasons for the appearance of a casting leak.
Źródło:
Advances in Science and Technology. Research Journal; 2022, 16, 5; 120--128
2299-8624
Pojawia się w:
Advances in Science and Technology. Research Journal
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
ADOPTING LEARNING DESIGN WITH LAMS: MULTI- DIMENSIONAL, SYNCHRONOUS LARGE-SCALE ADOPTION OF INNOVATION
Autorzy:
Badilescu-Buga, Emil
Powiązania:
https://bibliotekanauki.pl/articles/941240.pdf
Data publikacji:
2012
Wydawca:
Uniwersytet Marii Curie-Skłodowskiej w Lublinie. IATEFL Poland Computer Special Interest Group
Tematy:
learning design
LAMS
adoption life cycle
social network
information cognitive structures
Opis:
Learning Activity Management System (LAMS) has been trialled and used by users from many countries around the globe, but despite the positive attitude towards its potential benefits to pedagogical processes its adoption in practice has been uneven, reflecting how difficult it is to make a new technology based concept an integral part of the education system. In order to investigate and determine the elements that block the adoption of learning design tools in general, the study will review research papers that have been published in recent years on this subject, especially LAMS. The study will discuss patterns of critical aspects related to adoption of learning design tools and derive a framework that can be used in follow-up studies aimed at collecting relevant empirical data from practitioners to identify key progress measures of the adoption process. These measures may be used later to devise strategies that will see increased adoption of online learning design tools such as LAMS in school systems and higher education institutions.
Źródło:
Teaching English with Technology; 2012, 12, 2; 18-35
1642-1027
Pojawia się w:
Teaching English with Technology
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Artificial intelligence applications in project scheduling: a systematic review, bibliometric analysis, and prospects for future research
Autorzy:
Bahroun, Zied
Tanash, Moayad
Ad, Rami As
Alnajar, Mohamad
Powiązania:
https://bibliotekanauki.pl/articles/27315576.pdf
Data publikacji:
2023
Wydawca:
STE GROUP
Tematy:
artificial intelligence
machine learning
project scheduling
bibliometric analysis
network analysis
review
Opis:
The availability of digital infrastructures and the fast-paced development of accompanying revolutionary technologies have triggered an unprecedented reliance on Artificial intelligence (AI) techniques both in theory and practice. Within the AI domain, Machine Learning (ML) techniques stand out as essential facilitator largely enabling machines to possess human-like cognitive and decision making capabilities. This paper provides a focused review of the literature addressing applications of emerging ML toolsto solve various Project Scheduling Problems (PSPs). In particular, it employs bibliometric and network analysis tools along with a systematic literature review to analyze a pool of 104 papers published between 1985 and August 2021. The conducted analysis unveiled the top contributing authors, the most influential papers as well as the existing research tendencies and thematic research topics within this field of study. A noticeable growth in the number of relevant studies is seen recently with a steady increase as of the year 2018. Most of the studies adopted Artificial Neural Networks, Bayesian Network and Reinforcement Learning techniques to tackle PSPs under a stochastic environment, where these techniques are frequently hybridized with classical metaheuristics. The majority of works (57%) addressed basic Resource Constrained PSPs and only 15% are devoted to the project portfolio management problem. Furthermore, this study clearly indicates that the application of AI techniques to efficiently handle PSPs is still in its infancy stage bringing out the need for further research in this area. This work also identifies current research gaps and highlights a multitude of promising avenues for future research.
Źródło:
Management Systems in Production Engineering; 2023, 2 (31); 144--161
2299-0461
Pojawia się w:
Management Systems in Production Engineering
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Tomato disease detection model based on densenet and transfer learning
Autorzy:
Bakr, Mahmoud
Abdel-Gaber, Sayed
Nasr, Mona
Hazman, Maryam
Powiązania:
https://bibliotekanauki.pl/articles/2097440.pdf
Data publikacji:
2022
Wydawca:
Polskie Towarzystwo Promocji Wiedzy
Tematy:
leaf disease detection
convolutional neural network
deep learning
transfer learning
Opis:
Plant diseases are a foremost risk to the safety of food. They have the potential to significantly reduce agricultural products quality and quantity. In agriculture sectors, it is the most prominent challenge to recognize plant diseases. In computer vision, the Convolutional Neural Network (CNN) produces good results when solving image classification tasks. For plant disease diagnosis, many deep learning architectures have been applied. This paper introduces a transfer learning based model for detecting tomato leaf diseases. This study proposes a model of DenseNet201 as a transfer learning-based model and CNN classifier. A comparison study between four deep learning models (VGG16, Inception V3, ResNet152V2 and DenseNet201) done in order to determine the best accuracy in using transfer learning in plant disease detection. The used images dataset contains 22930 photos of tomato leaves in 10 different classes, 9 disorders and one healthy class. In our experimental, the results shows that the proposed model achieves the highest training accuracy of 99.84% and validation accuracy of 99.30%.
Źródło:
Applied Computer Science; 2022, 18, 2; 56--70
1895-3735
Pojawia się w:
Applied Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
PCA-based approximation of a class of distributed parameter systems: classical vs. neural network approach
Autorzy:
Bartecki, K.
Powiązania:
https://bibliotekanauki.pl/articles/201641.pdf
Data publikacji:
2012
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
distributed parameter system
principal component analysis
artificial neural network
supervised learning
unsupervised learning
Opis:
In this article, an approximation of the spatiotemporal response of a distributed parameter system (DPS) with the use of the principal component analysis (PCA) is considered. Based on a data obtained by the numerical solution of a set of partial differential equations, a PCA-based approximation procedure is performed. It consists in the projection of the original data into the subspace spanned by the eigenvectors of the data covariance matrix, corresponding to its highest eigenvalues. The presented approach is carried out using both the classical PCA method as well as two different neural network structures: two-layer feed-forward network with supervised learning (FF-PCA) and single-layer network with unsupervised, generalized Hebbian learning rule (GHA-PCA). In each case considered, the effect of the approximation model structure represented by the number of eigenvectors (or, in the neural case, units in the network projection layer) on the mean square approximation error of the spatiotemporal response and on the data compression ratio is analysed. As shown in the paper, the best approximation quality is obtained for the classical PCA method as well as for the FF-PCA neural approach. On the other hand, an adaptive learning method for the GHA-PCA network allows to use it in e.g. an on-line identification scheme.
Źródło:
Bulletin of the Polish Academy of Sciences. Technical Sciences; 2012, 60, 3; 651-660
0239-7528
Pojawia się w:
Bulletin of the Polish Academy of Sciences. Technical Sciences
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Wpływ opisu danych na efektywność uczenia oraz pracy sztucznej sieci neuronowej na przykładzie identyfikacji białek
Influence of data description on efficiency of learning and job artificial neural network on example of identification of proteins
Autorzy:
BARTMAN, Jacek
Powiązania:
https://bibliotekanauki.pl/articles/457310.pdf
Data publikacji:
2013
Wydawca:
Uniwersytet Rzeszowski
Tematy:
sztuczna sieć neuronowa
uczenie
artificial neural network
learning
Opis:
Uczenie jednokierunkowych wielowarstwowych sztucznych sieci neuronowych jest zagadnieniem szeroko omawianym w literaturze. Autorzy większości opracowań skupiają się na metodach uczenia, zdecydowanie mniej prac poświęconych jest wpływowi preprocesingu danych na uczenie i efektywność pracy sieci. Skoro uczenie sztucznych sieci neuronowych jest szukaniem funkcji odwzorowującej zbiór danych wejściowych w zbiór oczekiwanych odpowiedzi, to czego możemy oczekiwać, jeżeli zmienimy opis danych uczących? Zmienia się funkcja odwzorowująca, a więc szukamy innej funkcji, zatem jest możliwe, iż sposób kodowania danych wpływa na efektywność uczenia i pracy sieci. Niniejsza praca dotyka przedstawione zagadnienie badając wpływ sposobu zakodowania opisu białek na efektywność uczenia oraz pracy sieci neuronowej identyfikującej rodzaj białka
Learning feedforward multilayer neural networks is an issue widely discussed in the literature. The authors of the most works focus on methods of learning, much less work is devoted to the influence of data preprocessing on learning and the efficiency of the network. If learning of artificial neural networks is finding the mapping function set of input data into a set of expected responses, what you can expect if you change the description of the data learners? Changes of mapping functions, and so we are looking for another function, so it is possible that the encoding of data affects the efficiency of learning and job of the network. This paper touches the issue presented by examining the impact of coding method information about the proteins on the effectiveness of learning and the work of the neural network identifies the type of protein.
Źródło:
Edukacja-Technika-Informatyka; 2013, 4, 2; 358-365
2080-9069
Pojawia się w:
Edukacja-Technika-Informatyka
Dostawca treści:
Biblioteka Nauki
Artykuł
Wyświetlanie 1-15 z 160

Ta witryna wykorzystuje pliki cookies do przechowywania informacji na Twoim komputerze. Pliki cookies stosujemy w celu świadczenia usług na najwyższym poziomie, w tym w sposób dostosowany do indywidualnych potrzeb. Korzystanie z witryny bez zmiany ustawień dotyczących cookies oznacza, że będą one zamieszczane w Twoim komputerze. W każdym momencie możesz dokonać zmiany ustawień dotyczących cookies