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 "Neural networks" wg kryterium: Temat

  Lista filtrów
Wyrównaj
Wyświetlanie 1-15 z 24
Tytuł:
Approach to classifying data with highly localized unmarked features using neural networks
Autorzy:
Grzeszczuk, Rafał
Powiązania:
https://bibliotekanauki.pl/articles/305688.pdf
Data publikacji:
2019
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
classification
neural networks
medical image analysis
Opis:
To face the increasing demand of quality healthcare, cutting-edge automation technology is being applied in demanding areas such as medical imaging. This paper proposes a novel approach to classification problems on datasets with sparse highly localized features. It is based on the use of a saliency map in the amplification of features. Unlike previous efforts, this approach does not use any prior information about feature localization. We present an experimental study based on the Diabetic Retinopathy classification problem, in which our method has shown to achieve an over 20%-higher accuracy in solving a two-class Diabetic Retinopathy classification problem than a naive approach based solely on residual neural networks. The dataset consists of 35,120 images of various qualities, inconsistent resolutions, and aspect ratios.
Źródło:
Computer Science; 2019, 20 (3); 329-342
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Approximation properties of some two-layer feedforward neural networks
Autorzy:
Nowak, M. A.
Powiązania:
https://bibliotekanauki.pl/articles/255577.pdf
Data publikacji:
2007
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
neural networks
approximation of functions
sigmoidal function
Opis:
In this article, we present a multiyariate two-layer feedforward neural networks that approximate continuos functions defined on [0, 1]d. We show that the L1 error of approximation is asymptotically proportional to the modulus of continuity of the underlying function taken at √d/n, where n is the number of function values used.
Źródło:
Opuscula Mathematica; 2007, 27, 1; 59-72
1232-9274
2300-6919
Pojawia się w:
Opuscula Mathematica
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A repeatability study of artificial neural network predictions in flow stress model development for a magnesium alloy
Autorzy:
Siewior, Hubert
Madej, Łukasz
Powiązania:
https://bibliotekanauki.pl/articles/29520089.pdf
Data publikacji:
2021
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
flow stress
artificial neural networks
feedforward
recursive
Opis:
This work is devoted to an evaluation of the capabilities of artificial neural networks (ANN) in terms of developing a flow stress model for magnesium ZE20. The learning procedure is based on experimental flow-stress data following inverse analysis. Two types of artificial neural networks are investigated: a simple feedforward version and a recursive one. Issues related to the quality of input data and the size of the training dataset are presented and discussed. The work confirms the general ability of feedforward neural networks in flow stress data predictions. It also highlights that slightly better quality predictions are obtained using recursive neural networks.
Źródło:
Computer Methods in Materials Science; 2021, 21, 4; 209-218
2720-4081
2720-3948
Pojawia się w:
Computer Methods in Materials Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
From Linear Classifier to Convolutional Neural Network for Hand Pose Recognition
Autorzy:
Rościszewski, P.
Powiązania:
https://bibliotekanauki.pl/articles/305776.pdf
Data publikacji:
2017
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
machine learning
artificial neural networks
computer vision
Opis:
Recently gathered image datasets and new capabilities of high performance computing systems allowed developing new artificial neural network models and training algorithms. Using the new machine learning models, computer vision tasks can be accomplished based on the raw values of image pixels, instead of specific features. The principle of operation of deep artificial neural networks is more and more resembling of what we believe to be happening in the human visual cortex. In this paper we build up an understanding of convolutional neural networks through investigating supervised machine learning methods suchas K-Nearest Neighbors, linear classifiers and fully connected neural networks. We provide examples and accuracy results based on our implementation aimed for the problem of hand pose recognition.
Źródło:
Computer Science; 2017, 18 (4); 341-356
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Track finding with Deep Neural Networks
Autorzy:
Kucharczyk, Marcin
Wolter, Marcin
Powiązania:
https://bibliotekanauki.pl/articles/305791.pdf
Data publikacji:
2019
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
deep neural networks
machine learning
tracking
HEP
Opis:
High energy physics experiments require fast and efficient methods for reconstructing the tracks of charged particles. The commonly used algorithms are sequential and the required CPU power increases rapidly with the number of tracks. Neural networks can speed up the process due to their capability of modeling complex non-linear data dependencies and finding all tracks in parallel. In this paper, we describe the application of the deep neural network for reconstructing straight tracks in a toy two-dimensional model. It is planned to apply this method to the experimental data obtained by the MUonE experiment at CERN.
Źródło:
Computer Science; 2019, 20 (4); 475-491
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Compressing sentiment analysis CNN models for efficient hardware processing
Autorzy:
Wróbel, Krzysztof
Karwatowski, Michał
Wielgosz, Maciej
Pietroń, Marcin
Wiatr, Kazimierz
Powiązania:
https://bibliotekanauki.pl/articles/305234.pdf
Data publikacji:
2020
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
natural language processing
convolutional neural networks
FPGA
compression
Opis:
Convolutional neural networks (CNNs) were created for image classification tasks. Shortly after their creation, they were applied to other domains, including natural language processing (NLP). Nowadays, solutions based on artificial intelligence appear on mobile devices and embedded systems, which places constraints on memory and power consumption, among others. Due to CNN memory and computing requirements, it is necessary to compress them in order to be mapped to the hardware. This paper presents the results of the compression of efficient CNNs for sentiment analysis. The main steps involve pruning and quantization. The process of mapping the compressed network to an FPGA and the results of this implementation are described. The conducted simulations showed that the 5-bit width is enough to ensure no drop in accuracy when compared to the floating-point version of the network. Additionally, the memory footprint was significantly reduced (between 85 and 93% as compared to the original model).
Źródło:
Computer Science; 2020, 21 (1); 25-41
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Exploring convolutional auto-encoders for representation learning on networks
Autorzy:
Nerurkar, Pranav Ajeet
Chandane, Madhav
Bhirud, Sunil
Powiązania:
https://bibliotekanauki.pl/articles/305489.pdf
Data publikacji:
2019
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
network representation learning
deep learning
graph convolutional neural networks
Opis:
A multitude of important real-world or synthetic systems possess network structures. Extending learning techniques such as neural networks to process such non-Euclidean data is therefore an important direction for machine learning re- search. However, this domain has received comparatively low levels of attention until very recently. There is no straight-forward application of machine learning to network data, as machine learning tools are designed for i:i:d data, simple Euclidean data, or grids. To address this challenge, the technical focus of this dissertation is on the use of graph neural networks for network representation learning (NRL); i.e., learning the vector representations of nodes in networks. Learning the vector embeddings of graph-structured data is similar to embedding complex data into low-dimensional geometries. After the embedding process is completed, the drawbacks associated with graph-structured data are overcome. The current inquiry proposes two deep-learning auto-encoder-based approaches for generating node embeddings. The drawbacks in such existing auto-encoder approaches as shallow architectures and excessive parameters are tackled in the proposed architectures by using fully convolutional layers. Extensive experiments are performed on publicly available benchmark network datasets to highlight the validity of this approach.
Źródło:
Computer Science; 2019, 20 (3); 273-288
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Computational approach to understanding Autism Spectrum Disorders
Autorzy:
Duch, W.
Nowak, W.
Meller, J.
Osiński, G.
Dobosz, K.
Mikołajewski, D.
Wójcik, G. M.
Powiązania:
https://bibliotekanauki.pl/articles/305295.pdf
Data publikacji:
2012
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
computational neuroscience
neural networks
autism
Autism Spectrum Disorders
ASD
Opis:
Every year the prevalence of Autism Spectrum of Disorders (ASD) is rising. Is there a unifying mechanism of various ASD cases at the genetic, molecular, cellular or systems level? The hypothesis advanced in this paper is focused on neural dysfunctions that lead to problems with attention in autistic people. Simulations of attractor neural networks performing cognitive functions help to assess system long-term neurodynamics. The Fuzzy Symbolic Dynamics (FSD) technique is used for the visualization of attractors in the semantic layer of the neural model of reading. Large-scale simulations of brain structures characterized by a high order of complexity requires enormous computational power, especially if biologically motivated neuron models are used to investigate the influence of cellular structure dysfunctions on the network dynamics. Such simulations have to be implemented on computer clusters in a grid-based architectures.
Źródło:
Computer Science; 2012, 13 (2); 47-61
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A Survey on multi-objective based parameter optimization for deep learning
Autorzy:
Chakraborty, Mrittika
Pal, Wreetbhas
Bandyopadhyay, Sanghamitra
Maulik, Ujjwal
Powiązania:
https://bibliotekanauki.pl/articles/27312917.pdf
Data publikacji:
2023
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
deep learning
multi-objective optimization
parameter optimization
neural networks
Opis:
Deep learning models form one of the most powerful machine learning models for the extraction of important features. Most of the designs of deep neural models, i.e., the initialization of parameters, are still manually tuned. Hence, obtaining a model with high performance is exceedingly time-consuming and occasionally impossible. Optimizing the parameters of the deep networks, therefore, requires improved optimization algorithms with high convergence rates. The single objective-based optimization methods generally used are mostly time-consuming and do not guarantee optimum performance in all cases. Mathematical optimization problems containing multiple objective functions that must be optimized simultaneously fall under the category of multi-objective optimization sometimes referred to as Pareto optimization. Multi-objective optimization problems form one of the alternatives yet useful options for parameter optimization. However, this domain is a bit less explored. In this survey, we focus on exploring the effectiveness of multi-objective optimization strategies for parameter optimization in conjunction with deep neural networks. The case studies used in this study focus on how the two methods are combined to provide valuable insights into the generation of predictions and analysis in multiple applications.
Źródło:
Computer Science; 2023, 24 (3); 327--359
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Ensemble machine learning methods to predict the balancing of ayurvedic constituents in the human body
Autorzy:
Rajasekar, Vani
Krishnamoorthi, Sathya
Saracevic, Muzafer
Pepic, Dzenis
Zajmovic, Mahir
Zogic, Haris
Powiązania:
https://bibliotekanauki.pl/articles/27312840.pdf
Data publikacji:
2022
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
machine learning
artificial neural networks
diagnose
Ayurveda constituent
support vector machine
Opis:
In this paper, we demonstrate the result of certain machine-learning methods like support vector machine (SVM), naive Bayes (NB), decision tree (DT), k-nearest neighbor (KNN), artificial neural network (ANN), and AdaBoost algorithms for various performance characteristics to predict human body constituencies. Ayurveda-dosha studies have been used for a long time, but the quantitative reliability measurement of these diagnostic methods still lags. The careful and appropriate analysis leads to an effective treatment to predict human body constituencies. From an observation of the results, it is shown that the AdaBoost algorithm with hyperparameter tuning provides enhanced accuracy and recall (0.97), precision and F-score (0.96), and lower RSME values (0.64). The experimental results reveal that the improved model (which is based on ensemble-learning methods) significantly outperforms traditional methods. According to the findings, advancements in the proposed algorithms could give machine learning a promising future.
Źródło:
Computer Science; 2022, 23 (1); 117--132
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Towards textual data augmentation for neural networks: synonyms and maximum loss
Autorzy:
Jungiewicz, Michał
Smywiński-Pohl, Aleksander
Powiązania:
https://bibliotekanauki.pl/articles/305750.pdf
Data publikacji:
2019
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
deep learning
data augmentation
neural networks
natural language processing
sentence classification
Opis:
Data augmentation is one of the ways to deal with labeled data scarcity and overfitting. Both of these problems are crucial for modern deep-learning algorithms, which require massive amounts of data. The problem is better explored in the context of image analysis than for text; this work is a step forward to help close this gap. We propose a method for augmenting textual data when training convolutional neural networks for sentence classification. The augmentation is based on the substitution of words using a thesaurus as well as Princeton University's WordNet. Our method improves upon the baseline in most of the cases. In terms of accuracy, the best of the variants is 1.2% (pp.) better than the baseline.
Źródło:
Computer Science; 2019, 20 (1); 57-83
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Gramian angular field transformation-based intrusion detection
Autorzy:
Terzi, Duygu Sinanc
Powiązania:
https://bibliotekanauki.pl/articles/27312895.pdf
Data publikacji:
2022
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
encoding intrusions as images
convolutional neural networks
Gramian angular fields
intrusion detection
network security
Opis:
Cyber threats are increasing progressively in their frequency, scale, sophistication, and cost. The advancement of such threats has raised the need to enhance intelligent intrusion-detection systems. In this study, a different perspective has been developed for intrusion detection. Gramian angular fields were adapted to encode network traffic data as images. Hereby, a way to reveal bilateral feature relationships and benefit from the visual interpretation capability of deep-learning methods has been opened. Then, image-encoded intrusions were classified as binary and multi-class using convolutional neural networks. The obtained results were compared to both conventional machine-learning methods and related studies. According to the results, the proposed approach surpassed the success of traditional methods and produced success rates that were close to the related studies. Despite the use of complex mechanisms such as feature extraction, feature selection, class balancing, virtual data generation, or ensemble classifiers in related studies, the proposed approach is fairly plain – involving only data-image conversion and classification. This shows the power of simply changing the problem space.
Źródło:
Computer Science; 2022, 23 (4); 571--585
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Wykorzystanie modeli sieci neuronowych do identyfikacji składu litologicznego rudy miedzi
Application of neural networks models to lithological composition determination of copper ore
Autorzy:
Krawczykowska, A.
Trybalski, K.
Krawczykowski, D.
Powiązania:
https://bibliotekanauki.pl/articles/349707.pdf
Data publikacji:
2009
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
typy litologiczne rud miedzi
modelowanie
sieci neuronowe
lithological types of copper ore
modelling
neural networks
Opis:
Artykuł dotyczy zastosowania modeli sieci neuronowych w rozpoznawaniu typów litologicznych rudy miedzi. Do sprawdzenia zdolności predykcyjnych najskuteczniejszych modeli wykorzystano zbiory danych uzyskane z analizy zdjęć skaningowych dwóch charakterystycznych mieszanek różnych typów litologicznych: mieszanki z przewagą rudy piaskowcowej oraz mieszanki z przewagą rudy węglanowej i łupkowej. Wyniki rozpoznawania porównano z rzeczywistymi udziałami poszczególnych typów litologicznych rud miedzi w analizowanych mieszankach.
The paper concerns the application of neural networks models in recognition of lithological types of copper ore. To verify the predictive abilities of the most efficient models, the data sets given by scanning photos analyzes of two characteristic mixtures of various lithological types were applied. These were mixture with the advantage of sandstone ore and mixture with the advantage of carbonate and shale ores. The results of recognition were compared with the real contents of individual lithological types of copper ore in analyzed mixtures.
Źródło:
Górnictwo i Geoinżynieria; 2009, 33, 4; 141-151
1732-6702
Pojawia się w:
Górnictwo i Geoinżynieria
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Hybrid neuro-fuzzy classifier based on NEFCLASS model
Hybrydowy neuronowo-rozmyty klasyfikator oparty na modelu NEFCLASS
Autorzy:
Gliwa, B.
Byrski, A.
Powiązania:
https://bibliotekanauki.pl/articles/305407.pdf
Data publikacji:
2011
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
klasyfikatory neuronowo-rozmyte
NEFCLASS
sieci neuronowe
systemy rozmyte
neuro-fuzzy classifier
neural networks
fuzzy systems
Opis:
The paper presents hybrid neuro-fuzzy classifier, based on NEFCLASS model, which was modified. The presented classifier was compared to popular classifiers - neural networks and k-nearest neighbours. Efficiency of modifications in classifier was compared with methods used in original model NEFCLASS (learning methods). Accuracy of classifier was tested using 3 datasets from UCI Machine Learning Repository: iris, wine and breast cancer wis-consin. Moreover, influence of ensemble classification methods on classification accuracy was presented.
Artykuł przedstawia zasadę działania oraz wyniki badań eksperymentalnych klasyfikatora opartego na hybrydzie sieci neuronowej z logiką rozmytą, bazujący na modelu NEFCLASS. Prezentacja struktury i działania klasyfikatora została zilustrowana wynikami eksperymentów porównawczych przeprowadzonych dla popularnych klasyfikatorów, takich jak perceptron wielowarstwowy k najbliższych sąsiadów. Skuteczność wprowadzonych modyfikacji do klasyfikatora została porównana z metodami używanymi w oryginalnym modelu NEFCLASS (metody uczenia). Jako dane benchmarkowe posłużyły wybrane bazy danych z UCI Machine Learning Repository (iris, wine, breast cancer wisconsin). Zaprezentowano również wpływ użycia metod klasyfikacji zbiorczej na efektywność klasyfikacji.
Źródło:
Computer Science; 2011, 12; 115-135
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Próba wykorzystania sieci neuronowych w kompleksowej interpretacji danych elektromagnetycznych na przykładzie złoża Grabownica
An attempt to apply artificial neural networks in integrated interpretation of electromagnetic data - the Grabownica hydrocarbon deposit case study
Autorzy:
Mastej, W.
Powiązania:
https://bibliotekanauki.pl/articles/183525.pdf
Data publikacji:
2011
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
rozpoznawanie obrazów
sztuczne sieci neuronowe
magnetotelluryka
złoża węglowodorów
pattern recognition
artificial neural networks
magnetotellurics
hydrocarbon deposits
Opis:
W pracy przedstawiono próbę zastosowania metody rozpoznawania obrazów z użyciem sztucznych sieci neuronowych w kompleksowej interpretacji danych z sondowań magnetotellurycznych AMT (Audio-frequency Magnetotellurics) i CSAMT (Controlled Source Audio-frequency Magnetotellurics) ze złoża ropy i gazu Grabownica (dipol podłużny i poprzeczny względem linii profili pomiarowych). Obiektami klasyfikacji były pionowe pasy z przekrojów magnetotellurycznych, o szerokości 50 m, utworzone na bazie siatek interpolacyjnych. Strukturę obiektów formalnie niestrukturalnych wymuszono częściowo poprzez ich podział na: przypowierzchniową, wysokooporową strefę do 200 m n.p.m., strefę niskooporowych utworów uszczelniających oraz słabych maksimów - kominów dyfuzyjnych, od 200 do -100 m n.p.m. i najniższą, wysokooporową strefę złoża. Prawidłowe wskazanie rzeczywistych stref złożowych na bazie informacji pochodzących z często niejasnych i rozbieżnych między sobą obrazów z przekrojów magnetotellurycznych, świadczą o przydatności tej metody. Wskazano także dwie nieznane strefy złożowe w NE części przekroju G4 i w SW części przekroju G2.
The paper presents an attempt to apply the pattern recognition method using artificial neural networks in integrated interpretation of the magnetotelluric data AMT (Audio-frequency Magnetotellurics) and CSAMT (Controlled Source Audio-frequency Magnetotellurics), acquired from the Grabownica oil and gas deposit (longitudinal and transversal dipole in relation to measurement profile lines). Vertical belts of magnetotelluric cross-sections, each 50 m wide, obtained from interpolation grids, were the objects of classification. The structure of formally non-structural objects was partly imposed through division into: near-surface high-resistivity zone, to 200 m a.s.l., low-resistivity screens and week maxima - diffusion chimneys, from 200 to -100 m a.s.l., and the lowest, high-resistivity deposit zone. The usefulness of the method was proven by correct identification of real deposit zones based on data often coming from ambiguous and incompatible magnetotelluric cross-sections. In addition, two unknown deposit zones were discovered in NE part of cross-section G4 and SW part of cross-section G2.
Źródło:
Geologia / Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie; 2011, 37, 1; 157-173
0138-0974
Pojawia się w:
Geologia / Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie
Dostawca treści:
Biblioteka Nauki
Artykuł
Wyświetlanie 1-15 z 24

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