Zobrazeno 1 - 10
of 154
pro vyhledávání: '"Janusz A. Starzyk"'
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 31:331-344
In this paper, we introduce a new concept of associative memories in which synaptic connections of the self-organizing neural network learn time delays between input sequence elements. Synaptic connections represent both the synaptic weights and expe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6c9ecb21ff96f0759b4f429fa0fa1d9c
https://doi.org/10.1109/tnnls.2019.2921143
https://doi.org/10.1109/tnnls.2019.2921143
Publikováno v:
National Information Processing Institute
A generalization of active neural associative knowledge graphs (ANAKGs) to their minicolumn form is presented in this paper. Each minicolumn represents a single symbol, and the activation of an individual neuron in a minicolumn depends on the context
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::924dac5b2c3ea2699a718741573abff1
https://doi.org/10.1109/tnnls.2019.2927106
https://doi.org/10.1109/tnnls.2019.2927106
Autor:
Janusz A. Starzyk
Publikováno v:
Frontiers in Robotics, Automation and Control
Before artificial intelligence set its mind on developing abstract intelligent agents which can think, Alan Turing suggested training embodied machines equipped with sensors and actuators to accomplish intelligent tasks like understanding spoken Engl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::af01c74d838c893c07565da1f0b4a37c
http://www.intechopen.com/articles/show/title/motivation_in_embodied_intelligence
http://www.intechopen.com/articles/show/title/motivation_in_embodied_intelligence
Autor:
Wieslaw Galus, Janusz A. Starzyk
Publikováno v:
Advances in Human and Social Aspects of Technology ISBN: 9781799856535
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dfbf83d154f7c4e7a4e3bc3e137cad84
https://doi.org/10.4018/978-1-7998-5653-5
https://doi.org/10.4018/978-1-7998-5653-5
Publikováno v:
IEEE transactions on neural networks and learning systems. 32(8)
This article presents concurrent associative memories with synaptic delays useful for processing sequences of real vectors. Associative memories with synaptic delays were introduced by the authors for symbolic sequential inputs and demonstrated sever
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d3e5a9ad3378850960780ca296eca8be
https://pubmed.ncbi.nlm.nih.gov/33301411
https://pubmed.ncbi.nlm.nih.gov/33301411
Publikováno v:
SSCI
Wide neural networks were recently proposed as a less costly alternative to deep neural networks. In this paper, we analyze the properties of wide neural networks regarding feature selection and their significance We compared the random selection ofw
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c237dfcab12fb1c38b39823a3099bd2a
https://doi.org/10.1109/ssci44817.2019.9002711
https://doi.org/10.1109/ssci44817.2019.9002711
Autor:
Janusz A. Starzyk, Adrian Horzyk
Publikováno v:
SSCI
This paper introduces a biologically inspired associative data model and structure for finding nearest neighbors and similar patterns. The method can be used as an alternative to the classical approaches to accelerate the search for such patterns usi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5b87e6c0df58d2cf17fa64c43b9e1c82
https://doi.org/10.1109/ssci44817.2019.9002987
https://doi.org/10.1109/ssci44817.2019.9002987
Autor:
James Graham, Janusz A. Starzyk
Publikováno v:
IEEE Systems Journal. 11:1272-1283
This paper presents a new cognitive architecture and its major functional blocks. It describes how the new architecture is related to major trends in cognitive architectures that move toward greater autonomy, motivations, and the creation of goals. A
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9417b89b2d51d08f1314592fe721bfc3
https://doi.org/10.1109/jsyst.2015.2442995
https://doi.org/10.1109/jsyst.2015.2442995
Publikováno v:
Artificial Neural Networks and Machine Learning – ICANN 2019: Workshop and Special Sessions ISBN: 9783030304928
ICANN (Workshop)
ICANN (Workshop)
Contemporary artificial neural networks use various metrics to code input data and usually do not use temporal coding, unlike biological neural systems. Real neural systems operate in time and use the time to code external stimuli of various kinds to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f5ad8ddbaf7f882bb9056dfdd4962f0c
https://doi.org/10.1007/978-3-030-30493-5_56
https://doi.org/10.1007/978-3-030-30493-5_56
Autor:
Janusz A. Starzyk, Adrian Horzyk
Publikováno v:
IJCNN
This paper introduces the use of a new model of associative pulsing neurons (APN) for multi-class and multi-label classification tasks which are usually performed by separate artificial neural networks. The presented associative pulsing neurons have
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3e9fd7037158b2d603e14a1203923090
https://doi.org/10.1109/ijcnn.2018.8489176
https://doi.org/10.1109/ijcnn.2018.8489176