Zobrazeno 1 - 10
of 379
pro vyhledávání: '"A P, Davel"'
Autor:
Mouton, Coenraad, Rabe, Randle, Haasbroek, Daniël G., Theunissen, Marthinus W., Potgieter, Hermanus L., Davel, Marelie H.
It has been observed that the input space of deep neural network classifiers can exhibit `fragmentation', where the model function rapidly changes class as the input space is traversed. The severity of this fragmentation tends to follow the double de
Externí odkaz:
http://arxiv.org/abs/2411.04695
Understanding generalization in deep neural networks is an active area of research. A promising avenue of exploration has been that of margin measurements: the shortest distance to the decision boundary for a given sample or its representation intern
Externí odkaz:
http://arxiv.org/abs/2308.15466
Publikováno v:
In Communications in Computer and Information Science, vol 1734. Springer, Cham (2022)
Classification margins are commonly used to estimate the generalization ability of machine learning models. We present an empirical study of these margins in artificial neural networks. A global estimate of margin size is usually used in the literatu
Externí odkaz:
http://arxiv.org/abs/2302.06925
Publikováno v:
Speech Communication, 143, pp.10-20 (2022)
We propose a new framework to improve automatic speech recognition (ASR) systems in resource-scarce environments using a generative adversarial network (GAN) operating on acoustic input features. The GAN is used to enhance the features of mismatched
Externí odkaz:
http://arxiv.org/abs/2210.00721
Publikováno v:
Environmental and Sustainability Indicators, Vol 24, Iss , Pp 100526- (2024)
Research-for-development (R4D) refers to research activities specifically designed to address critical social, environmental, and economic challenges and improve human well-being. It is essential to have well-designed indicators to monitor and evalua
Externí odkaz:
https://doaj.org/article/118879f3b7704c2e8430d868c21c31f7
Autor:
Wenyi Xu, Alexa D. Monachino, Sarah A. McCormick, Emma T. Margolis, Ana Sobrino, Cara Bosco, Cassandra J. Franke, Lauren Davel, Michal R. Zieff, Kirsten A. Donald, Laurel J. Gabard-Durnam, Santiago Morales
Publikováno v:
Developmental Cognitive Neuroscience, Vol 70, Iss , Pp 101458- (2024)
EEG studies play a crucial role in enhancing our understanding of brain development across the lifespan. The increasing clinical and policy implications of EEG research underscore the importance of utilizing reliable EEG measures and increasing the r
Externí odkaz:
https://doaj.org/article/c95a96aff5ea46dc91686b0f23bdd6d4
Publikováno v:
Regepe Entrepreneurship and Small Business Journal, Vol 13, Iss 2 (2024)
Objective: To discuss how entrepreneurial education can help students develop emotional resilience through the educational practice of artistic entrepreneurship. Methodology/approach: Qualitative, inductive and interpretive methodological approach us
Externí odkaz:
https://doaj.org/article/ff57e329eb594842912ec2deeb357773
Resiliência emocional na educação empreendedora: A prática educacional do empreendedorismo artístico
Publikováno v:
Regepe Entrepreneurship and Small Business Journal, Vol 13, Iss 2 (2024)
Objetivo: Discutir como a educação empreendedora pode ajudar os estudantes a desenvolver a resiliência emocional, a partir da prática educacional do empreendedorismo artístico. Metodologia/abordagem: Abordagem metodológica de caráter qualita
Externí odkaz:
https://doaj.org/article/d92318a14d0a41598ff6a9466e4b5c71
Autor:
Nwabisa Mlandu, Sarah A. McCormick, Lauren Davel, Michal R. Zieff, Layla Bradford, Donna Herr, Chloë A. Jacobs, Anele Khumalo, Candice Knipe, Zamazimba Madi, Thandeka Mazubane, Bokang Methola, Tembeka Mhlakwaphalwa, Marlie Miles, Zayaan Goolam Nabi, Rabelani Negota, Khanyisa Nkubungu, Tracy Pan, Reese Samuels, Sadeeka Williams, Simone R. Williams, Trey Avery, Gaynor Foster, Kirsten A. Donald, Laurel J. Gabard-Durnam
Publikováno v:
Developmental Cognitive Neuroscience, Vol 67, Iss , Pp 101396- (2024)
Electroencephalography (EEG) is an important tool in the field of developmental cognitive neuroscience for indexing neural activity. However, racial biases persist in EEG research that limit the utility of this tool. One bias comes from the structure
Externí odkaz:
https://doaj.org/article/5ddac0dd4163431eb1f995329bb709a8
Publikováno v:
Artificial Intelligence Research 2022
Mismatched data is a challenging problem for automatic speech recognition (ASR) systems. One of the most common techniques used to address mismatched data is multi-style training (MTR), a form of data augmentation that attempts to transform the train
Externí odkaz:
http://arxiv.org/abs/2202.07219