Results 31 to 40 of about 2,910,377 (176)

Anti-periodicity on high-order inertial Hopfield neural networks involving mixed delays

Journal of Inequalities and Applications, 2020
This paper deals with a class of high-order inertial Hopfield neural networks involving mixed delays. Utilizing differential inequality techniques and the Lyapunov function method, we obtain a sufficient assertion to ensure the existence and global ...
Luogen Yao, Qian Cao
doaj   +1 more source

Theoretical characterization of uncertainty in high-dimensional linear classification

Machine Learning: Science and Technology, 2023
Being able to reliably assess not only the accuracy but also the uncertainty of models’ predictions is an important endeavor in modern machine learning. Even if the model generating the data and labels is known, computing the intrinsic uncertainty after ...
Lucas Clarté, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová   +3 more
doaj   +1 more source

Statistical Mechanics of Time Domain Ensemble Learning

, 2006
Conventional ensemble learning combines students in the space domain. On the other hand, in this paper we combine students in the time domain and call it time domain ensemble learning.
Freund Y., Hara K., Inoue J. I., Krogh A., Maeda Y., Miyoshi S., Miyoshi S., Miyoshi S., Miyoshi S., Miyoshi S., Nishimori H., Saad D., Urbanczik R.   +12 more
core   +1 more source

Improved multiscale attention based deep learning approach for automated sugarcane leaf disease detection using BSRI data

Scientific Reports
Early and accurate detection of sugarcane leaf diseases is critical for improving crop productivity and reducing economic losses in the agricultural sector.  Timely interventions enable sustainable crop management and better resource use.
Jannatul Mauya, Ruhul Amin, Md. Imam Hossain, Sabba Ruhi, Md. Shamim Reza   +4 more
doaj   +1 more source

Rethinking statistical learning theory: learning using statistical invariants [PDF]

Machine Learning, 2018
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Vladimir Vapnik, Rauf Izmailov
openaire   +1 more source

The geography of agriculture participation and food security in a small and a medium-sized city in Ghana

Agricultural and Food Economics, 2020
The debate about the contribution of urban agriculture to urban household food security has not considered the possible differential effects by geography of production activities, focusing either on urban household’s participation in agriculture ...
Hayford Mensah Ayerakwa, Fred Mawunyo Dzanku, Daniel Bruce Sarpong   +2 more
doaj   +1 more source

Non-linear Learning for Statistical Machine Translation

, 2015
Modern statistical machine translation (SMT) systems usually use a linear combination of features to model the quality of each translation hypothesis. The linear combination assumes that all the features are in a linear relationship and constrains that ...
Chen, Huadong, Chen, Jiajun, Dai, Xinyu, Huang, Shujian   +3 more
core   +1 more source

The extension of the largest generalized-eigenvalue based distance metric ) in arbitrary feature spaces to classify composite data points [PDF]

Genomics & Informatics, 2019
Analyzing patterns in data points embedded in linear and non-linear feature spaces is considered as one of the common research problems among different research areas, for example: data mining, machine learning, pattern recognition, and multivariate ...
Mosaab Daoud
doaj   +1 more source

Automatic Detection of Cognitive Impairment with Virtual Reality

Sensors, 2023
Cognitive impairment features in neuropsychiatric conditions and when undiagnosed can have a severe impact on the affected individual’s safety and ability to perform daily tasks.
Farzana A. Mannan, Lilla A. Porffy, Dan W. Joyce, Sukhwinder S. Shergill, Oya Celiktutan   +4 more
doaj   +1 more source

Fast rates in statistical and online learning [PDF]

, 2015
The speed with which a learning algorithm converges as it is presented with more data is a central problem in machine learning --- a fast rate of convergence means less data is needed for the same level of performance. The pursuit of fast rates in online
Grünwald, Peter D., Mehta, Nishant A., Reid, Mark D., van Erven, Tim, Williamson, Robert C.   +4 more
core   +1 more source