Results 31 to 40 of about 10,369,018 (353)
Unconstrained neighbor selection for minimum reconstruction error-based K-NN classifiers
Complex & Intelligent Systems, 2023 It is essential to define more convincing and applicable classifiers for small datasets. In this paper, a minimum reconstruction error-based K-nearest neighbors (K-NN) classifier is proposed. We propose a new neighbor selection method.
Rassoul Hajizadeh
doaj +1 more source
Deep learning in deep time [PDF]
Proceedings of the National Academy of Sciences, 2020 Digitized natural history records, now numbering in the billions (1), span widely across the tree of life and provide the foundation for numerous recent advances in biodiversity research (2, 3). Mechanistic insights are emerging for old questions, including how diversity has expanded and contracted through Earth’s history (4), how species have come to ...
openaire +2 more sources
The Journal of Neuroscience, 2018 Animals successfully thrive in noisy environments with finite resources. The necessity to function with resource constraints has led evolution to design animal brains (and bodies) to be optimal in their use of computational power while being adaptable to their environmental niche.
Shyam Srinivasan +3 more
openaire +2 more sources
Machine Learning, 2023 AbstractThis paper presents a novel holistic deep learning framework that simultaneously addresses the challenges of vulnerability to input perturbations, overparametrization, and performance instability from different train-validation splits. The proposed framework holistically improves accuracy, robustness, sparsity, and stability over standard deep ...
Dimitris Bertsimas +5 more
openaire +3 more sources
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation [PDF]
Computer Vision and Pattern Recognition, 2016 Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessarily voluminous and causes issues. In
C. Qi, Hao Su, Kaichun Mo, L. Guibas
semanticscholar +1 more source
Revista Brasileira de Ensino de Física, 2022 As a consequence of its capability of creating high level abstractions from data, deep learning has been effectively employed in a wide range of applications, including physics. Though deep learning can be, at first and simplistically understood in terms of very large neural networks, it also encompasses new concepts and methods. In order to understand
Arruda, Henrique F. de +3 more
openaire +4 more sources
Epilepsia Open, 2023 Objective As of 2022, 36 anti‐seizure medications (ASMs) have been licensed for the treatment of epilepsy, however, adverse effects (AEs) are commonly reported.
Kazuyuki Fukushima +14 more
doaj +1 more source
Understanding deep learning (still) requires rethinking generalization
Communications of the ACM, 2021 Despite their massive size, successful deep artificial neural networks can exhibit a remarkably small gap between training and test performance. Conventional wisdom attributes small generalization error either to properties of the model family or to the ...
Chiyuan Zhang +4 more
semanticscholar +1 more source
Deep learning-based anomalous object detection system powered by microcontroller for PTZ cameras [PDF]
, 2018 Automatic video surveillance systems are usually designed to detect anomalous objects being present in a scene or behaving dangerously. In order to perform adequately, they must incorporate models able to achieve accurate pattern recognition in an image,
Benito Picazo, Jesús +4 more
core +1 more source
SN Computer Science, 2021 Deep learning (DL), a branch of machine learning (ML) and artificial intelligence (AI) is nowadays considered as a core technology of today’s Fourth Industrial Revolution (4IR or Industry 4.0).
Iqbal H. Sarker
semanticscholar +1 more source