Results 261 to 270 of about 7,006,651 (299)
Advanced Functional Materials, EarlyView.The physical realization of artificial neurons is a critical challenge for energy‐efficient neuromorphic computing. This review presents a comprehensive analysis of the evolution of artificial neuron implementations from conventional CMOS to emerging post‐CMOS technologies.
Kannan Udaya Mohanan +4 more
wiley +1 more source
Advanced Functional Materials, EarlyView.A defect‐engineered Ag/Gd2O3:Nb2O5/Pt rare earth composite oxide memristor enables stable multilevel reservoir states through pulse driven conductance modulation. Experimentally measured device responses are incorporated into a device aware reservoir computing framework for CIFAR‐100 image classification, highlighting the potential of rare earth ...
Hammad Ghazanfar +9 more
wiley +1 more source
Patient Re-Identification Based on Deep Metric Learning in Trunk Computed Tomography Images Acquired from Devices from Different Vendors. [PDF]
J Imaging Inform MedUeda Y, Ogawa D, Ishida T.
europepmc +1 more source
Kinetics‐Controlled Architecture of Binder‐Free Organic Electrodes for Enhanced Ion Transport
Advanced Functional Materials, EarlyView.Pulse reverse electrodeposition controls nucleation and growth to create hierarchically porous Py‐derived oligomeric electrodes with enhanced ionic accessibility and reduced transport resistance. The resulting binder‐free architectures translate these transport advantages into practical sodium‐storage functionality.
Satendra Kumar +1 more
wiley +1 more source
Deep Metric Learning: A Survey
Symmetry, 2019 Metric learning aims to measure the similarity among samples while using an optimal distance metric for learning tasks. Metric learning methods, which generally use a linear projection, are limited in solving real-world problems demonstrating non-linear ...
Hasan Sakir Bilge, Mahmut Kaya
exaly +3 more sources
Some of the next articles are maybe not open access.
Related searches:
Related searches:
Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium, 2000
We introduce an algorithm for learning a local metric to a continuous input space that measures distances in terms of relevance to the processing task. The relevance is defined as local changes in discrete auxiliary information, which may be for example the class of the data items, an index of performance, or a contextual input.
Samuel Kaski, Janne Sinkkonen
openaire +2 more sources
We introduce an algorithm for learning a local metric to a continuous input space that measures distances in terms of relevance to the processing task. The relevance is defined as local changes in discrete auxiliary information, which may be for example the class of the data items, an index of performance, or a contextual input.
Samuel Kaski, Janne Sinkkonen
openaire +2 more sources
Metric Learning for Text Documents
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006Many algorithms in machine learning rely on being given a good distance metric over the input space. Rather than using a default metric such as the Euclidean metric, it is desirable to obtain a metric based on the provided data. We consider the problem of learning a Riemannian metric associated with a given differentiable manifold and a set of points ...
Guy Lebanon
exaly +3 more sources
Proceedings of the AAAI Conference on Artificial Intelligence, 2018
Earth Mover's Distance (EMD), targeting at measuring the many-to-many distances, has shown its superiority and been widely applied in computer vision tasks, such as object recognition, hyperspectral image classification and gesture recognition.
Zizhao Zhang 0003 +3 more
openaire +1 more source
Earth Mover's Distance (EMD), targeting at measuring the many-to-many distances, has shown its superiority and been widely applied in computer vision tasks, such as object recognition, hyperspectral image classification and gesture recognition.
Zizhao Zhang 0003 +3 more
openaire +1 more source
2016 International Joint Conference on Neural Networks (IJCNN), 2016
The main theme of this paper is to develop a systematic framework to learn a Mahalanobis distance metric based on matrix sketching. Within this framework, we present a novel sketch metric learning algorithm which sequentially sketches the received samples from training dataset and formulates a new kind of constraint for metric learning.
Yuting Mai +4 more
openaire +2 more sources
The main theme of this paper is to develop a systematic framework to learn a Mahalanobis distance metric based on matrix sketching. Within this framework, we present a novel sketch metric learning algorithm which sequentially sketches the received samples from training dataset and formulates a new kind of constraint for metric learning.
Yuting Mai +4 more
openaire +2 more sources