Results 271 to 280 of about 63,696 (324)

Vector-valued Reproducing Kernel Banach Spaces with Applications to Multi-task Learning

, 2011
Haizhang Zhang, Jun Zhang
openalex   +2 more sources

Increasing limit of reproducing kernels

Rocky Mountain Journal of Mathematics, 2011
openaire   +2 more sources

EndoARSS: Adapting Spatially Aware Foundation Model for Efficient Activity Recognition and Semantic Segmentation in Endoscopic Surgery

Advanced Intelligent Systems, EarlyView.
This article introduces EndoARSS, a novel multitask learning framework that combines surgical activity recognition and semantic segmentation for endoscopic surgery. Utilizing the foundation model with novel modules like task efficient shared low‐rank adapters and spatially aware multiscale attention, EndoARSS can effectively tackle challenges in ...
Guankun Wang, Rui Tang, Mengya Xu, Long Bai, Huxin Gao, Hongliang Ren   +5 more
wiley   +1 more source

Harnessing Nonidealities in Analog In‐Memory Computing Circuits: A Physical Modeling Approach for Neuromorphic Systems

Advanced Intelligent Systems, EarlyView.
This work harnesses nonidealities in analog in‐memory computing (IMC) by training physical neural networks modeled with ordinary differential equations. A differentiable spike‐time discretization accelerates training by 20× and reduces memory usage by 100×, enabling large IMC‐equivalent models to learn the CIFAR‐10 dataset.
Yusuke Sakemi, Yuji Okamoto, Takashi Morie, Sou Nobukawa, Takeo Hosomi, Kazuyuki Aihara   +5 more
wiley   +1 more source

α-decay half-life predictions with support vector machine. [PDF]

Sci Rep
Jalili A, Pan F, Draayer JP, Chen AX, Ren Z.   +4 more
europepmc   +1 more source

Rapid and Precise Geometric Measurement of Injection‐Molded Axial Fans Using Convolutional Neural Network Regression

Advanced Intelligent Systems, EarlyView.
This study presents a vision‐based artificial intelligence (AI) system that rapidly and accurately measures deformation in injection‐molded axial fan blades. By combining deep learning with explainable AI techniques, the system achieves high prediction accuracy while reducing inspection time by over 90%.
Keuntae Baek, Sanghun Shin, Minhyeok Kim, Jaemin Oh, Yeong Bin Kim, Myong Dok Kim, Hongyun So   +6 more
wiley   +1 more source

The FBA solution space kernel: introduction and illustrative examples. [PDF]

BMC Bioinformatics
Verwoerd WS, Mao L.
europepmc   +1 more source

Is Computing with Light All You Need? A Perspective on Codesign for Optical Artificial Intelligence and Scientific Computing

Advanced Intelligent Systems, EarlyView.
This perspective article considers what computations optical computing can and should enable. Focusing upon free‐space optical computing, it argues that a codesign approach whereby materials, devices, architectures, and algorithms are simultaneously optimized is needed.
Prasad P. Iyer, Gaurang R. Bhatt, Saaketh Desai, Elliot J. Fuller, Corinne M. Teeter, François Léonard, Craig M. Vineyard   +6 more
wiley   +1 more source

Rapid Assessment of Virtually Synthesizable Chemical Structures via Support Vector Machine Models. [PDF]

Mol Inform
Iwasaki Y, Miyao T.
europepmc   +1 more source

BiT‐HyMLPKANClassifier: A Hybrid Deep Learning Framework for Human Peripheral Blood Cell Classification Using Big Transfer Models and Kolmogorov–Arnold Networks

Advanced Intelligent Systems, EarlyView.
This study presents BiT‐HyMLPKANClassifier, a novel hybrid deep learning framework for automated human peripheral blood cell classification. Model combines Big Transfer models with multilayer perceptron and efficient Kolmogorov–Arnold Network architectures, achieving over 97% accuracy.
Ömer Miraç KÖKÇAM, Ferhat UÇAR
wiley   +1 more source