98%
921
2 minutes
20
This paper proposes a least square regularized regression algorithm in sum space of reproducing kernel Hilbert spaces (RKHSs) for nonflat function approximation, and obtains the solution of the algorithm by solving a system of linear equations. This algorithm can approximate the low- and high-frequency component of the target function with large and small scale kernels, respectively. The convergence and learning rate are analyzed. We measure the complexity of the sum space by its covering number and demonstrate that the covering number can be bounded by the product of the covering numbers of basic RKHSs. For sum space of RKHSs with Gaussian kernels, by choosing appropriate parameters, we tradeoff the sample error and regularization error, and obtain a polynomial learning rate, which is better than that in any single RKHS. The utility of this method is illustrated with two simulated data sets and five real-life databases.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1109/TNNLS.2013.2242091 | DOI Listing |
Front Neurol
August 2025
Otolaryngology-Head and Neck Surgery, The Ohio State University Wexner Medical Center, Columbus, OH, United States.
Introduction: External continuous perturbations using a motion platform have been developed by employing either sum-of-sines (SoS) or a pseudorandom ternary sequence (PRTS) of numbers to quantify body sway evoked in the medial-lateral (ML) or anterior-posterior (AP) directions, which ultimately helps understand the human postural control system. These stimuli have been provided via pitch tilts of the motion platform for evaluations of AP balance responses or roll tilts for ML balance responses. However, little is known about whether a healthy postural control system responds to 2-dimensional (2D) perturbations similarly when the perturbation stimuli are provided in semicircular canal coordinates (i.
View Article and Find Full Text PDFGlob Adv Integr Med Health
September 2025
Native Hawaiian and Indigenous Health, Department of Public Health Sciences, University of Hawai'i at Mānoa, Honolulu, HI, USA.
Background: Integrative health efforts typically offer clinical services of Western and non-Western origin in a biomedical context. Indigenous communities and other minoritized populations would benefit from improved equity efforts in integrative healthcare.
Objective: As an approach to improve healthcare for Kānaka 'Ōiwi (Native Hawaiians), we explore multi-eyed seeing, an elaboration on two-eyed seeing, emphasizing decolonialism and adaptive use of healing traditions from multiple cultural backgrounds.
Wien Klin Wochenschr
September 2025
Department of Neurology, Medical University of Vienna, Vienna, Austria.
Background: Disease-modifying therapies with amyloid-antibodies will soon be available for patients with early Alzheimer's disease, which necessitates diagnostic and therapeutic resources in hospital and outpatient settings.
Methods: The Austrian Alzheimer Society developed an online questionnaire to survey Austrian hospital-based departments of neurology and psychiatry regarding resources for amyloid-antibody therapies.
Results: Between May and October 2023, 30 out of 41 neurology (73%) and 12 out of 33 psychiatry departments (36%) responded.
Front Nutr
August 2025
School of Management, Ocean University of China, and the Institute of Marine Development, Ocean University of China, Qingdao, China.
Fisheries are an important source of protein for humans. Currently, freshwater and coastal aquaculture fisheries, as well as capture fisheries, have reached saturation point in terms of development potential and are severely polluted, making the supply of aquatic products unsustainable. Deep-sea aquaculture utilizes the vast exploitable space of the open sea, breaking through the limitations of coastal waters and land.
View Article and Find Full Text PDFJ Chem Theory Comput
September 2025
Department of Mathematics, University of California, Berkeley, California 94720, United States.
When calculating properties of periodic systems at the thermodynamic limit (TDL), the dominant source of finite size error (FSE) arises from the long-range Coulomb interaction, and can manifest as a slowly converging quadrature error when approximating an integral in the reciprocal space by a finite sum. The singularity subtraction (SS) method offers a systematic approach for reducing this quadrature error and thus the FSE. In this work, we first investigate the performance of the SS method in the simplest setting, aiming at reducing the FSE in exact exchange calculations by subtracting the Coulomb contribution with a single, adjustable Gaussian auxiliary function.
View Article and Find Full Text PDF