We review a neural implementation of the statistical technique of Canonical Correlation Analysis (CCA) and extend it to nonlinear CCA. We then derive the method of kernel-based CCA and compare these two methods on real and artificial data sets before using both on the Blind Separation of Sources.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1142/S012906570000034X | DOI Listing |
Mach Learn Clin Neuroimaging (2024)
December 2024
Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA, USA.
Many longitudinal neuroimaging studies aim to improve the understanding of brain aging and diseases by studying the dynamic interactions between brain function and cognition. Doing so requires accurate encoding of their multidimensional relationship while accounting for individual variability over time. For this purpose, we propose an unsupervised learning model (called ntrastive Learning-based ph Generalized nonical Correlation Analysis (CoGraCa)) that encodes their relationship via Graph Attention Networks and generalized Canonical Correlational Analysis.
View Article and Find Full Text PDFPLoS Pathog
January 2025
Department of Microbiology, Immunology and Pathology, College of Veterinary Medicine and Biomedical Sciences, Colorado State University, Fort Collins, Colorado, USA.
The mosquito midgut functions as a key interface between pathogen and vector. However, studies of midgut physiology and virus infection dynamics are scarce, and in Culex tarsalis-an extremely efficient vector of West Nile virus (WNV)-nonexistent. We performed single-cell RNA sequencing on Cx.
View Article and Find Full Text PDFHum Brain Mapp
February 2025
U1172 - LilNCog (Lille Neuroscience & Cognition), Univ. Lille, Inserm, CHU Lille, Lille, France.
Over a third of minor stroke patients experience post-stroke cognitive impairment (PSCI), but no validated tools exist to identify at-risk patients early. This study investigated whether disconnection features derived from infarcts and white matter hyperintensities (WMH) could serve as markers for short- and long-term cognitive decline in first-ever minor ischemic stroke patients. First-ever minor ischemic stroke patients (NIHSS ≤ 7) were prospectively followed at 72-h, 6 months, and 36 months post-stroke with cognitive tests and brain MRI.
View Article and Find Full Text PDFSchizophr Res
January 2025
Department of Psychiatry, Beth Israel Deaconess Medical Center, Boston, MA, USA; Department of Psychiatry, Harvard Medical School, Boston, MA, USA. Electronic address:
Background: Past studies associating personality with psychosis have been limited by small nonclinical samples and a focus on general symptom burden. This study uses a large clinical sample to examine personality's relationship with psychosis-specific features and compare personality dimensions across clinically and neurobiologically defined categories of psychoses.
Methods: A total of 1352 participants with schizophrenia, schizoaffective disorder, and bipolar with psychosis, as well as 623 healthy controls (HC), drawn from the Bipolar-Schizophrenia Network for Intermediate Phenotypes (BSNIP-2) study, were included.
J Clin Med
January 2025
Loricorps Research Unity, Research Center of Mental Health University Institute of Montreal (CR-IUSMM), 7331, Rue Hochelaga, Montreal, QC H1N 3V2, Canada.
Body image disturbance has been associated with various health conditions and has the potential to trigger the development of unhealthy behaviors, including dysfunctional attitudes and eating behaviors, which may evolve into eating disorders. This study explores the relationship between body image variables-such as global self-worth, physical self-worth, and physical attractiveness-and the continuum of eating attitudes and behaviors. A canonical correlation analysis was performed to assess the multivariate relationship between attitudinal and perceptual variables and the continuum of eating behaviors, with a total of 113 cases analyzed.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!