Results 61 to 70 of about 762,608 (309)
Bounded-Distortion Metric Learning [PDF]
Metric learning aims to embed one metric space into another to benefit tasks like classification and clustering. Although a greatly distorted metric space has a high degree of freedom to fit training data, it is prone to overfitting and numerical ...
Jia, Jiaya+4 more
core
Collaborative Residual Metric Learning
Accepted by SIGIR ...
Tianjun Wei+2 more
openaire +2 more sources
From omics to AI—mapping the pathogenic pathways in type 2 diabetes
Integrating multi‐omics data with AI‐based modelling (unsupervised and supervised machine learning) identify optimal patient clusters, informing AI‐driven accurate risk stratification. Digital twins simulate individual trajectories in real time, guiding precision medicine by matching patients to targeted therapies.
Siobhán O'Sullivan+2 more
wiley +1 more source
Adaptive Multi-Proxy for Remote Sensing Image Retrieval
With the development of remote sensing technology, content-based remote sensing image retrieval has become a research hotspot. Remote sensing image datasets not only contain rich location, semantic and scale information but also have large intra-class ...
Xinyue Li+4 more
doaj +1 more source
Hierarchical Metric Learning for Optical Remote Sensing Scene Categorization
We address the problem of scene classification from optical remote sensing (RS) images based on the paradigm of hierarchical metric learning. Ideally, supervised metric learning strategies learn a projection from a set of training data points so as to ...
Banerjee, Biplab+2 more
core +1 more source
Metrics for Learning in Topological Persistence [PDF]
Comment: 16 pages, 8 ...
José Licón Saláiz, Henri Riihimaki
openaire +2 more sources
Spinal muscular atrophy (SMA) is a genetic disease affecting motor neurons. Individuals with SMA experience mitochondrial dysfunction and oxidative stress. The aim of the study was to investigate the effect of an antioxidant and neuroprotective substance, ergothioneine (ERGO), on an SMNΔ7 mouse model of SMA.
Francesca Cadile+8 more
wiley +1 more source
Kernelised reference‐wise metric learning
Unlike the doublet or triplet constraints, a novel kernelised reference‐wise metric learning is proposed by constructing reference‐wise constraints, which contain similarity information of each sample to all reference samples.
Meng Wu, Kai Luo, Daijin Li, Jun Zhou
doaj +1 more source
Deep Metric Learning via Facility Location
Learning the representation and the similarity metric in an end-to-end fashion with deep networks have demonstrated outstanding results for clustering and retrieval.
Jegelka, Stefanie+3 more
core +1 more source
Coordinated Local Metric Learning [PDF]
Mahalanobis metric learning amounts to learning a linear data projection, after which the L2 metric is used to compute distances. To allow more flexible metrics, not restricted to linear projections, local metric learning techniques have been developed.
Saxena, Shreyas, Verbeek, Jakob
openaire +3 more sources