Results 31 to 40 of about 28,509 (255)
Perturbing low dimensional activity manifolds in spiking neuronal networks.
PLoS Computational Biology, 2019 Several recent studies have shown that neural activity in vivo tends to be constrained to a low-dimensional manifold. Such activity does not arise in simulated neural networks with homogeneous connectivity and it has been suggested that it is indicative ...
Emil Wärnberg, Arvind Kumar
doaj +1 more source
Multilabel Learning with Incomplete Using Dual-Manifold Mapping [PDF]
Jisuanji gongchengIn multilabel learning, the classification performance can be improved through the effective use of label correlations. However, owing to the subjectivity of manual tagging and the similarity of label semantics in practical applications, an incomplete ...
XU Zhilei, HUANG Rui
doaj +1 more source
Unsupervised Learning of Shape Manifolds [PDF]
Procedings of the British Machine Vision Conference 2007, 2007 Classical shape analysis methods use principal component analysis to reduce the dimensionality of shape spaces. The basic assumption behind these methods is that the subspace corresponding to the major modes of variation for a particular class of shapes is linearised. This may not necessarily be the case in practice.
Nasir M. Rajpoot +2 more
openaire +2 more sources
Adaptive Safe Semi-Supervised Extreme Machine Learning
IEEE Access, 2019 Semi-supervised learning (SSL) based on manifold regularization (MR) is an excellent learning framework. However, the performance of SSL heavily depends on the construction of manifold graph and the safety degrees of unlabeled samples.
Jun Ma, Chao Yuan
doaj +1 more source
, 2010 Mathematical formulation of certain natural phenomena exhibits group structure on topological spaces that resemble the Euclidean space only on a small enough scale, which prevents incorporation of conventional inference methods that require global vector norms.
openaire +1 more source
CoRR, 2019 Recent literature has shown that symbolic data, such as text and graphs, is often better represented by points on a curved manifold, rather than in Euclidean space. However, geometrical operations on manifolds are generally more complicated than in Euclidean space, and thus many techniques for processing and analysis taken for granted in Euclidean ...
Max Aalto, Nakul Verma
openaire +2 more sources
Learning on manifolds without manifold learning
Neural NetworksFunction approximation based on data drawn randomly from an unknown distribution is an important problem in machine learning. The manifold hypothesis assumes that the data is sampled from an unknown submanifold of a high dimensional Euclidean space.
Hrushikesh N. Mhaskar, Ryan O'Dowd
openaire +3 more sources
Joint Characterization of Sentinel-2 Reflectance: Insights from Manifold Learning
Remote Sensing, 2022 Most applications of multispectral imaging are explicitly or implicitly dependent on the dimensionality and topology of the spectral mixing space. Mixing space characterization refers to the identification of salient properties of the set of pixel ...
Daniel Sousa, Christopher Small
doaj +1 more source
CoRR, 2018 Recently proposed adversarial training methods show the robustness to both adversarial and original examples and achieve state-of-the-art results in supervised and semi-supervised learning. All the existing adversarial training methods consider only how the worst perturbed examples (i.e., adversarial examples) could affect the model output.
Shufei Zhang +3 more
openaire +2 more sources
A Nonparametric Model for Multi-Manifold Clustering with Mixture of Gaussians and Graph Consistency
Entropy, 2018 Multi-manifold clustering is among the most fundamental tasks in signal processing and machine learning. Although the existing multi-manifold clustering methods are quite powerful, learning the cluster number automatically from data is still a challenge.
Xulun Ye, Jieyu Zhao, Yu Chen
doaj +1 more source