Adaptive and Learning Systems for Signal Processing, Communications, and Control

By Jay A. Farrell, Marios M. Polycarpou. 2006

280 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Kernels for Vector-Valued Functions: a Review (2011, background): “We will first describe a frequentist/discriminative perspective (see [29, 90, 86]).”
Optimal Rates for the Regularized Least-Squares Algorithm (2007, background): “We now introduce some basic concepts of statistical learning theory in the regression setting for vector-valued outputs (for details see [32], [15], [24], [6], [20] and references therein).”
A Baseline for the Multivariate Comparison of Resting-State Networks (2011, methodology): “Following square noise-free spatial ICA estimation (Hyvärinen et al., 2001), we can write X = AS ˆ ˆ where the generative linear latent variables ˆ ˆ A S and are the T 2 × T 2 mixing matrix related to subject TCs and the T 2 × V aggregate SM, respectively.”
Learning from MOM’s principles: Le Cam’s approach (2017, background): “These examples encompass classical empirical risk minimizers of Vapnik (1998) but also their robust versions from Huber (1964); Audibert and Catoni (2011).”
Hierarchical learning : theory with applications in speech and vision (2009, background): “Most learning algorithms critically depend on a suitably defined similarity measure, though the theory of learning so far provides no general rule to choose such a similarity measure [115, 28, 93, 29].”
Global characterization and monitoring of forest cover using Landsat data: opportunities and challenges (2012, methodology): “SVM is a group of relatively new machine learning algorithms designed to find optimal classification solutions (Vapnik 1998), which are achieved by using the optimal boundary between classes as the classification boundary.”
Capturing inter-subject variability with group independent component analysis of fMRI data: A simulation study (2012, methodology): “…with one of the sources Ŝc can be canceled by dividing the corresponding column of Â by the same scalar: X ¼ Â Ŝ ¼ XC c¼1 1 αc Âc αcŜ cÞ: Though arbitrary scaling has long been discussed in the context of ICA (Hyvärinen et al., 2001), the implications for GICA have not been appreciated.”
Support Vector Machines for TCP traffic classification (2009, methodology): “Starting from the binary SVM technique [9], several extensions have been proposed to make SVMs suitable to deal with multi-class classification problems [15].”
Comparison and evaluation of advanced motion models for vehicle tracking (2008, background): “β can be set to 2 if Gaussian distributions are assumed, while κ = 3− L (see [10] for details).”
Feature Extraction for Hyperspectral Imagery: The Evolution From Shallow to Deep: Overview and Toolbox (2020, methodology): “ICA assumes a linear mixture model of the non-Gaussian independent source signals and the mixing matrix which both are simultaneously estimated and therefore ICA is referred to as blind source separation.”
Spectral Methods for Regularization in Learning Theory (2006, methodology): “In machine learning the idea to use regularization goes back to Poggio and Girosi (1992) and the connection between large margin kernel methods such as Support Vector Machines and regularization is well known (see Vapnik (1998), Evgeniou et al. (2000) and reference therein).”
Understanding deep learning requires rethinking generalization (2016, methodology): “These include VC dimension (Vapnik, 1998), Rademacher complexity (Bartlett & Mendelson, 2003), and uniform stability (Mukherjee et al., 2002; Bousquet & Elisseeff, 2002; Poggio et al., 2004).”
On regularization algorithms in learning theory (2007, methodology): “Moreover if ε(n) decreases fast enough, the Borel-Cantelli Lemma allows to derive almost sure convergence of ‖f z − fρ‖ρ → 0 as n goes to ∞, namely strong consistency (Vapnik, 1998; Devroye et al., 1996).”
Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels (2019, background): “Without label corruption, the generalization error can be bounded by complexity measures such as VC dimension (Vapnik, 1998), Rademacher complexity (Bartlett & Mendelson, 2002) and uniform stability (Mukherjee et al., 2002; Bousquet & Elisseeff, 2002; Poggio et al., 2004).”