Training Methods for Adaptive Boosting of Neural Networks

By Holger Schwenk, Yoshua Bengio. 1997

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

A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines (2018, background): “Although the term autoencoder is the most popular nowadays, they were also known as autoassociative neural networks [38], diabolo networks [39] and replicator neural networks [40].”
Ensembles of Learning Machines (2002, methodology): “While in bagging the samples are drawn with replacement using a uniform probability distribution, in boosting methods the learning algorithm is called at each iteration using a different distribution or weighting over the training examples [111, 40, 112, 39, 115, 110, 32, 38, 33, 32, 16, 17, 42, 41]”
Improved Boosting Algorithms Using Confidence-rated Predictions (1998, methodology): “We base our work on Freund and Schapire’s (1997) AdaBoost algorithm which has received extensive empirical and theoretical study (Bauer & Kohavi, to appear; Breiman, 1998; Dietterich, to appear; Dietterich & Bakiri, 1995; Drucker & Cortes, 1996; Freund & Schapire, 1996; Maclin & Opitz, 1997; Margine”
A Short Introduction to Boosting (1999, methodology): “AdaBoost has been tested empirically by many researchers, including [3, 13, 15 , 29, 33, 36, 45].”
Boosting Algorithms as Gradient Descent in Function Space (2007, methodology): “For example, Freund and Schapire's AdaBoost algorithm [12] and Breiman's Bagging algorithm [3] have been found to give signi cant performance improvements over algorithms for the corresponding base classi ers [7, 11, 18, 6, 22, 2, 16], and have led to the study of many related algorithms [4, 21, 14,”
The Boosting Approach to Machine Learning An Overview (2003, methodology): “AdaBoost has been tested empirically by many researchers, i nclud ng [4, 18, 21, 40, 49, 59, 73].”
Boosting Neural Networks (2000, methodology): “This article extends and provides a deeper experimental analysis of our first experiments with the application of AdaBoost to neural networks ( Schwenk & Bengio, 1997, 1998 ).”
Advances in Large Margin Classifiers (2000, methodology): “The first bound on the fat shattering dimension of bounded linear functions in a finite dimensional space was obtained by Shawe-Taylor et al. [1998]. Gurvits [1997] generalized this to infinite dimensional Banach spaces.”