Boosting Neural Networks

By Holger Schwenk, Yoshua Bengio. 2000

320 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.

In Artificial Intelligence

Citations in the corpus

Machine Unlearning (2019, background): “Ensemble learning ap-3 Observe that this strategy holds even when the entire dataset D is replaced by the dataset for a particular country D c . proaches utilize boosting algorithms [46], even for ensembles of neural networks [47], to enhance accuracy.”
AdaBoost with SVM-based component classifiers (2008, methodology): “In this paper, we shall show that AdaBoost incorporating properly designed RBFSVM (SVM with the RBF kernel) component classifiers, which we call AdaBoostSVM, can perform as well as SVM.”
Neural Networks and Deep Learning (2018, unknown): “Boosting has also been used in the context of neural network learning [435].”
Scene Classification via a Gradient Boosting Random Convolutional Network Framework (2016, background): “In [26], Schwenk proposed adaptive boosting of a multilayer network for character recognition, which also obtained a significant improvement.”
Bagging, Boosting and the Random Subspace Method for Linear Classifiers (2002, background): “For instance, it was shown that bagging and boosting may be useful for perceptrons [12,13].”
Predicting subscriber dissatisfaction and improving retention in the wireless telecommunications industry (2000, unknown): “Adaboost [3] was used for the decision tree, and a variant of Adaboost appropriate when a classiﬁer produces conﬁdence ratings [8, 9] was used for the neural network.”
SelfieBoost: A Boosting Algorithm for Deep Learning (2014, methodology): “The celebrated analysis of AdaBoost guarantees that if at each boosting iteration the weak learner manages to produce a classifier which is slightly better than a random guess than after O(log(1/ )) iterations, AdaBoost returns an ensemble of classifiers whose training error is at most .”
Iterative Scaled Trust-Region Learning in Krylov Subspaces via Pearlmutter's Implicit Sparse Hessian-Vector Multiply (2003, methodology): “We used the 16-70-50-26 MLP (see [12]) (n=6,066) with 10 sets of different initial parameters randomly generated uniformly in the range [−0.”
Adaptive boosting for SAR automatic target recognition (2007, methodology): “Concerning AdaBoost, the literature reports success of many AdaBoost-based systems for pattern classification (e.g., [ 9 , 10]).”
Cost-sensitive boosting for classification of imbalanced data (2007, methodology): “In the past several years, many publications have reported that the AdaBoost algorithm has been successfully applied to most popular classifiers [25, 31, 81, 83].”
Comparison of random forest, artificial neural networks and support vector machine for intelligent diagnosis of rotating machinery (2018, background): “With the successful applications in the 1990s, ensemble learning has been proven to remarkably improve the accuracy and generalization capability of the whole system (Hansen et al., 1992; Schwenk and Bengio, 2000).”
SQANTI: extensive characterization of long-read transcript sequences for quality control in full-length transcriptome identification and quantification (2017, methodology): “Several machine learning methods were tested (Adaboost [Schwenk and Bengio 2000], CART [Breiman et al.”
Neural network ensemble strategies for financial decision applications (2005, methodology): “Schwenk and Bengio applied AdaBoost methods to neural network ensembles and report that boosting can signiÿcantly improve neural network classiÿers [37].”
An Introduction to Boosting and Leveraging (2002, methodology): “For instance [176] and earlier [55] and [112] used boosted ensembles of neural networks for OCR.”