#### Filter Results:

#### Publication Year

1992

2016

#### Publication Type

#### Co-author

#### Key Phrase

#### Publication Venue

#### Data Set Used

Learn More

The problem of model selection, or determination of the number of hidden units, can be approached statistically, by generalizing Akaike's information criterion (AIC) to be applicable to unfaithful (i.e., unrealizable) models with general loss criteria including regularization terms. The relation between the training error and the generalization error is… (More)

In this paper we introduce a new technique for blind source separation of speech signals. We focus on the temporal structure of the signals in contrast to most other major approaches to this problem. The idea is to apply the decorrelation method proposed by Molgedey and Schuster in the time-frequency domain. We show some results of experiments with both… (More)

A statistical theory for overtraining is proposed. The analysis treats general realizable stochastic neural networks, trained with Kullback-Leibler divergence in the asymptotic case of a large number of training examples. It is shown that the asymptotic gain in the generalization error is small if we perform early stopping, even if we have access to the… (More)

We aim at an extension of AdaBoost to U-Boost, in the paradigm to build a stronger classification machine from a set of weak learning machines. A geometric understanding of the Bregman divergence defined by a generic convex function U leads to the U-Boost method in the framework of information geometry extended to the space of the finite measures over a… (More)

Learning is a flexible and effective means of extracting the stochastic structure of the environment. It provides an effective method for blind separation and deconvolution in signal processing. Two different types of learning are used, namely batch learning and on-line learning. The batch learning procedure uses all the training examples repeatedly so that… (More)

We construct new algorithms from scratch, which use the fourth order cumulant of stochastic variables for the cost function. The multiplicative updating rule here constructed is natural from the homogeneous nature of the Lie group and has numerous merits for the rigorous treatment of the dynamics. As one consequence, the second order convergence is shown.… (More)

Boosting is known as a gradient descent algorithm over loss functions. It is often pointed out that the typical boosting algorithm, Adaboost, is highly affected by outliers. In this letter, loss functions for robust boosting are studied. Based on the concept of robust statistics, we propose a transformation of loss functions that makes boosting algorithms… (More)

A statistical theory for overtraining is proposed. The analysis treats realizable stochastic neural networks, trained with Kullback-Leibler loss in the asymptotic case. It is shown that the asymptotic gain in the generalization error is small if we perform early stopping , even if we have access to the optimal stopping time. Considering cross-validation… (More)

An adaptive on-line algorithm extending the learning of learning idea is proposed and theoretically motivated. Relying only on gradient flow information it can be applied to learning continuous functions or distributions, even when no explicit loss function is given and the Hessian is not available. Its efficiency is demonstrated for a non-stationary blind… (More)