In this thesis, nonnegative matrix factorization (NMF) is viewed as a feedbackward neural network and generalized to a deep convolutional architecture with forwardpropagation under β-divergence. NMF and feedfoward neural networks are put in relation and a new class of autoencoders is proposed, namely the nonnegative autoencoders. It is shown that NMF is essentially the decoder part of an autoencoder with nonnegative weights and input. The shallow autoencoder with fully connected neurons is extended to a deep convolutional autoencoder with the same properties. Multiplicative factor updates are used to ensure nonnegativity of the weights in the network. As a result, a shallow nonnegative autoencoder (NAE), a shallow convolutional nonnegative ...
Nonnegative matrix factorization (NMF) is an unsupervised learning method for decomposing high-dimen...
Abstract Nonnegative Matrix Factorization (NMF) has been proved to be valuable in many ap-plications...
In recent years, although deep neural networks have yielded immense success in solving various recog...
This paper proposes new nonnegative (shallow and multi-layer) autoencoders by combining the spiking ...
In this thesis, new variants of nonnegative matrix factorization (NMF) based ona convolutional data ...
A new shallow multi-layer auto-encoder that combines the spiking Random Neural Network (RNN) with th...
Nonnegative matrix factorization (NMF) has been success-fully applied to different domains as a tech...
Non-negative matrix factorization (NMF) has been widely used for challenging single-channel audio so...
With ever greater computational resources and more accessible software, deep neural networks have be...
We consider the existence of fixed points of nonnegative neural networks, i.e., neural networks that...
International audienceThis paper introduces improvements to nonnegative feature learning-based metho...
A recurrent neural network solving the approximate nonnegative matrix factorization (NMF) problem is...
In order to perform object recognition it is necessary to learn representations of the underlying c...
à paraître dans Neural ComputationThis paper describes algorithms for nonnegative matrix factorizati...
Nonnegative matrix factorization (NMF) has drawn considerable interest in recent years due to its im...
Nonnegative matrix factorization (NMF) is an unsupervised learning method for decomposing high-dimen...
Abstract Nonnegative Matrix Factorization (NMF) has been proved to be valuable in many ap-plications...
In recent years, although deep neural networks have yielded immense success in solving various recog...
This paper proposes new nonnegative (shallow and multi-layer) autoencoders by combining the spiking ...
In this thesis, new variants of nonnegative matrix factorization (NMF) based ona convolutional data ...
A new shallow multi-layer auto-encoder that combines the spiking Random Neural Network (RNN) with th...
Nonnegative matrix factorization (NMF) has been success-fully applied to different domains as a tech...
Non-negative matrix factorization (NMF) has been widely used for challenging single-channel audio so...
With ever greater computational resources and more accessible software, deep neural networks have be...
We consider the existence of fixed points of nonnegative neural networks, i.e., neural networks that...
International audienceThis paper introduces improvements to nonnegative feature learning-based metho...
A recurrent neural network solving the approximate nonnegative matrix factorization (NMF) problem is...
In order to perform object recognition it is necessary to learn representations of the underlying c...
à paraître dans Neural ComputationThis paper describes algorithms for nonnegative matrix factorizati...
Nonnegative matrix factorization (NMF) has drawn considerable interest in recent years due to its im...
Nonnegative matrix factorization (NMF) is an unsupervised learning method for decomposing high-dimen...
Abstract Nonnegative Matrix Factorization (NMF) has been proved to be valuable in many ap-plications...
In recent years, although deep neural networks have yielded immense success in solving various recog...