#### Filter Results:

- Full text PDF available (73)

#### Publication Year

1954

2017

- This year (3)
- Last 5 years (13)
- Last 10 years (22)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Brain Region

#### Key Phrases

#### Method

Learn More

We combine supervised learning with unsupervised learning in deep neural networks. The proposed model is trained to simultaneously minimize the sum of supervised and unsupervised cost functions by backpropagation, avoiding the need for layer-wise pre-training. Our work builds on top of the Ladder network proposed by Valpola [1] which we extend by combining… (More)

- Jaakko Särelä, Harri Valpola
- Journal of Machine Learning Research
- 2005

A new algorithmic framework called denoising source separation (DSS) is introduced. The main benefit of this framework is that it allows for easy development of new source separation algorithms which are optimised for specific problems. In this framework, source separation algorithms are constucted around denoising procedures. The resulting algorithms can… (More)

- Harri Valpola, Juha Karhunen
- Neural Computation
- 2002

A Bayesian ensemble learning method is introduced for unsupervised extraction of dynamic processes from noisy data. The data are assumed to be generated by an unknown nonlinear mapping from unknown factors. The dynamics of the factors are modeled using a nonlinear statespace model. The nonlinear mappings in the model are represented using multilayer… (More)

Blind separation of sources from their linear mixtures is a well understood problem. However, if the mixtures are nonlinear, this problem becomes generally very difficult. This is because both the nonlinear mapping and the underlying sources must be learned from the data in a blind manner, and the problem is highly ill-posed without a suitable… (More)

- Antti Rasmus, Harri Valpola, Mikko Honkala, Mathias Berglund, Tapani Raiko
- ArXiv
- 2015

We combine supervised learning with unsupervised learning in deep neural networks. The proposed model is trained to simultaneously minimize the sum of supervised and unsupervised cost functions by backpropagation, avoiding the need for layer-wise pre-training. Our work builds on the Ladder network proposed by Valpola (2015), which we extend by combining the… (More)

- Harri Valpola
- ArXiv
- 2014

A network supporting deep unsupervised learning is presented. The network is an autoencoder with lateral shortcut connections from the encoder to decoder at each level of the hierarchy. The lateral shortcut connections allow the higher levels of the hierarchy to focus on abstract invariant features. Whereas autoencoders are analogous to latent variable… (More)

- Harri Valpola, Markus Harva, Juha Karhunen
- Signal Processing
- 2004

In many models, variances are assumed to be constant although this assumption is known to be unrealistic. Joint modelling of means and variances can lead to infinite probability densities which makes it a difficult problem for many learning algorithms. We show that a Bayesian variational technique which is sensitive to probability mass instead of density is… (More)

The building blocks introduced earlier by us in [1] are used for constructing a hierarchical nonlinear model for nonlinear factor analysis. We call the resulting method hierarchical nonlinear factor analysis (HNFA). The variational Bayesian learning algorithm used in this method has a linear computational complexity, and it is able to infer the structure of… (More)

- Alexander Ilin, Harri Valpola
- Neural Processing Letters
- 2005

We show that the choice of posterior approximation affects the solution found in Bayesian variational learning of linear independent component analysis models. Assuming the sources to be independent a posteriori favours a solution which has orthogonal mixing vectors. Linear mixing models with either temporally correlated sources or non-Gaussian source… (More)

- Tapani Raiko, Harri Valpola, Yann LeCun
- AISTATS
- 2012

We transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model the linear dependencies instead. This transformation aims at separating the problems of learning the linear and nonlinear parts of the whole input-output mapping, which has many… (More)