Deep learning, which is a subfield of machine learning, has opened a new era for the
development of neural networks. The auto-encoder is a key component of deep structure …

Autoencoder is an unsupervised learning model, which can automatically learn data
features from a large number of samples and can act as a dimensionality reduction method …

Autoencoders have become a hot researched topic in unsupervised learning due to their
ability to learn data features and act as a dimensionality reduction method. With rapid …

The concept of autoencoder was originally proposed by LeCun in 1987, early works on
autoencoder were used for dimensionality reduction or feature learning. Recently, with the …

Modeling complex correlations on multiview data is still challenging, especially for high-
dimensional features with possible noise. To address this issue, we propose a novel …

We propose a multi-step training method for designing generalized linear classifiers. First,
an initial multi-class linear classifier is found through regression. Then validation error is …

Autoencoders (AE) aim to reproduce the output from the input. They may hence tend to
overfit towards learning the identity-function between the input and output, ie, they may …

Despite their great success in practical applications, there is still a lack of theoretical and
systematic methods to analyze deep neural networks. In this paper, we illustrate an …

The autoencoder is an effective unsupervised learning model which is widely used in deep
learning. It is well known that an autoencoder with a single fully-connected hidden layer, a …

Learning on data represented with multiple views (eg, multiple types of descriptors or
modalities) is a rapidly growing direction in machine learning and computer vision. Although …