Autoencoders, a type of unsupervised neural network, are exactly one of the models. In the following sections, we will apply three different autoencoders which are simple autoencoder, deep ...

An autoencoder is a type of artificial neural network which can learn both linear and non-linear representations of the data, and use the learned representations to reconstruct the original data.

First, we prove that neural networks that combine two types of neurons have superior theoretical approximation efficiency compared with networks comprising solely homogeneous neurons. Second, we ...

In our study, a new computational method via deep forest ensemble learning based on autoencoder (DFELMDA) is proposed to predict miRNA–disease associations. Specifically, a new feature representation ...