We present a new deep neural network architecture, motivated by sparse random matrix theory that uses a low-complexity embedding through a sparse matrix instead of a conventional stacked autoencoder. We regard autoencoders as an information-preserving dimensionality reduction method, similar to random projections in compressed sensing. Thus, exploiting recent theory on sparse matrices for dimen...

Capsule networks are a type of neural network that use the spatial relationship between features to classify images. By capturing poses and relative positions features, this is better able recognize affine transformation surpass traditional convolutional (CNNs) when handling translation, rotation, scaling. The stacked capsule autoencoder (SCAE) state-of-the-art encodes an image in capsules whic...

Unsupervised domain adaptation involves knowledge transfer from a labeled source to unlabeled target domains assist learning tasks. A critical aspect of unsupervised is the more transferable and distinct feature representations different domains. Although previous investigations, using, for example, CNN-based auto-encoder-based methods, have produced remarkable results in adaptation, there are ...

We have two main contributions in this work: 1. We explore the usage of a stacked denoising autoencoder, and a paragraph vector model to learn task-independent dense patient representations directly from clinical notes. We evaluate these representations by using them as features in multiple supervised setups, and compare their performance with those of sparse representations. 2. To understand a...

Protein structure prediction is an important problem in computational biology, and is widely applied to various biomedical problems such as protein function study, protein design, and drug design. In this work, we developed a novel deep learning approach based on a deeply stacked denoising autoencoder for protein structure reconstruction. We applied our approach to a template-based protein stru...

We use an autoencoder composed of stacked restricted Boltzmann machines to extract features from the history of individual stock prices. Our model is able to discover an enhanced version of the momentum effect in stocks without extensive hand-engineering of input features and deliver an annualized return of 45.93% over the 1990-2009 test period versus 10.53% for basic momentum.