In this paper, we propose a method for referring to the real world to improve named entity recognition (NER) specialized for a domain. Our method adds a stacked autoencoder to a text-based deep neural network for NER. We first train the stacked auto-encoder only from the real world information, then the entire deep neural network from sentences annotated with NEs and accompanied by real world i...

This paper presents classification methods for electroencephalography (EEG) signals in imagination of direction measured by a portable EEG headset. In the authors’ previous studies, principal component analysis extracted significant features from EEG signals to construct neural network classifiers. To improve the performance, the authors have implemented a Stacked Autoencoder (SAE) for the clas...

We implement stacked denoising autoencoders, a class of neural networks that are capable of learning powerful representations of high dimensional data. We describe stochastic gradient descent for unsupervised training of autoencoders, as well as a novel genetic algorithm based approach that makes use of gradient information. We analyze the performance of both optimization algorithms and also th...

Recently deep learning has been successfully adopted in many applications such as speech recognition and image classification. In this work, we explore the possibility of employing deep learning in graph clustering. We propose a simple method, which first learns a nonlinear embedding of the original graph by stacked autoencoder, and then runs k-means algorithm on the embedding to obtain cluster...

The backpropagation algorithm for calculating gradients has been widely used in computation of weights for deep neural networks (DNNs). This method requires derivatives of objective functions and has some difficulties finding appropriate parameters such as learning rate. In this paper, we propose a novel approach for computing weight matrices of fully-connected DNNs by using two types of semi-n...