Bio-electrochemical reactor provides a promising technology to remove nitrogen contaminants in water. In this study, a heterotrophic biofilm for denitrification process was developed, and stable total nitrogen removal efficiencies (>80%) were achieved. Fluorescence in situ hybridization showed that genes norB mainly transcribed in inner biofilm while genes nosZ showed similar transcription acti...

Restricted Boltzmann Machines are commonly used in unsupervised learning to extract features from training data. Since these features are learned for regenerating training data a classifier based on them has to be trained. If only a few of the learned features are discriminative other non-discriminative features will distract the classifier during the training process and thus waste computing r...

In this paper, we propose a novel graph-based approach for semi-supervised learning problems, which considers an adaptive adjacency of the examples throughout the unsupervised portion of the training. Adjacency of the examples is inferred using the predictions of a neural network model which is first initialized by a supervised pretraining. These predictions are then updated according to a nove...

Recently, it has been observed that when representations are learnt in a way that encourages sparsity, improved performance is obtained on classification tasks. These methods involve combinations of activation functions, sampling steps and different kinds of penalties. To investigate the effectiveness of sparsity by itself, we propose the “k sparse autoencoder”, which is an autoencoder with lin...

Spectral algorithms for learning low-dimensional data manifolds have largely been supplanted by deep learning methods in recent years. One reason is that classic spectral manifold learning methods often learn collapsed embeddings that do not fill the embedding space. We show that this is a natural consequence of data where different latent dimensions have dramatically different scaling in obser...

The major aetiological agent of human bacterial meningitis is Neisseria meningitidis. During the course of disease and host colonization, the bacterium has to withstand limited oxygen availability. Nitrogen oxide and nitrogen oxyanions are thought to be present, which may constitute an alternative sink for electrons from the N. meningitidis respiratory chain. A partial denitrification pathway i...

Deep generative models with multiple hidden layers have been shown to be able to learn meaningful and compact representations of data. In this work we propose deep energy models, which use deep feedforward neural networks to model the energy landscapes that define probabilistic models. We are able to efficiently train all layers of our model simultaneously, allowing the lower layers of the mode...

The human visual system is able to recognize objects despite transformations that can drastically alter their appearance. To this end, much effort has been devoted to the invariance properties of recognition systems. Invariance can be engineered (e.g. convolutional nets), or learned from data explicitly (e.g. temporal coherence) or implicitly (e.g. by data augmentation). One idea that has not, ...

An Internet based Distributed Control System (DCS) is presented in this paper for monitoring real time data using ordinary web browser. Each DCS will be connected to the central server which will be the system web server. The proposed system is based on the three-tier client-server model. The application server is written in C#.Net. SQL database server 2005 is used for all the DCSs local databa...