Faster Gated Recurrent Units via Conditional Computation

2016 ◽  
Author(s):  
Andrew S. Davis ◽  
Itamar Arel
Keyword(s):  
Gated Recurrent Units

G-CNN and double-referenced thresholding for detecting time series anomalies

2020 ◽  
pp. 1-12
Author(s):  
Liping Li ◽  
Zean Tian ◽  
Kenli Li ◽  
Cen Chen
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Series Data ◽  
Prediction Errors ◽  
Feedback Information ◽  
Public Datasets ◽  
Gated Recurrent Units ◽  
Control Feedback ◽  
Intermediate Output ◽  
Internet Company

Anomaly detection based on time series data is of great importance in many fields. Time series data produced by man-made systems usually include two parts: monitored and exogenous data, which respectively are the detected object and the control/feedback information. In this paper, a so-called G-CNN architecture that combined the gated recurrent units (GRU) with a convolutional neural network (CNN) is proposed, which respectively focus on the monitored and exogenous data. The most important is the introduction of a complementary double-referenced thresholding approach that processes prediction errors and calculates threshold, achieving balance between the minimization of false positives and the false negatives. The outstanding performance and extensive applicability of our model is demonstrated by experiments on two public datasets from aerospace and a new server machine dataset from an Internet company. It is also found that the monitored data is close associated with the exogenous data if any, and the interpretability of the G-CNN is discussed by visualizing the intermediate output of neural networks.

scholarly journals Forecasting Energy Consumption of Wastewater Treatment Plants with a Transfer Learning Approach for Sustainable Cities

Electronics ◽  
2021 ◽  
Vol 10 (10) ◽  
pp. 1149
Author(s):  
Pedro Oliveira ◽  
Bruno Fernandes ◽  
Cesar Analide ◽  
Paulo Novais
Keyword(s):  
Wastewater Treatment ◽  
Energy Consumption ◽  
Transfer Learning ◽  
Short Term Memory ◽  
Wastewater Treatment Plants ◽  
Learning Approach ◽  
Sustainable Cities ◽  
Short Term ◽  
Long Short Term Memory ◽  
Gated Recurrent Units

A major challenge of today’s society is to make large urban centres more sustainable. Improving the energy efficiency of the various infrastructures that make up cities is one aspect being considered when improving their sustainability, with Wastewater Treatment Plants (WWTPs) being one of them. Consequently, this study aims to conceive, tune, and evaluate a set of candidate deep learning models with the goal being to forecast the energy consumption of a WWTP, following a recursive multi-step approach. Three distinct types of models were experimented, in particular, Long Short-Term Memory networks (LSTMs), Gated Recurrent Units (GRUs), and uni-dimensional Convolutional Neural Networks (CNNs). Uni- and multi-variate settings were evaluated, as well as different methods for handling outliers. Promising forecasting results were obtained by CNN-based models, being this difference statistically significant when compared to LSTMs and GRUs, with the best model presenting an approximate overall error of 630 kWh when on a multi-variate setting. Finally, to overcome the problem of data scarcity in WWTPs, transfer learning processes were implemented, with promising results being achieved when using a pre-trained uni-variate CNN model, with the overall error reducing to 325 kWh.

scholarly journals TOXIFY: a deep learning approach to classify animal venom proteins

2019 ◽  
Author(s):  
T Jeffrey Cole ◽  
Michael S Brewer
Keyword(s):  
Protein Sequence ◽  
Software Package ◽  
Shotgun Proteomics ◽  
Learning Approach ◽  
The Novel ◽  
Venom Protein ◽  
Order Of Magnitude ◽  
Gated Recurrent Units ◽  
Venom Proteins ◽  
Generation Sequencing

In the era of Next-Generation Sequencing and shotgun proteomics, the sequences of animal toxigenic proteins are being generated at rates exceeding the pace of traditional means for empirical toxicity verification. To facilitate the automation of toxin identification from protein sequences, we trained Recurrent Neural Networks with Gated Recurrent Units on publicly available datasets. The resulting models are available via the novel software package TOXIFY, allowing users to infer the probability of a given protein sequence being a venom protein. TOXIFY is more than 20X faster and uses over an order of magnitude less memory than previously published methods. Additionally, TOXIFY is more accurate, precise, and sensitive at classifying venom proteins. Availability: https://www.github.com/tijeco/toxify

Sign in / Sign up

Export Citation Format

Share Document