Representation Learning: A Review and New Perspectives

Bengio, Yoshua; Courville, Aaron; Vincent, Pascal

doi:10.1109/tpami.2013.50

Cited by 10,502 publications

(6,751 citation statements)

References 117 publications

Supporting

Mentioning

6,286

Contrasting

Unclassified

Order By: Relevance

“…Using a large amount of data, the deep learning model automatically learns features or representations needed for given tasks such as classification and detection. This is why deep learning shows better results than traditional machine learning 39, 40, 41…”

Section: Discussionmentioning

confidence: 99%

An Algorithm Based on Deep Learning for Predicting In‐Hospital Cardiac Arrest

Kwon

Lee²,

Lee³

et al. 2018

JAHA

220

205

View full text Add to dashboard Cite

BackgroundIn‐hospital cardiac arrest is a major burden to public health, which affects patient safety. Although traditional track‐and‐trigger systems are used to predict cardiac arrest early, they have limitations, with low sensitivity and high false‐alarm rates. We propose a deep learning–based early warning system that shows higher performance than the existing track‐and‐trigger systems.Methods and ResultsThis retrospective cohort study reviewed patients who were admitted to 2 hospitals from June 2010 to July 2017. A total of 52 131 patients were included. Specifically, a recurrent neural network was trained using data from June 2010 to January 2017. The result was tested using the data from February to July 2017. The primary outcome was cardiac arrest, and the secondary outcome was death without attempted resuscitation. As comparative measures, we used the area under the receiver operating characteristic curve (AUROC), the area under the precision–recall curve (AUPRC), and the net reclassification index. Furthermore, we evaluated sensitivity while varying the number of alarms. The deep learning–based early warning system (AUROC: 0.850; AUPRC: 0.044) significantly outperformed a modified early warning score (AUROC: 0.603; AUPRC: 0.003), a random forest algorithm (AUROC: 0.780; AUPRC: 0.014), and logistic regression (AUROC: 0.613; AUPRC: 0.007). Furthermore, the deep learning–based early warning system reduced the number of alarms by 82.2%, 13.5%, and 42.1% compared with the modified early warning system, random forest, and logistic regression, respectively, at the same sensitivity.ConclusionsAn algorithm based on deep learning had high sensitivity and a low false‐alarm rate for detection of patients with cardiac arrest in the multicenter study.

show abstract

Section: Discussionmentioning

confidence: 99%

An Algorithm Based on Deep Learning for Predicting In‐Hospital Cardiac Arrest

Kwon

Lee²,

Lee³

et al. 2018

JAHA

220

205

View full text Add to dashboard Cite

show abstract

“…There are also systems which take advantage of the spatialtemporal [5] profile of the data [1] [9]. They are closer to the concept of the solution presented in this paper, which may be considered a hybrid approach since it features components of both schemes.…”

Section: A Object Classification In Video Streamsmentioning

confidence: 99%

Using Spatial Pooler of Hierarchical Temporal Memory for object classification in noisy video streams

Wielgosz

Pietroń

Wiatr

2016

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Abstract-This paper focuses on analyzing a Spatial Pooler (SP) of Hierarchical Temporal Memory (HTM) ability for facilitating object classification in noisy video streams. In particular, we seek to determine whether employing SP as a component of the video system increases overall robustness to noise. We have implemented our own version of HTM and applied it to object recognition tasks under various testing conditions. The system is composed of a video preprocessing block, a dimensionality reduction section which contains SP, a histograms collecting module and SVM classifier.Our experiments involve assessing performance of two different system setups (i.e. a version featuring SP and one without it) under various noise conditions with 32-frame video files. In order to make tests fair and repeatable the videos of several 3-D geometric shapes were artificially generated. Subsequently, Gaussian noise of a different intensity was introduced to the videos making them more indistinct. Such an approach mimics real-life scenarios where the system is taught ideal objects and then faces in its normal working conditions the challenge of detecting noisy ones.The results of the experiments reveal the superiority of the solution featuring Spatial Pooler over the one without it. Furthermore, the system with SP performed better also in the experiment without a noise component introduced and achieved a mean F1-score of 0.91 in ten trials.

show abstract

“…Specific domain knowledge can be used to help the design of the representations, with the possibility to use generic priors. New developments can be implemented in unsupervised feature learning and can include probabilistic models [23].…”

Section: Integrated Forensic Platform Projects At the Netherlands Formentioning

confidence: 99%

The interface between forensic science and technology: how technology could cause a paradigm shift in the role of forensic institutes in the criminal justice system

Kloosterman

Mapes

Geradts

et al. 2015

Phil. Trans. R. Soc. B

View full text Add to dashboard Cite

In this paper, the importance of modern technology in forensic investigations is discussed. Recent technological developments are creating new possibilities to perform robust scientific measurements and studies outside the controlled laboratory environment. The benefits of real-time, on-site forensic investigations are manifold and such technology has the potential to strongly increase the speed and efficacy of the criminal justice system. However, such benefits are only realized when quality can be guaranteed at all times and findings can be used as forensic evidence in court. At the Netherlands Forensic Institute, innovation efforts are currently undertaken to develop integrated forensic platform solutions that allow for the forensic investigation of human biological traces, the chemical identification of illicit drugs and the study of large amounts of digital evidence. These platforms enable field investigations, yield robust and validated evidence and allow for forensic intelligence and targeted use of expert capacity at the forensic institutes. This technological revolution in forensic science could ultimately lead to a paradigm shift in which a new role of the forensic expert emerges as developer and custodian of integrated forensic platforms.

show abstract

Representation Learning: A Review and New Perspectives

Cited by 10,502 publications

References 117 publications

An Algorithm Based on Deep Learning for Predicting In‐Hospital Cardiac Arrest

An Algorithm Based on Deep Learning for Predicting In‐Hospital Cardiac Arrest

Using Spatial Pooler of Hierarchical Temporal Memory for object classification in noisy video streams

The interface between forensic science and technology: how technology could cause a paradigm shift in the role of forensic institutes in the criminal justice system

Contact Info

Product

Resources

About