The observer-assisted method for adjusting hyper-parameters in deep learning algorithms

Wielgosz, Maciej

doi:10.48550/arxiv.1611.10328

Cited by 1 publication

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The description of those approaches is beyond the scope of this paper, but it needs to be pointed out that most of those algorithms are not created with hardware implementation in mind. The authors are researching an automatic, resource-aware NN models hyper-parameters optimization, the preliminary concept of which is described in [67], to address this issue.…”

Section: Setup Improvementmentioning

confidence: 99%

“…Ultimately, the authors plan to develop an RL-based NN model optimization algorithm, the preliminary idea of which was presented in [67], and use it to simplify the process of the detector prototype implementation on an FPGA platform. an anomaly candidate maximum amplitude (measured as a distance between real and predicted sample quantization bin middles) that qualifies it as an anomaly cumulative amplitude threshold † sum of anomaly candidate amplitudes that qualifies it as an anomaly † various threshold values can be combined, creating a set of rules allowing to determine if an anomaly candidate is an anomaly Table B.12: Feature extractors used for OC-SVM [36,37].…”

Section: Future Workmentioning

confidence: 99%

See 1 more Smart Citation

The model of an anomaly detector for HiLumi LHC magnets based on Recurrent Neural Networks and adaptive quantization

Wielgosz

Mertik

Skoczeń

et al. 2018

Engineering Applications of Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

A B S T R A C TThis paper focuses on an examination of an applicability of Recurrent Neural Network models for detecting anomalous behavior of the CERN superconducting magnets. In order to conduct the experiments, the authors designed and implemented an adaptive signal quantization algorithm and a custom Gated Recurrent Unit-based detector and developed a method for the detector parameters selection.Three different datasets were used for testing the detector. Two artificially generated datasets were used to assess the raw performance of the system whereas the dataset intended for real-life experiments and model training was composed of the signals acquired from a new type of magnet, to be used during High-Luminosity Large Hadron Collider project. Several different setups of the developed anomaly detection system were evaluated and compared with state-of-the-art One Class Support Vector Machine (OC-SVM) reference model operating on the same data. The OC-SVM model was equipped with a rich set of feature extractors accounting for a range of the input signal properties.It was determined in the course of the experiments that the detector, along with its supporting design methodology, reaches F1 equal or very close to 1 for almost all test sets. Due to the profile of the data, the setup with the lowest maximum false anomaly length of the detector turned out to perform the best among all five tested configuration schemes of the detection system. The quantization parameters have the biggest impact on the overall performance of the detector with the best values of input/output grid equal to 16 and 8, respectively. The proposed solution of the detection significantly outperformed OC-SVM-based detector in most of the cases, with much more stable performance across all the datasets.

show abstract

Section: Setup Improvementmentioning

confidence: 99%