Soft Attention Convolutional Neural Networks for Rare Event Detection in Sequences

Mandar Kulkarni; Aria Abubakar

Soft Attention Convolutional Neural Networks for Rare Event Detection in Sequences

Signal Processing 2020-11-05 v1

Authors: Mandar Kulkarni , Aria Abubakar

Abstract

Automated event detection in the sequences is an important aspect of temporal data analytics. The events can be in the form of peaks, changes in data distribution, changes of spectral characteristics etc. In this work, we propose a Soft-Attention Convolutional Neural Network (CNN) based approach for rare event detection in sequences. For the purpose of demonstration, we experiment with well logs where we aim to detect events depicting the changes in the geological layers (a.k.a. well tops/markers). Well logs (single or multivariate) are inputted to a soft attention CNN and a model is trained to locate the marker position. Attention mechanism enables the machine to relatively scale the relevant log features for the task. Experimental results show that our approach is able to locate the rare events with high precision.

Keywords

deep learning for detection and classification neural networks for signal processing computer vision and image classification

Cite

@article{arxiv.2011.02338,
  title  = {Soft Attention Convolutional Neural Networks for Rare Event Detection in Sequences},
  author = {Mandar Kulkarni and Aria Abubakar},
  journal= {arXiv preprint arXiv:2011.02338},
  year   = {2020}
}

Comments

Accepted at NeuralIPS 2020 workshop on AI for Earth Sciences

Soft Attention Convolutional Neural Networks for Rare Event Detection in Sequences

Abstract

Keywords

Cite

Comments

Related papers