Better Modelling Out-of-Distribution Regression on Distributed Acoustic Sensor Data Using Anchored Hidden State Mixup

02/23/2022
by   Hasan Asyari Arief, et al.
0

Generalizing the application of machine learning models to situations where the statistical distribution of training and test data are different has been a complex problem. Our contributions in this paper are threefold: (1) we introduce an anchored-based Out of Distribution (OOD) Regression Mixup algorithm, leveraging manifold hidden state mixup and observation similarities to form a novel regularization penalty, (2) we provide a first of its kind, high resolution Distributed Acoustic Sensor (DAS) dataset that is suitable for testing OOD regression modelling, allowing other researchers to benchmark progress in this area, and (3) we demonstrate with an extensive evaluation the generalization performance of the proposed method against existing approaches, then show that our method achieves state-of-the-art performance. Lastly, we also demonstrate a wider applicability of the proposed method by exhibiting improved generalization performances on other types of regression datasets, including Udacity and Rotation-MNIST datasets.

READ FULL TEXT

page 1

page 2

research
06/07/2019

Likelihood Ratios for Out-of-Distribution Detection

Discriminative neural networks offer little or no performance guarantees...
research
05/13/2019

Zoom To Learn, Learn To Zoom

This paper shows that when applying machine learning to digital zoom for...
research
06/29/2022

Towards out of distribution generalization for problems in mechanics

There has been a massive increase in research interest towards applying ...
research
05/08/2023

Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data

Decentralized learning enables the training of deep learning models over...
research
02/02/2023

Domain Generalization Emerges from Dreaming

Recent studies have proven that DNNs, unlike human vision, tend to explo...
research
04/05/2019

Modelling of Sound Events with Hidden Imbalances Based on Clustering and Separate Sub-Dictionary Learning

This paper proposes an effective modelling of sound event spectra with a...
research
05/26/2019

State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations

Machine learning promises methods that generalize well from finite label...

Please sign up or login with your details

Forgot password? Click here to reset