Machine Learning Operations (MLOPS) Architecture Considerations for Deep Learning with a Passive Acoustic Vector Sensor
Abstract
As machine learning augmented decision-making becomes more prevalent, defense applications for these techniques are needed to prevent being outpaced by peer adversaries. One area that has significant potential is deep learning applications to classify passive sonar acoustic signatures, which would accelerate tactical, operational, and strategic decision-making processes in one of the most contested and difficult warfare domains. Convolutional Neural Networks have achieved some of the greatest success in accomplishing this task; however, a full production pipeline to continually train, deploy, and evaluate acoustic deep learning models throughout their life cycle in a realistic architecture is a barrier to further and more rapid success in this field of research. Two main contributions of this thesis are a proposed production architecture for model life cycle management using Machine Learning Operations (MLOps) and evaluation of the same on live passive sonar stream. Using the proposed production architecture, this work evaluates model performance differences in a production setting and explores methods to improve model performance in production. Through documenting considerations for creating a platform and architecture to continuously train, deploy, and evaluate various deep learning acoustic classification models, this study aims to create a framework and recommendations to accelerate progress in acoustic deep learning classification research.
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 01, 2021
- Accession Number
- AD1165029
Entities
People
- Nicholas R Villemez
Organizations
- Naval Postgraduate School