Scaling and Sensitivity Analysis of Machine Learning Regression on Periodic Functions

Abstract

In this report we document the scalability and sensitivity of machine learning (ML) regression on a periodic, highly oscillating, and C ^ infinity function. This work is motivated by the need to use ML regression on periodic problems such as tidal propagation. In this work, TensorFlow is used to investigate the machine scalability of a periodic function from one to three dimensions. Wall clock times for each dimension were calculated for a range of layers, neurons, and learning rates to further investigate the sensitivity of the ML regression to these parameters. Lastly, the stochastic gradient descent and Adam optimizers wall clock timings and sensitivities were compared.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 2023
Accession Number
AD1209163

Entities

People

  • Corey J. Trahan
  • Peter G. Rivera

Organizations

  • United States Army Corps of Engineers

Tags

Communities of Interest

  • Engineered Resilient Systems

DTIC Thesaurus Topics

  • Algorithms
  • Army
  • Army Corps Of Engineers
  • Artificial Intelligence
  • Computational Science
  • Data Analysis
  • Data Mining
  • Engineers
  • Information Science
  • Machine Learning
  • Neural Networks
  • Oceans
  • Periodic Functions
  • Regression Analysis
  • Scalability
  • Standards
  • Statistical Algorithms

Fields of Study

  • Computer science

Readers

  • Fluid Mechanics and Fluid Dynamics.
  • Operations Research
  • Regression Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks