Hyper-Parameter Optimization of a Convolutional Neural Network

Abstract

In the world of machine learning, neural networks have become a powerful pattern recognition technique that gives a user the ability to interpret high-dimensional data where as conventional methods, such as logistic regression, would fail. There exists different types of neural networks, each containing its own set of hyper-parameters, that are dependent on the type of analysis required, but the focus of this paper will be on the hyper-parameters of convolutional neural networks. Convolutional neural networks are commonly used for classifications of visual imagery. For example, if you were to build a network for the purpose of predicting a specific animal, it would hopefully output, with high fidelity, the correct classification of a new animal introduced to the model. Traditionally, hyper-parameters were never optimized because it required a lot of computational power and time. If hyper-parameters were adjusted, analysts would manually change a few hyper-parameters, re-run the model, and hopefully get a better classification accuracy. But because of the advancements in technology, hyper-parameter tuning can now be done through complex and powerful optimization algorithms to improve the model. This paper implements and compares three different optimization techniques: random search, Bayesian Optimization with Gaussian Process, and tree of parzenestimator approach. The best performing technique is then improved through the Kiefer-Wolfowitz approximation

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 2019
Accession Number
AD1077380

Entities

People

  • Steven H. Chon

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Air Force
  • Algorithms
  • Computations
  • Computer Languages
  • Computers
  • Convolutional Neural Networks
  • Gaussian Processes
  • Governments
  • Information Science
  • Kernel Functions
  • Machine Learning
  • Neural Networks
  • Operations Research
  • Probability
  • Probability Distributions
  • Random Variables
  • United States Government

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Distributed Systems and Data Platform Development
  • Solar Photovoltaics and Thermoelectric Devices.

Technology Areas

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