Abstract

In machine learning, performance is of great value. However, each learning process requires much time and effort in setting each parameter. The critical problem in machine learning is determining the hyperparameters, such as the learning rate, mini-batch size, and regularization coefficient. In particular, we focus on the learning rate, which is directly related to learning efficiency and performance. Bayesian optimization using a Gaussian Process is common for this purpose. In this paper, based on Bayesian optimization, we attempt to optimize the hyperparameters automatically by utilizing a Gamma distribution, instead of a Gaussian distribution, to improve the training performance of predicting image discrimination. As a result, our proposed method proves to be more reasonable and efficient in the estimation of learning rate when training the data, and can be useful in machine learning.

Highlights

  • At Google’s I/O 2017 conference, its CEO, Sundar Pichai, made some rather striking comments on AutoML

  • Bayesian optimization has been studied in relation to the Manifold Gaussian Process [11]

  • Google is indispensable for machine learning, and even more so for AutoML

Read more

Summary

Introduction

At Google’s I/O 2017 conference, its CEO, Sundar Pichai, made some rather striking comments on AutoML. Related research on AutoML has typically considered automated feature learning [1], architecture search [2], and hyperparameter optimization; where hyperparameter optimization includes optimizing the Learning Rate, Mini-batch Size, and Regularization Coefficient. It must be decided which are the most appropriate values for each model’s learning rate, mini-batch size, and normalization coefficient which should be set in advance for learning. Each parameter has an individual problem, which contributes towards solving the multidimensional problem In this regard, Bayesian optimization has been studied in relation to the Manifold Gaussian Process (mGP) [11].

Bayesian Optimization
Acquisition Functions for Bayesian Optimization
Gaussian Distribution and Gamma Distribution
Proposed Object Function
Experiment on MNIST
Performance Evaluation
Evaluation
Conclusions

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.