About this add-in
This add-in is an add-in for performing Bayesian optimization using the Gaussian process model of JMP.
System requirements
- JMP 15 or later
- Display language is English and Japanese only
About Bayesian optimization
Bayesian optimization is one of the methods used to find the optimal solution by repeating successive experiments. The main flow of Bayesian optimization is as follows.
- Make a Space Filling plan (or another plan) with an appropriate number of experiments.
- do an experiment.
- The Gaussian process model is estimated from the obtained data.
- From the Gaussian process model g (x) (and its covariance matrix ∑) estimated from the data, find the point x * where A (g (x)) calculated from the appropriate function A (.) Is maximized.
- Add x * as an experimental point and return to (2).
For details on Bayesian optimization, refer to the following papers.
B. Shahriari, K. Swersky, Z. Wang, R. P. Adams and N. de Freitas, "Taking the Human Out of the Loop: A Review of Bayesian Optimization," in Proceedings of the IEEE, vol. 104, no. 1, pp. 148-175, Jan. 2016, doi: 10.1109 / JPROC.2015.2494218.
How to use the add-in
(See also the attached document)
- Open the JMP data table with the experimental data you have already entered. * Note: The current add-in supports only when the objective variable Y is one. Also, the explanatory variable X can only be a continuous scale.
- Select Add-ins> Bayesian Optimization.
- Set columns and options.
- When the analysis is finished, the result window will be displayed. If you want to add candidate experimental points to the table, click the Add Row to Table button.
- If you want to do the following experiment, you can run Bayesian optimization under the same conditions by running the table script "Run Bayesian Optimization Add-in".
screenshot
