[ https://issues.apache.org/jira/browse/MATH-1563?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17353747#comment-17353747 ]
Gilles Sadowski commented on MATH-1563: --------------------------------------- {quote}Is there any other activity I need to perform for approval of this enhancement. {quote} All enhancements are welcome; this one will be hosted in Commons Math given the PMC did not agree to the creation of a GA dedicated component (cf. "dev" ML archive). Commons Math has just been partially modularized and the GA functionality is now in package {{o.a.c.math4.legacy.genetics}}. You should create a (non-legacy) module {{commons-math-ga}} for the GA functionality and move the code into package {{o.a.c.math4.ga}}, refactoring it on the way, so that it does *not* depend on any "legacy" module. Currently, there are 2 non-legacy modules ({{commons-math-neuralnet}} and {{commons-math-transform}}) that illustrate how refactored package should look like: In the case of GA codes, it pretty much boils down to replacing the usage of "legacy" exception types by a new (package-private) {{GAException}}. > Implementation of Adaptive Probability Generation Strategy for Genetic > Algorithm > -------------------------------------------------------------------------------- > > Key: MATH-1563 > URL: https://issues.apache.org/jira/browse/MATH-1563 > Project: Commons Math > Issue Type: Improvement > Reporter: AVIJIT BASAK > Priority: Major > > In Genetic Algorithm probability of crossover and mutation operation can be > generated in an adaptive manner. Some experiment was done related to this and > published in this article > "https://www.ijcaonline.org/archives/volume175/number10/basak-2020-ijca-920572.pdf". > Currently Apache's API works on constant probability strategy. I would like > to propose incorporation of rank based adaptive probability generation > strategy as described in the mentioned article. This will improve the > performance and robustness of the algorithm and would make this more suitable > for use in higher dimensional problems like machine learning or deep learning. -- This message was sent by Atlassian Jira (v8.3.4#803005)