Parallel ensemble of machine learning algorithms

Patent metadata

Field	Value
Publication number	US-11443244-B2
Application number	US-201916431802-A
Country	US
Kind code	B2
Filing date	Jun 5, 2019
Priority date	Jun 5, 2019
Publication date	Sep 13, 2022
Grant date	Sep 13, 2022

Abstract

An aspect of the invention includes receiving machine learning (ML) training data that includes a plurality of features for a plurality of observations. The ML training data is broken into a plurality of non-overlapping subsets of features and observations. A first ML algorithm is trained based on a first subset of the features and observations, and a second ML algorithm is trained based on a second subset of the features and observations. The training of the first ML algorithm overlaps in time with the training of the second ML algorithm. The first and second ML algorithms are tested. Either the first or second ML algorithm is selected based at least in part on results of the testing. The selected ML algorithm is retained as a trained ML algorithm for predicting one or more of the plurality of features based on one or more others of the plurality of features.

First claim

What is claimed is:

1. A computer-implemented method comprising:
receiving machine learning (ML) training data comprising a plurality of features for a plurality of observations;
breaking the ML training data into a plurality of non-overlapping subsets of features and observations;
training a first ML algorithm based on a first subset of the features and observations, and a second ML algorithm based on a second subset of the features and observations, the training of the first ML algorithm overlapping in time with the training of the second ML algorithm;
testing the first ML algorithm and the second ML algorithm;
selecting one of the first ML algorithm and the second ML algorithm based at least in part on results of the testing; and
retaining the selected ML algorithm as a trained ML algorithm for predicting one or more of the plurality of features based on one or more other features of the other plurality of features.

2. The computer-implemented method of claim 1 , wherein the results of the testing include an error level.

3. The computer-implemented method of claim 1 , wherein the first and second subset include a same subset of the plurality of features.

4. The computer-implemented method of claim 3 , wherein the training, testing, selecting, and retaining are repeated for multiple different subsets of the plurality of features.

5. The computer-implemented method of claim 3 , wherein the training, testing, selecting, and retaining are repeated for all subsets of the plurality of features.

6. The computer-implemented method of claim 1 , wherein the testing the first ML algorithm overlaps in time with the testing of the second ML algorithm.

7. The computer-implemented method of claim 1 , wherein the training and testing are ML algorithm agnostic.

8. The computer-implemented method of claim 1 , wherein the training and testing are repeated until a user defined error threshold is reached.

9. A system comprising:
a memory having computer readable instructions; and
one or more processors for executing the computer readable instructions, the computer readable instructions controlling the one or more processors to perform operations comprising:
receiving machine learning (ML) training data comprising a plurality of features for a plurality of observations;
breaking the ML training data into a plurality of non-overlapping subsets of features and observations;
training a first ML algorithm based on a first subset of the features and observations, and a second ML algorithm based on a second subset of the features and observations, the training of the first ML algorithm overlapping in time with the training of the second ML algorithm;
testing the first ML algorithm and the second ML algorithm;
selecting one of the first ML algorithm and the second ML algorithm based at least in part on results of the testing; and
retaining the selected ML algorithm as a trained ML algorithm for predicting one or more of the plurality of features based on one or more other features of the other plurality of features.

10. The system of claim 9 , wherein the results of the testing include an error level.

11. The system of claim 9 , wherein the first and second subset include a same subset of the plurality of features.

12. The system of claim 11 , wherein the training, testing, selecting, and retaining are repeated for multiple different subsets of the plurality of features.

13. The system of claim 12 , wherein the training, testing, selecting, and retaining are repeated for all subsets of the plurality of features.

14. The system of claim 12 , wherein the testing the first ML algorithm overlaps in time with the testing of the second ML algorithm.

15. The system of claim 9 , wherein the training and testing are ML algorithm agnostic.

16. The system of claim 9 , wherein the training and testing are repeated until a user defined error threshold is reached.

17. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform operations comprising:
receiving machine learning (ML) training data comprising a plurality of features for a plurality of observations;
breaking the ML training data into a plurality of non-overlapping subsets of features and observations;
training a first ML algorithm based on a first subset of the features and observations, and a second ML algorithm based on a second subset of the features and observations, the training of the first ML algorithm overlapping in time with the training of the second ML algorithm;
testing the first ML algorithm and the second ML algorithm;
selecting one of the first ML algorithm and the second ML algorithm based at least in part on results of the testing; and
retaining the selected ML algorithm as a trained ML algorithm for predicting one or more of the plurality of features based on one or more other features of the other plurality of features.

18. The computer program product of claim 17 , wherein the results of the testing include an error level.

19. The computer program product of claim 17 , wherein the first and second subset include a same subset of the plurality of features.

20. The computer program product of claim 19 , wherein the training, testing, selecting, and retaining are repeated for multiple different subsets of the plurality of features.

Assignees

• IBM
• Int Business Machines Corportation

Inventors

• Hackett Charles E

Classifications

• G06N20/20 Primary

  Ensemble learning · CPC title