Dynamically enhancing supervised learning
View Patent ↗Embodiments of the present invention provide an approach for dynamically enhancing supervised learning using factor modification based on parsing user input. A user selects an object being displayed incorrectly and provides input as to the reason. The user input is parsed to derive a factor that is contributing to the false outcome. The factor is dynamically altered resulting in a decision path that produces a positive outcome. The change is sent to a model or application owner for final validation and refined training of the machine learning model.
1. A computer-implemented method, comprising the computer-implemented steps of:
receiving a selection of a data object in an image produced as a result of a machine learning model, wherein the selection indicates that the data object contains a false outcome produced by a supervised machine learning process;
receiving user input related to a reason for the false outcome;
parsing the user input to derive a noun and a verb;
deriving, based on the noun, a factor of the machine learning model contributing to the false outcome; and
dynamically altering, based on the verb, the factor to yield a new decision path within the machine learning model that generates an alteration of the data object in the image having a positive outcome, wherein the new decision path is created by increasing a density of nodes, within the machine learning model, based on computed values determined from the verb during the supervised machine learning process.
2. The computer-implemented method of claim 1 , wherein the false outcome is associated with a misclassification of the data object and the positive outcome is associated with a correct classification of the data object.
3. The computer-implemented method of claim 1 , wherein the user inputs a selection from the group consisting of: a voice input or a text input.
4. The computer-implemented method of claim 1 , wherein dynamically altering the factor includes adding more weight to the factor to influence a selection of the new decision path in the machine learning process.
5. The computer-implemented method of claim 1 , further comprising presenting the positive outcome for approval.
6. The computer-implemented method of claim 5 , further comprising performing a final update, upon approval, of the machine learning model based on the dynamic alteration of the factor.
7. The computer-implemented method of claim 1 , wherein dynamically altering the factor includes adding the new decision path to the machine learning model.
8. A system, comprising:
a memory medium comprising program instructions;
a bus coupled to the memory medium; and
a processor, for executing the program instructions, coupled to the memory medium that when executing the program instructions causes the system to:
receive a selection of a data object in an image produced as a result of a machine learning model, wherein the selection indicates that the data object contains a false outcome produced by a supervised machine learning process;
receive user input related to a reason for the false outcome;
parse the user input to derive a noun and a verb;
derive, based on the noun, a factor of the machine learning model contributing to the false outcome; and
dynamically alter, based on the verb, the factor to yield a new decision path within the machine learning model that generates an alteration of the data object in the image having a positive outcome, wherein the new decision path is created by increasing a density of nodes, within the machine learning model, based on computed values determined from the verb during the supervised machine learning process.
9. The system of claim 8 , wherein the false outcome is associated with a misclassification of the data object and the positive outcome is associated with a correct classification of the data object.
10. The system of claim 8 , wherein the user inputs a selection from the group consisting of: a voice input or a text input.
11. The system of claim 8 , wherein dynamically altering the factor includes adding more weight to the factor to influence a selection of the decision path in the machine learning process.
12. The system of claim 8 , the memory medium further comprising instructions to present the positive outcome for approval.
13. The system of claim 12 , the memory medium further comprising instructions to perform a final update, upon approval, of the machine learning model based on the dynamic alteration of the factor.
14. The system of claim 8 , wherein dynamically altering the factor includes adding the new decision path to the machine learning model.
15. A computer program product comprising a computer readable storage device, and program instructions stored on the computer readable storage device, to:
receive a selection of a data object in an image produced as a result of a machine learning model, wherein the selection indicates that the data object contains a false outcome produced by a supervised machine learning process;
receive user input related to a reason for the false outcome;
parse the user input to derive a noun and a verb;
derive, based on the noun, a factor of the machine learning model contributing to the false outcome; and
dynamically alter, based on the verb, the factor to yield a new decision path within the machine learning model that generates an alteration of the data object in the image having a positive outcome, wherein the new decision path is created by increasing a density of nodes, within the machine learning model, based on computed values determined from the verb during the supervised machine learning process.
16. The computer program product of claim 15 , wherein the false outcome is associated with a misclassification of the data object and the positive outcome is associated with a correct classification of the data object.
17. The computer program product of claim 15 , wherein the user inputs a selection from the group consisting of: a voice input or a text input.
18. The computer program product of claim 15 , wherein dynamically altering the factor includes adding more weight to the factor to influence a selection of the new decision path to the machine learning process.
19. The computer program product of claim 15 , further comprising program instructions stored on the computer readable storage device to present the positive outcome for approval.
20. The computer program product of claim 19 , further comprising program instructions stored on the computer readable storage device to perform a final update, upon approval, of the machine learning model.