1.A method of tracing a learning source of an explainable artificial intelligence (AI) model, the method comprising:
receiving, by a tracing device, a desired behavior of the explainable AI model with respect to input data;
generating, by the tracing device, a learning graph based on similarities among a plurality of learning sources with respect to the input data for the desired behavior and for a current behavior;
retracing, by the tracing device, a learning of the explainable AI model by iteratively comparing the learning graph for the desired behavior and for the current behavior at each of a plurality of layers of the explainable AI model starting from an outer layer; and
detecting, by the tracing device, the learning source responsible for the current behavior based on the retracing.
2. The method of claim 1, wherein the learning sources comprises at least one of a cluster of training data, a training environment, or an object-class pair applied by the user.
3. The method of claim 1, further comprising generating a sequence graph by organizing the plurality of learning sources in a hierarchical manner.
4. The method of claim 3, wherein generating the learning graph comprises generating the learning graph with a randomly selected set of learning sources from among the plurality of learning sources based on the sequence graph.
5. The method of claim 4, wherein the randomly selected set of learning sources comprises a randomly selected learning source, a learning source hierarchically above the randomly selected learning source, and a learning source hierarchically below the randomly selected learning source
6. The method of claim 4, wherein generating the learning graph comprises generating one or more probabilities for a layer through Inverse Bayesian Fusion (IBF) so as to separate learning components of one or more of the randomly selected set of learning sources.
7. The method of claim 6, wherein the one or more probabilities for the layer is computed based on one or more distance metrics between output of the layer and outputs of a previous layer.
8. The method of claim 7, wherein each of the one or more distance metrics is a function of one or more distances between an output of the layer and outputs of the previous layer and one or more probabilities of the previous layer.
9. The method of claim 7, wherein detecting the learning source comprises selecting a learning source for an output with least distance metric in a direction of reducing gradient.
10. The method of claim 1, further comprising updating the AI model with respect to the learning source.
11. The method of claim 10, wherein the current behavior comprises an erroneous classification of the input data, wherein desired behavior comprises a correct classification of the input data, and wherein updating the AI model comprises correcting a classification model by unlearning with respect to the learning source responsible for the erroneous classification and learning again with respect to a corrected learning source.
12. The method of claim 10, further comprising validating the updated AI model using additional test data.
13. A system for tracing a learning source of an explainable artificial intelligence (AI) system, the system comprising:
a tracing device comprising at least one processor and a computer-readable medium storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
receiving a desired behavior of the explainable AI model with respect to input data;
generating a learning graph based on similarities among a plurality of learning sources with respect to the input data for the desired behavior and for a current behavior;
retracing a learning of the explainable AI model by iteratively comparing the learning graph for the desired behavior and for the current behavior at each of a plurality of layers of the explainable AI model starting from an outer layer; and
detecting the learning source responsible for the current behavior based on the retracing.
14. The system of claim 13, wherein the operations further comprise generating a sequence graph by organizing the plurality of learning sources in a hierarchical manner.
15. The system of claim 14, wherein generating the learning graph comprises generating the learning graph with a randomly selected set of learning sources from among the plurality of learning sources based on the sequence graph, and wherein the randomly selected set of learning sources comprises a randomly selected learning source, a learning source hierarchically above the randomly selected learning source, and a learning source hierarchically below the randomly selected learning source
16. The system of claim 15, wherein generating the learning graph comprises generating one or more probabilities for a layer through Inverse Bayesian Fusion (IBF) so as to separate learning components of one or more of the randomly selected set of learning sources.
17. The system of claim 16, wherein the one or more probabilities for the layer is computed based on one or more distance metrics between output of the layer and outputs of a previous layer, and wherein each of the one or more distance metrics is a function of one or more distances between an output of the layer and outputs of the previous layer and one or more probabilities of the previous layer.
18. The system of claim 17, wherein detecting the learning source comprises selecting a learning source for an output with least distance metric in a direction of reducing gradient.
19. The system of claim 13, further comprising:
updating the AI model with respect to the learning source by unlearning with respect to the learning source responsible for the current behavior and learning again with respect to a corrected learning source; and
validating the updated AI model using additional test data.

Dated this 5th day of June, 2018

R Ramya Rao
Of K&S Partners
Agent for the Applicant
, Description:TECHNICAL FIELD
This disclosure relates generally to artificial intelligence system, and more particularly to method and system for tracing a learning source of an explainable artificial intelligence model.