| 摘要 |
Methods, systems and computer program products for evaluating performance of generative models are disclosed. One method includes providing a base model and a candidate model having observed variables and first and second conceptually related variables related to the observed variables, respectively, receiving observations assigned to a subset of the observed variables, and for each observation, evaluating the observation by the base model to produce a base assessment of the observation, evaluating the observation by the candidate model to produce a second assessment of the observation, determining a similarity measure of the assessment of the observation based on the base and second assessments, and selecting a subset of observations having low similarity measures for use in evaluating performance of the candidate model. |
| 主权项 |
1. A computer implemented method for evaluating performances of generative models, comprising:
receiving data describing observations associated with observable variables of a first generative model and a second generative model, each of the first and second generative models having information about relationships among one or more variables; for at least one observation:
applying the first generative model to the observation to produce a first assessment of the observation;applying the second generative model to the observation to produce a second assessment of the observation; anddetermining, using one or more processors, a similarity score between the first and second assessments; and outputting a subset of the observations, each corresponding to first and second assessments having a similarity score that is less than a predetermined threshold. |
