Abstract: |
Embodiments are disclosed for health assessment and diagnosis implemented in an artificial intelligence (AI) system. In an embodiment, a method comprises: feeding a first set of input features to the AI model; obtaining a first set of raw output predictions from the model; determining a first set of impact scores for the input features fed into the model; training a neural network with the first set of impact scores as input to the network and pre-determined sentences describing the model's behavior as output; feeding a second set of input features to the AI model; obtaining a second set of raw output predictions from the model; determining a second set of impact scores based on the second set of output predictions; feeding the second set of impact scores to the neural network; and generating a sentence describing the AI model's behavior on the second set of input features. |
Inventor: |
Anushiravani, Ramin (Santa Clara, CA, US); Nemala, Sridhar Krishna (Santa Clara, CA, US); Yalamanchili, Ravi Kiran (San Jose, CA, US); Davuluri, Navya Swetha (Sunnyvale, CA, US) |
Applicant: |
CurieAI, Inc. (Santa Clara, CA, US) |
Face Assignee: |
N/A |
Filed: |
2019-11-11 |
Issued: |
2020-05-14 |
Claims: |
14 |
|
US20200151516
|
1. A method of interpreting an artificial intelligence (AI) model prediction, comprising:
(4)
(9)
|
|
3. A system comprising:
(4)
(2)
|
|