Invention Grant
- Patent Title: Methods for explainability of deep-learning models
-
Application No.: US16680458Application Date: 2019-11-11
-
Publication No.: US10706329B2Publication Date: 2020-07-07
- Inventor: Ramin Anushiravani , Sridhar Krishna Nemala , Ravi Kiran Yalamanchili , Navya Swetha Davuluri
- Applicant: CurieAI, Inc.
- Applicant Address: US CA Santa Clara
- Assignee: CurieAI, Inc.
- Current Assignee: CurieAI, Inc.
- Current Assignee Address: US CA Santa Clara
- Agency: Fish & Richardson P.C.
- Main IPC: G06N3/04
- IPC: G06N3/04 ; G06K9/62 ; G16H10/60 ; G16H80/00

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.
Public/Granted literature
- US20200151516A1 Methods for Explainability of Deep-Learning Models Public/Granted day:2020-05-14
Information query