Enjoy your
FREE PREVIEW which shows only 2022 data and 25 documents. Contact
Patent Forecast for full access.
AI Biotech/Diagnostics: Cardio
Search All Applications in AI Biotech/Diagnostics: Cardio
Application US20200151516
Published 2020-05-14
Methods For Explainability Of Deep-learning Models
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.
Much More than Average Length Specification
View the Patent Matrix® Diagram to Explore the Claim Relationships
USPTO Full Text Publication >
- 1. A method of interpreting an artificial intelligence (AI) model prediction, comprising:
feeding a first set of input features to the AI model; obtaining, using one or more processors, a first set of raw output predictions from the model; determining, using the one or more processors, a first set of impact scores for one or more of 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, using one or more processors, 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.
- 3. A system comprising:
one or more processors; memory storing instructions that when executed by the one or more processors, cause the one or more processors to perform operations comprising:
feeding a first set of input features to an artificial intelligence (AI) model;
obtaining a first set of raw output predictions from the AI model;
determining a first set of impact scores for one or more of the input features fed into the AI 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.