System and Method For Detecting Misclassification Errors in Neural Networks Classifiers
AssigneeCognizant Technology Solutions U.S. Corporation
InventorsXin Qiu, Risto Miikkulainen
Life of this patent
Estimating the term…
Abstract
An error detection framework, RED (Residual-based Error Detection), produces reliable confidence scores for detecting misclassification errors. RED calibrates the classifier's inherent confidence indicators and estimates uncertainty of the calibrated confidence scores using Gaussian Processes.
Claims18
A process for detecting errors in a base neural network classifier, the process comprising:
- assigning a target detection score c to each training sample (χ,y) based on correctness of a classification prediction y for the training sample by the base neural network classifier;
- predicting by a trained model with input-output (I/O) kernel, a residual r between the target detection score c and an original maximum class probability ĉ;
- and
- for a given data point x*, providing a Gaussian distribution of estimated residual {circumflex over (r)}*, wherein {circumflex over (r)}* is defined by residual mean {circumflex over (r)}* and variance var({circumflex over (r)}*);
- and
- adding {circumflex over (r)}* and ĉ* to calculate an error detection score ĉ′*, wherein var({circumflex over (r)}*) indicates a corresponding uncertainty of the error detection score.
At least one computer-readable medium storing instructions that, when executed by a computer, perform a process for detecting errors in a base neural network classifier, the process comprising:
- assigning a target detection score c to each training sample (χ,y) based on correctness of a classification prediction ŷ for the training sample by the base neural network classifier;
- predicting by a trained model with input-output (I/O) kernel, a residual r between the target detection score c and an original maximum class probability ĉ;
- and
- for a given data point x*, providing a Gaussian distribution of estimated residual {circumflex over (r)}*, wherein {circumflex over (r)}* is defined by residual mean {circumflex over (r)}* and variance var({circumflex over (r)}*);
- and
- adding {circumflex over (r)}* and ĉ* to calculate an error detection score ĉ′*, wherein var({circumflex over (r)}*) indicates a corresponding uncertainty of the error detection score.
A dual model system for detecting errors in a base neural network classifier, the system comprising:
- a first model pre-trained as a base neural network classifier running on at least a first processor, wherein each training sample (χ,y) of the first model is assigned a target detection score c in accordance with correctness of the first model's classification prediction ŷ for the training sample;
- and
- a second trained model including input-output (I/O) kernel for predicting a residual r between the target detection score c and an original maximum class probability ĉ;
- wherein for a given data point x*, the system provides a Gaussian distribution of estimated residual {circumflex over (r)}*, wherein {circumflex over (r)}* is defined by residual mean {circumflex over (r)}* and variance var({circumflex over (r)}*), and calculates an error detection score ĉ′* by adding {circumflex over (r)}* and ĉ*, and further wherein var({circumflex over (r)}*) indicates a corresponding uncertainty of the error detection score.
Dependencies are inferred from the claim text.