Back to results
US 2021/0064046 A1Published application
Measuring confidence in deep neural networks
AssigneeFord Global Technologies, LLC
InventorGURJEET SINGH
Life of this patent
Estimating the term…
Abstract
A distribution of a plurality of predictions generated by a deep neural network using sensor data is calculated, and the deep neural network includes a plurality of neurons. At least one of a measurement or a classification corresponding to an object is determined based on the distribution. The deep neural network generates each prediction of the plurality of predictions with a different number of neurons.
Claims20
A system comprising a computer including a processor and a memory, the memory including instructions such that the processor is programmed to:
- calculate a distribution of a plurality of predictions generated by a deep neural network using sensor data, wherein the deep neural network includes a plurality of neurons;
- and
- determine at least one of a measurement or a classification corresponding to an object based on the distribution,
- wherein the deep neural network generates each prediction of the plurality of predictions with a different number of neurons.
1 more element
A system comprising:
- a server;
- and
- a vehicle including a vehicle system, the vehicle system comprising a computer including a processor and a memory, the memory including instructions such that the processor is programmed to:
- calculate, at the vehicle, a distribution of a plurality of predictions generated by a deep neural network using sensor data, wherein the deep neural network includes a plurality of neurons;
- and
- determine at least one of a measurement or a classification corresponding to an object detected by the sensor data,
- wherein the deep neural network generates each prediction of the plurality of predictions with a different number of neurons.
4 more elements
A method, comprising:
- calculating a distribution of a plurality of predictions generated by a deep neural network using sensor data, wherein the deep neural network includes a plurality of neurons;
- and
- determining at least one of a measurement or a classification corresponding to an object based on the distribution,
- wherein the deep neural network generates each prediction of the plurality of predictions with a different number of neurons.
1 more element
Dependencies are inferred from the claim text.