公开(公告)号：US20220343171A1

公开(公告)日：2022-10-27

申请号：US17855774

申请日：2022-06-30

Applicant: Neslihan Kose Cihangir ,  Omesh Tickoo ,  Ranganath Krishnan ,  Ignacio J. Alvarez ,  Michael Paulitsch ,  Akash Dhamasia

Inventor： Neslihan Kose Cihangir ,  Omesh Tickoo ,  Ranganath Krishnan ,  Ignacio J. Alvarez ,  Michael Paulitsch ,  Akash Dhamasia

IPC: G06N3/08

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed that calibrate error aligned uncertainty for regression and continuous structured prediction tasks/optimizations. An example apparatus includes a prediction model, at least one memory, instructions, and processor circuitry to at least one of execute or instantiate the instructions to calculate a count of samples corresponding to an accuracy-certainty classification category, calculate a trainable uncertainty calibration loss value based on the calculated count, calculate a final differentiable loss value based on the trainable uncertainty calibration loss value, and calibrate the prediction model with the final differentiable loss value.