- 专利标题: METHODS AND APPARATUS TO CALIBRATE ERROR ALIGNED UNCERTAINTY FOR REGRESSION AND CONTINUOUS STRUCTURED PREDICTION TASKS
-
申请号: US17855774申请日: 2022-06-30
-
公开(公告)号: US20220343171A1公开(公告)日: 2022-10-27
- 发明人: Neslihan Kose Cihangir , Omesh Tickoo , Ranganath Krishnan , Ignacio J. Alvarez , Michael Paulitsch , Akash Dhamasia
- 申请人: Neslihan Kose Cihangir , Omesh Tickoo , Ranganath Krishnan , Ignacio J. Alvarez , Michael Paulitsch , Akash Dhamasia
- 申请人地址: DE Munich; US OR Portland; US OR Hillsboro; US OR Portland; DE Ottobrunn; DE Munich
- 专利权人: Neslihan Kose Cihangir,Omesh Tickoo,Ranganath Krishnan,Ignacio J. Alvarez,Michael Paulitsch,Akash Dhamasia
- 当前专利权人: Neslihan Kose Cihangir,Omesh Tickoo,Ranganath Krishnan,Ignacio J. Alvarez,Michael Paulitsch,Akash Dhamasia
- 当前专利权人地址: DE Munich; US OR Portland; US OR Hillsboro; US OR Portland; DE Ottobrunn; DE Munich
- 主分类号: G06N3/08
- IPC分类号: G06N3/08
摘要:
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.
信息查询