公开(公告)号：AU2021251463A1

公开(公告)日：2022-09-15

申请号：AU2021251463

申请日：2021-02-16

Applicant: IBM

Inventor： ARNOLD MATTHEW RICHARD ,  ELDER BENJAMIN TYLER ,  NAVRATIL JIRI ,  VENKATARAMAN GANESH

IPC: G06N20/00

Abstract: A technique for generating a performance prediction of a machine learning model with uncertainty intervals includes obtaining a first model configured to perform a task and a production dataset.At least one metric predicting a performance of the first model at performing the task on the production dataset is generated using a second model. The second model is a meta-model associated with the first model. At least one value predicting an uncertainty of the at least one metric predicting the performance of the first model at performing the task on the production dataset is generated using a third model. The third model is a meta-meta-model associated with the second model. An indication of the at least one metric predicting the performance of the first model and the at least one value predicting the uncertainty of the at least one metric is provided.

公开(公告)号：DE10111056B4

公开(公告)日：2005-11-10

申请号：DE10111056

申请日：2001-03-08

Applicant: IBM

Inventor： NAVRATIL JIRI ,  VISWANATHAN MAHESH

IPC: G10L15/20 ,  G10L15/06 ,  G06F17/20

公开(公告)号：DE10111056A1

公开(公告)日：2001-10-18

申请号：DE10111056

申请日：2001-03-08

Applicant: IBM

Inventor： NAVRATIL JIRI ,  VISWANATHAN MAHESH

IPC: G10L15/20 ,  G10L15/06 ,  G06F17/20

Abstract: The non-target speech identification method uses transcription of each non-target speech expression within an audio stream using a transcription system which is trained via the target speech, with generation of a confidence weighting for each transcribed speech expression and identification of the speech expression as a non-target speech expression when the confidence weighting fails to meet defined criteria. Also included are Independent claims for the following; (a) a non-target speech identification system; (b) a product for non-target speech identification