PROVIDING EXPLAINABLE MACHINE LEARNING MODEL RESULTS USING DISTRIBUTED LEDGERS

Title:

PROVIDING EXPLAINABLE MACHINE LEARNING MODEL RESULTS USING DISTRIBUTED LEDGERS

Document Type and Number:

WIPO Patent Application WO/2022/127474

Kind Code:

A1

Abstract:

Providing reproducible machine learning model results by receiving input data for a machine learning (ML) model, processing the input data using the ML model, yielding an initial result, adding a first block to a distributed ledger, the block comprising the input data, the initial result, an ML model data structure, and a link to training data for the ML model, wherein the training data resides in previous distributed ledger blocks, and providing an output including the initial result.

More Like This:

WO/2023/085443	DEEP LEARNING WEIGHT LIGHTENING ACCELERATION DEVICE
WO/2022/016926	NEURAL NETWORK COMPUTING APPARATUS AND DATA READING AND DATA STORAGE METHOD AND RELATED DEVICE
JP2021002133	ARITHMETIC UNIT AND PRODUCT SUM OPERATION SYSTEM

Inventors:

SZCZEPANIK GRZEGORZ PIOTR (PL)
PALUS LUKASZ JAKUB (PL)
PATEL KUSHAL S (IN)
PATEL SARVESH S (IN)

Application Number:

PCT/CN2021/130936

Publication Date:

June 23, 2022

Filing Date:

November 16, 2021

Export Citation:

Click for automatic bibliography generation Help

Assignee:

IBM (US)
IBM CHINA CO LTD (CN)

International Classes:

G06N3/063

Foreign References:

CN109670583A	2019-04-23
CN110991622A	2020-04-10
CN109615015A	2019-04-12
US20190130545A1	2019-05-02

Attorney, Agent or Firm:

LIU, SHEN & ASSOCIATES (CN)

Download PDF:

View/Download PDF PDF Help

Previous Patent: NETWORK SLICE SELECTION METHOD AND APPARATUS, DEVICE AND STORAGE MEDIUM

Next Patent: DATA TRANSMISSION METHOD AND APPARATUS, ELECTRONIC DEVICE, AND STORAGE MEDIUM