CERTAINTY-BASED CLASSIFICATION NETWORKS

Title:

CERTAINTY-BASED CLASSIFICATION NETWORKS

Document Type and Number:

WIPO Patent Application WO/2022/018424

Kind Code:

A3

Abstract:

A certainty-based prediction apparatus and method are provided. A plurality of main classifier (MC) modules each predict an MC predicted class based on input data, and determine an MC certainty. Each MC module processes a pre-trained, machine learning main classifier having at least one expert class and a plurality of non-expert classes. An expert classifier (EC) module associated with each expert class predicts an EC predicted class based on the input data. Each EC module processes a pre-trained, machine learning expert classifier having two classes including an associated expert class and a residual class that includes any non-associated expert classes and the plurality of non-expert classes. A final predicted class decision module determines a final predicted class and a final certainty based on each MC predicted class, each MC certainty and each EC predicted class. The final predicted class and the final certainty are output.

More Like This:

WO/2018/213840	DEPTHWISE SEPARABLE CONVOLUTIONS FOR NEURAL MACHINE TRANSLATION
WO/2023/287702	METHOD AND APPARATUS FOR ACCELERATED INFERENCE OF MACHINE-LEARNING MODELS
WO/2020/114122	NEURAL NETWORK SYSTEM AND METHOD FOR ANALYZING RELATIONSHIP NETWORK GRAPH

Inventors:

VENU BALAJI (GB)
EYOLE MBOU (GB)

Application Number:

PCT/GB2021/051855

Publication Date:

March 03, 2022

Filing Date:

July 19, 2021

Export Citation:

Click for automatic bibliography generation Help

Assignee:

ADVANCED RISC MACH LTD (GB)

International Classes:

G06N3/04; G06N3/063; G06N3/08; G06N7/00

Domestic Patent References:

WO2019002474A1

2019-01-03

Foreign References:

EP0676704A2	1995-10-11
US20140114885A1	2014-04-24

Other References:

AIZPURUA J I ET AL: "Improved power transformer condition monitoring under uncertainty through soft computing and probabilistic health index", APPLIED SOFT COMPUTING, ELSEVIER, AMSTERDAM, NL, vol. 85, 8 June 2019 (2019-06-08), XP085935233, ISSN: 1568-4946, [retrieved on 20190608], DOI: 10.1016/J.ASOC.2019.105530
SAYADI HOSSEIN ET AL: "2SMaRT: A Two-Stage Machine Learning-Based Approach for Run-Time Specialized Hardware-Assisted Malware Detection", 2019 DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE & EXHIBITION (DATE), EDAA, 25 March 2019 (2019-03-25), pages 728 - 733, XP033550162, DOI: 10.23919/DATE.2019.8715080

Attorney, Agent or Firm:

TLIP LTD et al. (GB)

Download PDF:

View/Download PDF PDF Help

Previous Patent: ENTROPY CALCULATION FOR CERTAINTY-BASED CLASSIFICATION NETWORKS

Next Patent: HYDROGENATION CATALYST