BR112023019673A2 - REPORTS FOR MACHINE LEARNING MODEL UPDATES - Google Patents
REPORTS FOR MACHINE LEARNING MODEL UPDATESInfo
- Publication number
- BR112023019673A2 BR112023019673A2 BR112023019673A BR112023019673A BR112023019673A2 BR 112023019673 A2 BR112023019673 A2 BR 112023019673A2 BR 112023019673 A BR112023019673 A BR 112023019673A BR 112023019673 A BR112023019673 A BR 112023019673A BR 112023019673 A2 BR112023019673 A2 BR 112023019673A2
- Authority
- BR
- Brazil
- Prior art keywords
- neural network
- reports
- network parameters
- machine learning
- learning model
- Prior art date
Links
- 238000010801 machine learning Methods 0.000 title abstract 2
- 238000013528 artificial neural network Methods 0.000 abstract 13
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0803—Configuration setting
- H04L41/0813—Configuration setting characterised by the conditions triggering a change of settings
- H04L41/082—Configuration setting characterised by the conditions triggering a change of settings the condition being updates or upgrades of network functionality
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/06—Generation of reports
- H04L43/065—Generation of reports related to network devices
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/70—Services for machine-to-machine communication [M2M] or machine type communication [MTC]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mobile Radio Communication Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
relatórios para atualizações de modelo de aprendizado de máquina. um receptor recebe, a partir de um transmissor, uma rede neural de referência. o receptor treina a rede neural de referência para obter parâmetros de rede neural atualizados para a rede neural de referência. o receptor relata ao transmissor em resposta a um disparo, uma diferença entre os parâmetros de rede neural atualizados e os parâmetros de rede neural anteriores para a rede neural de referência. o disparo pode ser baseado em uma função de perda, uma magnitude da diferença entre os parâmetros de rede neural atualizados e os parâmetros de rede neural anteriores e/ou uma diferença entre o desempenho da rede neural de referência com os parâmetros de rede neural atualizados e o desempenho da rede neural de referência com os parâmetros de rede neural anteriores.reports for machine learning model updates. a receiver receives, from a transmitter, a reference neural network. the receiver trains the reference neural network to obtain updated neural network parameters for the reference neural network. the receiver reports to the transmitter in response to a trigger, a difference between the updated neural network parameters and the previous neural network parameters for the reference neural network. triggering may be based on a loss function, a magnitude of difference between the updated neural network parameters and the previous neural network parameters, and/or a difference between the performance of the reference neural network with the updated neural network parameters and the performance of the reference neural network with the previous neural network parameters.
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US202163177180P | 2021-04-20 | 2021-04-20 | |
US17/694,467 US20220335294A1 (en) | 2021-04-20 | 2022-03-14 | Reporting for machine learning model updates |
PCT/US2022/020355 WO2022225627A1 (en) | 2021-04-20 | 2022-03-15 | Reporting for machine learning model updates |
Publications (1)
Publication Number | Publication Date |
---|---|
BR112023019673A2 true BR112023019673A2 (en) | 2023-10-31 |
Family
ID=81326940
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
BR112023019673A BR112023019673A2 (en) | 2021-04-20 | 2022-03-15 | REPORTS FOR MACHINE LEARNING MODEL UPDATES |
Country Status (4)
Country | Link |
---|---|
EP (1) | EP4327251A1 (en) |
KR (1) | KR20230173664A (en) |
BR (1) | BR112023019673A2 (en) |
WO (1) | WO2022225627A1 (en) |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2572537A (en) * | 2018-03-27 | 2019-10-09 | Nokia Technologies Oy | Generating or obtaining an updated neural network |
CN111611610B (en) * | 2020-04-12 | 2023-05-30 | 西安电子科技大学 | Federal learning information processing method, system, storage medium, program, and terminal |
-
2022
- 2022-03-15 KR KR1020237035182A patent/KR20230173664A/en unknown
- 2022-03-15 WO PCT/US2022/020355 patent/WO2022225627A1/en active Application Filing
- 2022-03-15 BR BR112023019673A patent/BR112023019673A2/en unknown
- 2022-03-15 EP EP22715237.8A patent/EP4327251A1/en active Pending
Also Published As
Publication number | Publication date |
---|---|
EP4327251A1 (en) | 2024-02-28 |
WO2022225627A1 (en) | 2022-10-27 |
KR20230173664A (en) | 2023-12-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3506095A3 (en) | Communication optimizations for distributed machine learning | |
BR112019003171A2 (en) | methods and apparatus for beam information for independent links | |
SE1750625A1 (en) | A method of manufacturing a film having low oxygen transmission rate values | |
WO2010056015A3 (en) | Emergency rescue system using eye expression recognition, and method for same | |
BR112017017739A2 (en) | access point routing | |
BRPI0811634A2 (en) | SYSTEM AND METHOD FOR CREATING AN ONLINE SOCIAL COMMUNICATION NETWORK COMMUNITY | |
BR112021020736A2 (en) | Method and system for dynamically adjusting a configuration of an intra-train communication network | |
BRPI0705901A (en) | method of processing a message on a communication relay network | |
BRPI0702009A (en) | Dynamic syndicated content delivery system and method | |
BRPI0403159A (en) | Organic Fabric Product | |
MX2017000457A (en) | Asphalt coatings for roofing waterproof membranes, waterproof membranes including the asphalt coatings and methods for making the asphalt coatings. | |
BR112019008538A2 (en) | Top link control information transmission method, and terminal device | |
WO2012080707A8 (en) | Method and apparatus for structuring a network | |
GB2574343A (en) | Decision support system and methods associated with same | |
AU2018298640A1 (en) | Determination device, determination method, and determination program | |
BR112023019673A2 (en) | REPORTS FOR MACHINE LEARNING MODEL UPDATES | |
MX2020007346A (en) | Network slice configuration method, first network element and second network element. | |
BRPI0403160A (en) | Method for Manufacturing an Organic Fabric Product | |
WO2021195642A3 (en) | Document control item | |
EP4242069A3 (en) | Updating a controller unit in a vehicle | |
TW200623716A (en) | Client provisioning with linking | |
DE50003112D1 (en) | COLLAGEN-FREE COSMETIC PREPARATIONS | |
BR112018015756A2 (en) | computer-implemented network monitoring identification method, network monitor detection entity, and computer program product | |
BR102013019217A8 (en) | method for evaluating the hydraulic speed of an acoustic node | |
GB2559693A (en) | Managing topic updates for a distributed data system |