GB2602296B - Training a neural network comprising a plurality of layers - Google Patents

Training a neural network comprising a plurality of layers Download PDF

Info

Publication number
GB2602296B
GB2602296B GB2020392.3A GB202020392A GB2602296B GB 2602296 B GB2602296 B GB 2602296B GB 202020392 A GB202020392 A GB 202020392A GB 2602296 B GB2602296 B GB 2602296B
Authority
GB
United Kingdom
Prior art keywords
training
layers
neural network
neural
network
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
GB2020392.3A
Other versions
GB202020392D0 (en
GB2602296A (en
Inventor
Asad Muhammad
Condorelli Elia
Dikici Cagatay
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Imagination Technologies Ltd
Original Assignee
Imagination Technologies Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Imagination Technologies Ltd filed Critical Imagination Technologies Ltd
Priority to GB2020392.3A priority Critical patent/GB2602296B/en
Priority to GB2311108.1A priority patent/GB2627030A/en
Publication of GB202020392D0 publication Critical patent/GB202020392D0/en
Publication of GB2602296A publication Critical patent/GB2602296A/en
Application granted granted Critical
Publication of GB2602296B publication Critical patent/GB2602296B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
    • 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
    • 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
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Neurology (AREA)
  • Image Analysis (AREA)
GB2020392.3A 2020-12-22 2020-12-22 Training a neural network comprising a plurality of layers Active GB2602296B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
GB2020392.3A GB2602296B (en) 2020-12-22 2020-12-22 Training a neural network comprising a plurality of layers
GB2311108.1A GB2627030A (en) 2020-12-22 2020-12-22 Training a neural network comprising a plurality of layers

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
GB2020392.3A GB2602296B (en) 2020-12-22 2020-12-22 Training a neural network comprising a plurality of layers

Publications (3)

Publication Number Publication Date
GB202020392D0 GB202020392D0 (en) 2021-02-03
GB2602296A GB2602296A (en) 2022-06-29
GB2602296B true GB2602296B (en) 2023-09-06

Family

ID=74221278

Family Applications (1)

Application Number Title Priority Date Filing Date
GB2020392.3A Active GB2602296B (en) 2020-12-22 2020-12-22 Training a neural network comprising a plurality of layers

Country Status (1)

Country Link
GB (1) GB2602296B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113065636B (en) * 2021-02-27 2024-06-07 华为技术有限公司 Pruning processing method, data processing method and equipment for convolutional neural network

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190294928A1 (en) * 2018-03-21 2019-09-26 Megvii (Beijing) Technology Co., Ltd. Image processing method and apparatus, and computer-readable storage medium
WO2020131968A1 (en) * 2018-12-18 2020-06-25 Movidius Ltd. Neural network compression

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2579399B (en) 2018-11-30 2020-12-16 Imagination Tech Ltd Data compression and storage

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190294928A1 (en) * 2018-03-21 2019-09-26 Megvii (Beijing) Technology Co., Ltd. Image processing method and apparatus, and computer-readable storage medium
WO2020131968A1 (en) * 2018-12-18 2020-06-25 Movidius Ltd. Neural network compression

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
CORNELL UNIVERSITY LIBRARY, 2017, JIAN-HAO LUO ET AL, "ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression" *
CORNELL UNIVERSITY LIBRARY, 2020, MUHAMMAD UMAIR HAIDER ET AL, "Comprehensive Online Network Pruning via Learnable Scaling Factors" *
IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WAVC), 2019, SINGH PRAVENDRA ET AL, "Multi-Layer Pruning Framework for Compressing Single Shot MultiBox Detector", pages 1318-1327 *

Also Published As

Publication number Publication date
GB202020392D0 (en) 2021-02-03
GB2602296A (en) 2022-06-29

Similar Documents

Publication Publication Date Title
GB2596412B (en) Techniques for modifying and training a neural network
GB202113649D0 (en) Knowledge discovery using a neural network
GB201703330D0 (en) Training a computational neural network
IL271929A (en) Training a neural network with representations of user interface devices
EP3948775A4 (en) Image processing using a convolutional neural network to track a plurality of objects
SG11201903591QA (en) Fast computation of a convolutional neural network
GB201821192D0 (en) A computer-implemented method of training a graph neural network
GB202203221D0 (en) Neural network training technique
SG11202110345XA (en) Training of artificial neural networks
GB2602296B (en) Training a neural network comprising a plurality of layers
GB2589382B (en) Hardware implementation of a neural network
EP3881623C0 (en) Configuring a maximum number of transmission layers
EP4226285A4 (en) Anonymous training of a learning model
GB202200873D0 (en) Techniques to process layers of a three-dimensial image using one or more neural networks
GB202201148D0 (en) Neural network training technique
GB202311108D0 (en) Training a neural network comprising a plurality of layers
IL288021B1 (en) Cluster-connected neural network
GB201907476D0 (en) Multilayer set of neural networks
GB2601543B (en) Method of training a neural network
GB202015128D0 (en) Method and sustem for training a neural network
GB2623044B (en) Training a neural network
GB202207318D0 (en) A behaviour training aid
GB202213576D0 (en) Training a neural network
GB202215480D0 (en) A neural network training method and apparatus thereof
GB202008786D0 (en) A bird deterrent apparatus

Legal Events

Date Code Title Description
732E Amendments to the register in respect of changes of name or changes affecting rights (sect. 32/1977)

Free format text: REGISTERED BETWEEN 20240822 AND 20240828