BR112023019978A2 - Treinamento de redes neurais de controle de taxa por meio de aprendizado por reforço - Google Patents

Treinamento de redes neurais de controle de taxa por meio de aprendizado por reforço

Info

Publication number
BR112023019978A2
BR112023019978A2 BR112023019978A BR112023019978A BR112023019978A2 BR 112023019978 A2 BR112023019978 A2 BR 112023019978A2 BR 112023019978 A BR112023019978 A BR 112023019978A BR 112023019978 A BR112023019978 A BR 112023019978A BR 112023019978 A2 BR112023019978 A2 BR 112023019978A2
Authority
BR
Brazil
Prior art keywords
rate control
training
control neural
reinforcement learning
neural networks
Prior art date
Application number
BR112023019978A
Other languages
English (en)
Inventor
Balkishan Mandhane Amol
Anton Zhernov
Chenjie Gu
J Mankowitz Daniel
Julian Schrittwieser
Elizabeth Rauh Mary
Miaosen Wang
Keisuke Hubert Thomas
Original Assignee
Deepmind Tech 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 Deepmind Tech Ltd filed Critical Deepmind Tech Ltd
Publication of BR112023019978A2 publication Critical patent/BR112023019978A2/pt

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
    • G06N3/092—Reinforcement learning
    • 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
    • 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/102—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
    • H04N19/124—Quantisation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
    • H04N19/136—Incoming video signal characteristics or properties
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
    • H04N19/146—Data rate or code amount at the encoder output
    • H04N19/147—Data rate or code amount at the encoder output according to rate distortion criteria

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Biophysics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Neurology (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)
  • Studio Devices (AREA)
  • Feedback Control In General (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)

Abstract

treinamento de redes neurais de controle de taxa por meio de aprendizado por reforço. sistemas e métodos para treinar redes neurais de controle de taxa por meio de aprendizado por reforço. durante treinamento, valores de recompensa para exemplos de treinamento são gerados a partir do desempenho atual da rede neural de controle de taxa ao codificar o vídeo no exemplo de treinamento e do desempenho histórico da rede neural de controle de taxa ao codificar o vídeo no exemplo de treinamento.
BR112023019978A 2021-05-28 2022-05-30 Treinamento de redes neurais de controle de taxa por meio de aprendizado por reforço BR112023019978A2 (pt)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US202163194940P 2021-05-28 2021-05-28
PCT/EP2022/064566 WO2022248736A1 (en) 2021-05-28 2022-05-30 Training rate control neural networks through reinforcement learning

Publications (1)

Publication Number Publication Date
BR112023019978A2 true BR112023019978A2 (pt) 2023-11-21

Family

ID=82258546

Family Applications (1)

Application Number Title Priority Date Filing Date
BR112023019978A BR112023019978A2 (pt) 2021-05-28 2022-05-30 Treinamento de redes neurais de controle de taxa por meio de aprendizado por reforço

Country Status (8)

Country Link
EP (1) EP4289138A1 (pt)
JP (1) JP7498377B2 (pt)
KR (1) KR20230148252A (pt)
CN (1) CN117044199A (pt)
AU (1) AU2022279597B2 (pt)
BR (1) BR112023019978A2 (pt)
CA (1) CA3214193A1 (pt)
WO (1) WO2022248736A1 (pt)

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100790900B1 (ko) 2006-12-14 2008-01-03 삼성전자주식회사 영상 부호화를 위한 초기 ＱＰ (ＱｕａｎｔｉｚａｔｉｏｎＰａｒａｍｅｔｅｒ) 값 예측 방법 및 장치
US10499056B2 (en) 2016-03-09 2019-12-03 Sony Corporation System and method for video processing based on quantization parameter
US10721471B2 (en) 2017-10-26 2020-07-21 Intel Corporation Deep learning based quantization parameter estimation for video encoding
TWI789581B (zh) 2019-04-23 2023-01-11 國立陽明交通大學 用於視頻編碼器的強化學習方法
CN112399176B (zh) 2020-11-17 2022-09-16 深圳市创智升科技有限公司 一种视频编码方法、装置、计算机设备及存储介质

Also Published As

Publication number Publication date
JP7498377B2 (ja) 2024-06-11
AU2022279597A1 (en) 2023-10-05
EP4289138A1 (en) 2023-12-13
CA3214193A1 (en) 2022-12-01
KR20230148252A (ko) 2023-10-24
WO2022248736A1 (en) 2022-12-01
JP2024521612A (ja) 2024-06-04
AU2022279597B2 (en) 2024-07-11
CN117044199A (zh) 2023-11-10

Similar Documents

Publication Publication Date Title
EP3596618A4 (en) REAL-TIME, INCREMENTAL, ONLINE LEARNING TO MARK AND LABEL DATA FLOWS FOR DEEP NEURAL NETWORKS AND NEURAL NETWORK APPLICATIONS
WO2019228550A3 (en) Blockchain data storage based on shared nodes and error correction code
MX2021001833A (es) Metodos y aparatos de procesamiento de video con prediccion bidireccional en sistemas de codificacion de video.
WO2020111754A3 (ko) 세미 슈퍼바이즈드 학습을 이용한 진단 시스템 제공방법 및 이를 이용하는 진단 시스템
EP4236317A3 (en) Adaptive bit rate ratio control
IN2014DE00528A (pt)
EP4024763A4 (en) NETWORK CONGESTION CONTROL METHOD, NODE, SYSTEM AND STORAGE MEDIUM
GB2600245B (en) Predictive control using one or more neural networks
EP3756144A4 (en) METHOD, DEVICE AND SYSTEM FOR GENERATION OF BAYESIAN INFERENCE WITH A SPIKING NEURAL NETWORK
BR112023019978A2 (pt) Treinamento de redes neurais de controle de taxa por meio de aprendizado por reforço
ATE545130T1 (de) Verfahren zur optimierung der durchführung eines neuronalen netzwerkes in einem spracherkennungssystem durch bedingtes überspringen einer variablen anzahl von zeitfenstern
Li et al. Fuzzy Markov chains based on the fuzzy transition probability
CN115828863A (zh) 混沌工程试验场景下应急预案自动生成方法
ZA202105148B (en) Data processing device, data processing system, and data processing method
Cámara Quorum sensing: A cell-cell signalling mechanism used to coordinate behavioral changes in bacterial populations
MX2021013752A (es) Metodo y dispositivo para codificar video en funcion del tama?o del video y metodo y dispositivo para decodificar video en funcion del tama?o del video.
SE1851397A1 (en) Adaptive behaviour of embedded systems for increased robustness against communication downtime
Song et al. An improved adaptive genetic algorithm
Sudhir Patil et al. Composite Adaptive Lyapunov-Based Deep Neural Network (Lb-DNN) Controller
Smoorenburg et al. Comparison of model predictive control methods that can account for uncertainties in forecasts of flood discharge and storm surge; case study Volkerak-Zoommeer, the Netherlands
MX2023003242A (es) Metodo y aparato de transmision de informacion y medio de almacenamiento legible por computadora.
Witczak et al. Design of robust predictive fault-tolerant control for takagi-sugeno fuzzy systems: Application to the twin-rotor system
SE0203872D0 (sv) Method and arrangement in a communication system
Božić Neuro adaptive control of nonlinear processes
Wong et al. An Evaluation of Machine Learning Techniques to Support Latency-Sensitive Human-to-Machine (H2M) Communications