WO2014009031A3 - Artificial memory system and method for use with a computational machine for interacting with dynamic behaviours - Google Patents

Artificial memory system and method for use with a computational machine for interacting with dynamic behaviours Download PDF

Info

Publication number
WO2014009031A3
WO2014009031A3 PCT/EP2013/056104 EP2013056104W WO2014009031A3 WO 2014009031 A3 WO2014009031 A3 WO 2014009031A3 EP 2013056104 W EP2013056104 W EP 2013056104W WO 2014009031 A3 WO2014009031 A3 WO 2014009031A3
Authority
WO
WIPO (PCT)
Prior art keywords
memory system
interacting
artificial
artificial memory
computational machine
Prior art date
Application number
PCT/EP2013/056104
Other languages
French (fr)
Other versions
WO2014009031A2 (en
Inventor
Luca Ascari
Federico SASSI
Matteo Sacchi
Luca MUSSI
Jonas Ambeck-Madsen
Ichiro SAKATO
Hiromichi Yanagihara
Original Assignee
Toyota Motor Europe Nv/Sa
Henesis S.R.L.
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
Priority claimed from PCT/EP2012/063371 external-priority patent/WO2013004846A1/en
Application filed by Toyota Motor Europe Nv/Sa, Henesis S.R.L. filed Critical Toyota Motor Europe Nv/Sa
Priority to EP13711422.9A priority Critical patent/EP2870571B1/en
Priority to US14/413,944 priority patent/US11074497B2/en
Priority to JP2015520855A priority patent/JP2015525924A/en
Publication of WO2014009031A2 publication Critical patent/WO2014009031A2/en
Publication of WO2014009031A3 publication Critical patent/WO2014009031A3/en

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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Testing Or Calibration Of Command Recording Devices (AREA)
  • Machine Translation (AREA)
  • Manipulator (AREA)
  • Feedback Control In General (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

This invention relates to an artificial memory system and a method of continuous learning for predicting and anticipating human operator´s action as response to ego-intention as well as environmental influences during machine operation. More specifically the invention relates to an architecture with artificial memory for interacting with dynamic behaviors of a tool and an operator, wherein the architecture is a first neural network having structures and mechanisms for abstraction, generalization and learning, the network implementation comprising an artificial hierarchical memory system.
PCT/EP2013/056104 2011-07-07 2013-03-22 Artificial memory system and method for use with a computational machine for interacting with dynamic behaviours WO2014009031A2 (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP13711422.9A EP2870571B1 (en) 2012-07-09 2013-03-22 Artificial memory system and method for use with a computational machine for interacting with dynamic behaviours
US14/413,944 US11074497B2 (en) 2011-07-07 2013-03-22 Artificial memory system and method for use with a computational machine for interacting with dynamic behaviours
JP2015520855A JP2015525924A (en) 2012-07-09 2013-03-22 Artificial memory system and method for interacting with dynamic behavior using a computer

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EPPCT/EP2012/063371 2012-07-09
PCT/EP2012/063371 WO2013004846A1 (en) 2011-07-07 2012-07-09 Artificial memory system and method for use with a computational machine for interacting with dynamic behaviours

Publications (2)

Publication Number Publication Date
WO2014009031A2 WO2014009031A2 (en) 2014-01-16
WO2014009031A3 true WO2014009031A3 (en) 2014-04-10

Family

ID=47915264

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2013/056104 WO2014009031A2 (en) 2011-07-07 2013-03-22 Artificial memory system and method for use with a computational machine for interacting with dynamic behaviours

Country Status (2)

Country Link
JP (1) JP2015525924A (en)
WO (1) WO2014009031A2 (en)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107924484A (en) 2015-07-23 2018-04-17 丰田汽车欧洲股份有限公司 For the system and computer based method in environmental background Imitating class people's controlling behavior
US9914475B2 (en) * 2015-10-05 2018-03-13 Delphi Technologies, Inc. Humanized steering model for automated vehicles
US11151446B2 (en) * 2015-10-28 2021-10-19 Google Llc Stream-based accelerator processing of computational graphs
US10223613B2 (en) * 2016-05-31 2019-03-05 Microsoft Technology Licensing, Llc Machine intelligent predictive communication and control system
JP6773099B2 (en) 2018-10-30 2020-10-21 トヨタ自動車株式会社 Control device
WO2021087341A1 (en) * 2019-10-30 2021-05-06 Fraign Analytics, Llc Task concatenation and prediction of operator and system response in socio-technical systems using artificial intelligence
GB2590671A (en) * 2019-12-23 2021-07-07 Airbus Operations Ltd Control system
JP7204717B2 (en) * 2020-09-29 2023-01-16 トヨタ モーター ヨーロッパ A system and computer-based method for simulating human-like control behavior in an environmental context.
CN112560712B (en) * 2020-12-18 2023-05-26 西安电子科技大学 Behavior recognition method, device and medium based on time enhancement graph convolutional network
CN115277220B (en) * 2022-07-29 2023-10-20 西安热工研究院有限公司 Industrial control network traffic safety classification method, system and readable storage device

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080167820A1 (en) * 2007-01-04 2008-07-10 Kentaro Oguchi System for predicting driver behavior
WO2013004846A1 (en) * 2011-07-07 2013-01-10 Toyota Motor Europe Nv/Sa Artificial memory system and method for use with a computational machine for interacting with dynamic behaviours

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070192267A1 (en) * 2006-02-10 2007-08-16 Numenta, Inc. Architecture of a hierarchical temporal memory based system
DE102008040077A1 (en) 2008-07-02 2010-01-07 Robert Bosch Gmbh Driver assistance process

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080167820A1 (en) * 2007-01-04 2008-07-10 Kentaro Oguchi System for predicting driver behavior
WO2013004846A1 (en) * 2011-07-07 2013-01-10 Toyota Motor Europe Nv/Sa Artificial memory system and method for use with a computational machine for interacting with dynamic behaviours

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
ANDREAS ANDREAKIS ET AL: "Incremental Unsupervised Time Series Analysis Using Merge Growing Neural Gas", 8 June 2009, ADVANCES IN SELF-ORGANIZING MAPS, SPRINGER BERLIN HEIDELBERG, BERLIN, HEIDELBERG, PAGE(S) 10 - 18, ISBN: 978-3-642-02396-5, XP019119791 *
CHARALAMPOUS K ET AL: "Sparse deep-learning algorithm for recognition and categorisation", ELECTRONICS LETTERS, IEE STEVENAGE, GB, vol. 48, no. 20, 27 September 2012 (2012-09-27), pages 1265 - 1266, XP006039594, ISSN: 0013-5194, DOI: 10.1049/EL.2012.1033 *
FEDERICO SASSI ET AL: "Classifying Human Body Acceleration Patterns Using a Hierarchical Temporal Memory", 9 December 2009, AI*IA 2009: EMERGENT PERSPECTIVES IN ARTIFICIAL INTELLIGENCE, SPRINGER BERLIN HEIDELBERG, BERLIN, HEIDELBERG, PAGE(S) 496 - 505, ISBN: 978-3-642-10290-5, XP019134305 *
IOANNIS KOSTAVELIS ET AL: "On the optimization of Hierarchical Temporal Memory", PATTERN RECOGNITION LETTERS, vol. 33, no. 5, 1 April 2012 (2012-04-01), pages 670 - 676, XP055099972, ISSN: 0167-8655, DOI: 10.1016/j.patrec.2011.11.017 *
JEFF HAWKINS ET AL: "Hierarchical Temporal Memory Concepts, Theory, and Terminology", INTERNET CITATION, 27 March 2007 (2007-03-27), pages 1 - 20, XP002499414, Retrieved from the Internet <URL:http://www.numenta.com/Numenta_HTM_Concepts.pdf> [retrieved on 20081007] *

Also Published As

Publication number Publication date
WO2014009031A2 (en) 2014-01-16
JP2015525924A (en) 2015-09-07

Similar Documents

Publication Publication Date Title
WO2014009031A3 (en) Artificial memory system and method for use with a computational machine for interacting with dynamic behaviours
WO2015196133A3 (en) Energy infrastructure sensor data rectification using regression models
EP3710998A4 (en) Machine-leaning models based on non-local neural networks
EP3779727A4 (en) Dangerous behavior prediction device, prediction model generation device, and dangerous behavior prediction program
MX2016006764A (en) Method and system for artificially intelligent model-based control of dynamic processes using probabilistic agents.
EP3467724A4 (en) Device and method for generating artificial neural network-based prediction model
EP3679524A4 (en) Execution method, execution device, learning method, learning device, and program for deep neural network
WO2014162181A3 (en) System and method for personalized hemodynamics modeling and monitoring
WO2015100177A3 (en) Neural watchdog
EP3732674A4 (en) A low-power keyword spotting system
EP3530535A4 (en) Vehicle movement control device, vehicle movement control method, and vehicle movement control program
WO2015120243A8 (en) Application execution control utilizing ensemble machine learning for discernment
EP3089081A4 (en) Hierarchical neural network device, learning method for determination device, and determination method
WO2013038175A3 (en) Autonomous vehicle and task modelling
EP4005498A4 (en) Information processing device, program, learned model, diagnostic assistance device, learning device, and method for generating prediction model
EP3528072A4 (en) Operation state monitoring device, and learning data generation device, method, and program
WO2012036958A3 (en) Identifying one or more activities of an animate or inanimate object
EP3835972A4 (en) Cognitive impairment prediction device, prediction model generation device, and program for cognitive impairment prediction
EP4220399A3 (en) Dynamic reconfiguration of applications on a multi-processor embedded system
GB201217271D0 (en) Traffic sensor management
WO2016080655A3 (en) Method for spraying fragrance by considering user&#39;s situation
WO2013050953A3 (en) Methods, apparatuses, and computer program products for restricting overlay of an augmentation
EP3780003A4 (en) Prediction system, model generation system, method, and program
EP3779728A4 (en) Phenomenon prediction device, prediction model generation device, and phenomenon prediction program
WO2012006007A3 (en) Systems and methods for improving visual attention models

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2015520855

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 14413944

Country of ref document: US

Ref document number: 2013711422

Country of ref document: EP

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 13711422

Country of ref document: EP

Kind code of ref document: A2