JP2022514935A - 多重予測ネットワーク - Google Patents
多重予測ネットワーク Download PDFInfo
- Publication number
- JP2022514935A JP2022514935A JP2021536301A JP2021536301A JP2022514935A JP 2022514935 A JP2022514935 A JP 2022514935A JP 2021536301 A JP2021536301 A JP 2021536301A JP 2021536301 A JP2021536301 A JP 2021536301A JP 2022514935 A JP2022514935 A JP 2022514935A
- Authority
- JP
- Japan
- Prior art keywords
- predictions
- network
- prediction
- input
- predictive
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 claims abstract description 61
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 12
- 230000006855 networking Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 abstract description 12
- 238000012549 training Methods 0.000 abstract description 8
- 238000013528 artificial neural network Methods 0.000 abstract description 6
- 238000004364 calculation method Methods 0.000 abstract description 6
- 239000003795 chemical substances by application Substances 0.000 description 39
- 230000006870 function Effects 0.000 description 15
- 230000015654 memory Effects 0.000 description 15
- 230000000694 effects Effects 0.000 description 12
- 238000004590 computer program Methods 0.000 description 11
- 238000012545 processing Methods 0.000 description 9
- 238000003860 storage Methods 0.000 description 8
- 230000009471 action Effects 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000006399 behavior Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000009193 crawling Effects 0.000 description 4
- 230000001953 sensory effect Effects 0.000 description 3
- 208000006820 Arthralgia Diseases 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 2
- 230000001143 conditioned effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 208000024765 knee pain Diseases 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000272 proprioceptive effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000005670 electromagnetic radiation Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000010422 painting Methods 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 229920001690 polydopamine Polymers 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/008—Artificial life, i.e. computing arrangements simulating life based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Robotics (AREA)
- User Interface Of Digital Computer (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
Description
f1(S)~f4(S) 出力
Claims (20)
- 機械及びコンピュータベースのソフトウェアアプリケーションにおいて人工知能を形成する多重ヘッド予測方法であって、
環境から状態情報として入力を受け取るステップと、
それぞれが異なる状態情報特徴に対応する複数の予測を出力するステップと、
を含むことを特徴とする方法。 - 前記ネットワークの最後の層を除く全ての層における前記ネットワークの重み又はパラメータが、前記複数の予測の各々の間で共有される、
請求項1に記載の多重ヘッド予測方法。 - 前記ネットワークの最後の層を除く全ての層における前記ネットワークの重み又はパラメータを前記複数の予測の各々の間で共有することによって、前記複数の予測の各々を学習するのに必要な時間を最小化するステップをさらに含む、
請求項1に記載の多重ヘッド予測方法。 - 前記ネットワークの最後の層を除く全ての層における前記ネットワークの重み又はパラメータを前記複数の予測の各々の間で共有することによって、前記複数の予測を計算する計算コストを最小化するステップをさらに含む、
請求項1に記載の多重ヘッド予測方法。 - 前記状態情報を一般化するステップをさらに含む、
請求項1に記載の多重ヘッド予測方法。 - 複数のスキルID及び複数の予測IDのうちの少なくとも1つを入力してハイブリッドネットワークを提供するステップをさらに含み、前記複数の予測は、前記複数のスキルID及び前記複数の予測IDにそれぞれ基づく一連の同様のスキル又は予測のための出力である、
請求項1に記載の多重ヘッド予測方法。 - 機械及びコンピュータベースのソフトウェアアプリケーションにおいて人工知能を形成する多重入力予測方法であって、
環境から状態情報として入力を受け取るステップと、
予測ID、スキルID、及びパラメータ値のうちの少なくとも1つからさらなる入力を受け取るステップと、
前記さらなる入力の各々の予測を出力するステップと、
を含むことを特徴とする方法。 - 前記さらなる入力は複数の予測IDを含み、前記出力される予測は、入力として供給される前記予測IDの予測値である、
請求項7に記載の多重入力予測方法。 - 前記ネットワークの重み又はパラメータが、前記予測のうちの複数の予測にわたって共有される、
請求項7に記載の多重入力予測方法。 - 前記さらなる入力は、複数のスキルIDを含む、
請求項7に記載の多重入力予測方法。 - 共通の状態依存を共有するスキルに基づいて前記予測を一般化するステップをさらに含む、
請求項10に記載の多重入力予測方法。 - 前記さらなる入力は、挙動に影響を与える可変入力パラメータを含む、
請求項7に記載の多重入力予測方法。 - 機械及びコンピュータベースのソフトウェアアプリケーションにおいて人工知能を形成する予測ネットワーク方法であって、
環境から状態情報として入力を受け取るステップと、
予測ID、スキルID、及びパラメータ値のうちの少なくとも1つからさらなる入力を受け取るステップと、
前記さらなる入力を、前記予測ネットワークに入力される前に、学習され縮小されたベクトル表現に埋め込むステップと、
各学習され縮小されたベクトル表現の予測を出力するステップと、
を含むことを特徴とする方法。 - それぞれが異なる状態情報特徴に対応する複数の予測を出力するステップをさらに含む、
請求項13に記載の予測ネットワーク方法。 - 前記ネットワークの最後の層を除く全ての層における前記ネットワークの重み又はパラメータが、前記複数の予測の各々の間で共有される、
請求項14に記載の予測ネットワーク方法。 - 複数のスキルID及び複数の予測IDのうちの少なくとも1つを入力してハイブリッドネットワークを提供するステップをさらに含み、前記複数の予測は、前記複数のスキルID及び前記複数の予測IDにそれぞれ基づく一連の同様のスキル又は予測のための出力である、
請求項14に記載の予測ネットワーク方法。 - 前記さらなる入力は複数の予測IDを含み、前記出力される予測は、入力として供給される前記予測IDの予測値である、
請求項13に記載の予測ネットワーク方法。 - 前記ネットワークの重み又はパラメータが、前記予測のうちの複数の予測にわたって共有される、
請求項17に記載の予測ネットワーク方法。 - 前記さらなる入力は、複数のスキルIDを含む、
請求項17に記載の予測ネットワーク方法。 - 共通の状態依存を共有するスキルに基づいて前記予測を一般化するステップをさらに含む、
請求項19に記載の予測ネットワーク方法。
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201962788339P | 2019-01-04 | 2019-01-04 | |
US62/788,339 | 2019-01-04 | ||
PCT/US2020/012073 WO2020142620A1 (en) | 2019-01-04 | 2020-01-02 | Multi-forecast networks |
Publications (2)
Publication Number | Publication Date |
---|---|
JP2022514935A true JP2022514935A (ja) | 2022-02-16 |
JP7379494B2 JP7379494B2 (ja) | 2023-11-14 |
Family
ID=71404792
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2021536301A Active JP7379494B2 (ja) | 2019-01-04 | 2020-01-02 | 多重予測ネットワーク |
Country Status (6)
Country | Link |
---|---|
US (1) | US20200218992A1 (ja) |
EP (1) | EP3888017A4 (ja) |
JP (1) | JP7379494B2 (ja) |
KR (1) | KR20210090265A (ja) |
CN (1) | CN113228063A (ja) |
WO (1) | WO2020142620A1 (ja) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11670028B1 (en) * | 2019-09-26 | 2023-06-06 | Apple Inc. | Influencing actions of agents |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160217387A1 (en) * | 2015-01-22 | 2016-07-28 | Preferred Networks, Inc. | Machine learning with model filtering and model mixing for edge devices in a heterogeneous environment |
CN106651915A (zh) * | 2016-12-23 | 2017-05-10 | 大连理工大学 | 基于卷积神经网络的多尺度表达的目标跟踪方法 |
CN107085716A (zh) * | 2017-05-24 | 2017-08-22 | 复旦大学 | 基于多任务生成对抗网络的跨视角步态识别方法 |
US20170286830A1 (en) * | 2016-04-04 | 2017-10-05 | Technion Research & Development Foundation Limited | Quantized neural network training and inference |
US20180276691A1 (en) * | 2017-03-21 | 2018-09-27 | Adobe Systems Incorporated | Metric Forecasting Employing a Similarity Determination in a Digital Medium Environment |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130024167A1 (en) | 2011-07-22 | 2013-01-24 | Edward Tilden Blair | Computer-Implemented Systems And Methods For Large Scale Automatic Forecast Combinations |
AU2013207551B2 (en) * | 2012-07-20 | 2015-12-17 | Tata Consultancy Services Limited | Method and system for adaptive forecast of wind resources |
US10055687B2 (en) * | 2014-04-17 | 2018-08-21 | Mark B. Ring | Method for creating predictive knowledge structures from experience in an artificial agent |
US20190171928A1 (en) * | 2016-06-27 | 2019-06-06 | Robin Young | Dynamically managing artificial neural networks |
US20180012411A1 (en) * | 2016-07-11 | 2018-01-11 | Gravity Jack, Inc. | Augmented Reality Methods and Devices |
US10096125B1 (en) * | 2017-04-07 | 2018-10-09 | Adobe Systems Incorporated | Forecasting multiple poses based on a graphical image |
US10943697B2 (en) * | 2017-12-01 | 2021-03-09 | International Business Machines Corporation | Determining information based on an analysis of images and video |
-
2020
- 2020-01-02 EP EP20736098.3A patent/EP3888017A4/en active Pending
- 2020-01-02 WO PCT/US2020/012073 patent/WO2020142620A1/en unknown
- 2020-01-02 KR KR1020217018869A patent/KR20210090265A/ko not_active Application Discontinuation
- 2020-01-02 CN CN202080007396.6A patent/CN113228063A/zh active Pending
- 2020-01-02 JP JP2021536301A patent/JP7379494B2/ja active Active
- 2020-01-02 US US16/732,918 patent/US20200218992A1/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160217387A1 (en) * | 2015-01-22 | 2016-07-28 | Preferred Networks, Inc. | Machine learning with model filtering and model mixing for edge devices in a heterogeneous environment |
US20170286830A1 (en) * | 2016-04-04 | 2017-10-05 | Technion Research & Development Foundation Limited | Quantized neural network training and inference |
CN106651915A (zh) * | 2016-12-23 | 2017-05-10 | 大连理工大学 | 基于卷积神经网络的多尺度表达的目标跟踪方法 |
US20180276691A1 (en) * | 2017-03-21 | 2018-09-27 | Adobe Systems Incorporated | Metric Forecasting Employing a Similarity Determination in a Digital Medium Environment |
CN107085716A (zh) * | 2017-05-24 | 2017-08-22 | 复旦大学 | 基于多任务生成对抗网络的跨视角步态识别方法 |
Also Published As
Publication number | Publication date |
---|---|
CN113228063A (zh) | 2021-08-06 |
KR20210090265A (ko) | 2021-07-19 |
US20200218992A1 (en) | 2020-07-09 |
EP3888017A4 (en) | 2022-08-03 |
WO2020142620A1 (en) | 2020-07-09 |
JP7379494B2 (ja) | 2023-11-14 |
EP3888017A1 (en) | 2021-10-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Luo et al. | A survey on model-based reinforcement learning | |
Jain et al. | A cordial sync: Going beyond marginal policies for multi-agent embodied tasks | |
JP7264376B2 (ja) | 汎用学習済モデルの生成方法 | |
CN110023965A (zh) | 用于选择由机器人智能体执行的动作的神经网络 | |
Zhang et al. | Synergistic integration between machine learning and agent-based modeling: A multidisciplinary review | |
US9524461B1 (en) | Conceptual computation system using a hierarchical network of modules | |
WO2023221928A1 (zh) | 一种推荐方法、训练方法以及装置 | |
CN111176758B (zh) | 配置参数的推荐方法、装置、终端及存储介质 | |
KR102289256B1 (ko) | 자가진단 기반 건강기능식품 추천 서비스 제공 방법, 장치 및 시스템 | |
Guo et al. | Solving combinatorial problems with machine learning methods | |
CN110447041A (zh) | 噪声神经网络层 | |
CN113538162A (zh) | 一种种植策略生成方法、装置、电子设备及存储介质 | |
KR102539679B1 (ko) | 사용자의 경로를 이용하여 사용자 맞춤형 장소 추천 방법, 장치 및 시스템 | |
Jameel et al. | Machine learning techniques for wireless-powered ambient backscatter communications: Enabling intelligent IoT networks in 6G era | |
KR20220045215A (ko) | 게이팅된 어텐션 신경망 | |
JP2022514935A (ja) | 多重予測ネットワーク | |
Noureddine et al. | An agent-based architecture using deep reinforcement learning for the intelligent internet of things applications | |
US11763170B2 (en) | Method and system for predicting discrete sequences using deep context tree weighting | |
US11443229B2 (en) | Method and system for continual learning in an intelligent artificial agent | |
CN114648103A (zh) | 用于处理深度学习网络的自动多目标硬件优化 | |
KR102515168B1 (ko) | 광고 컨텐츠 제작 최적화 방법, 장치 및 시스템 | |
KR102552856B1 (ko) | 커머스 연계 콘텐츠 제공 플랫폼 서비스를 위한 키워드 추출 및 콘텐츠 템플릿 생성 자동화 방법, 장치 및 시스템 | |
CN117518907A (zh) | 智能体的控制方法、装置、设备及存储介质 | |
US11568621B2 (en) | Dynamic character model fitting of three-dimensional digital items | |
Khaldi et al. | A deep recurrent neural network framework for swarm motion speed prediction |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A621 | Written request for application examination |
Free format text: JAPANESE INTERMEDIATE CODE: A621 Effective date: 20210621 |
|
A131 | Notification of reasons for refusal |
Free format text: JAPANESE INTERMEDIATE CODE: A131 Effective date: 20220824 |
|
A601 | Written request for extension of time |
Free format text: JAPANESE INTERMEDIATE CODE: A601 Effective date: 20221124 |
|
A601 | Written request for extension of time |
Free format text: JAPANESE INTERMEDIATE CODE: A601 Effective date: 20230124 |
|
A521 | Request for written amendment filed |
Free format text: JAPANESE INTERMEDIATE CODE: A523 Effective date: 20230222 |
|
A131 | Notification of reasons for refusal |
Free format text: JAPANESE INTERMEDIATE CODE: A131 Effective date: 20230406 |
|
A601 | Written request for extension of time |
Free format text: JAPANESE INTERMEDIATE CODE: A601 Effective date: 20230706 |
|
A521 | Request for written amendment filed |
Free format text: JAPANESE INTERMEDIATE CODE: A523 Effective date: 20230906 |
|
TRDD | Decision of grant or rejection written | ||
A01 | Written decision to grant a patent or to grant a registration (utility model) |
Free format text: JAPANESE INTERMEDIATE CODE: A01 Effective date: 20231002 |
|
A61 | First payment of annual fees (during grant procedure) |
Free format text: JAPANESE INTERMEDIATE CODE: A61 Effective date: 20231101 |
|
R150 | Certificate of patent or registration of utility model |
Ref document number: 7379494 Country of ref document: JP Free format text: JAPANESE INTERMEDIATE CODE: R150 |