JP7692482B2 - ニューラルネットワークにおける過剰予測のための方法およびシステム - Google Patents

ニューラルネットワークにおける過剰予測のための方法およびシステム Download PDF

Info

Publication number
JP7692482B2
JP7692482B2 JP2023532791A JP2023532791A JP7692482B2 JP 7692482 B2 JP7692482 B2 JP 7692482B2 JP 2023532791 A JP2023532791 A JP 2023532791A JP 2023532791 A JP2023532791 A JP 2023532791A JP 7692482 B2 JP7692482 B2 JP 7692482B2
Authority
JP
Japan
Prior art keywords
layer
machine learning
learning model
prediction
confidence score
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
JP2023532791A
Other languages
English (en)
Japanese (ja)
Other versions
JP2023551325A5 (https=
JP2023551325A (ja
Inventor
ホアン，コン・ズイ・ブー
ブー，タン・ティエン
ザレムーディ，ポーヤ
シュ，イン
ブリノフ，ブラディスラフ
ホング，ユ－ヘング
ダルマシリ，ヤクピティヤゲ・ドン・タヌジャ・サモッダイ
ビシュノイ，ビシャル
ルクマン ジャラルッディン，エリアス・
パレク，マニッシュ
ドゥオング，タン・ロング
ジョンソン，マーク・エドワード
Original Assignee
オラクル・インターナショナル・コーポレイション
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 オラクル・インターナショナル・コーポレイション filed Critical オラクル・インターナショナル・コーポレイション
Publication of JP2023551325A publication Critical patent/JP2023551325A/ja
Publication of JP2023551325A5 publication Critical patent/JP2023551325A5/ja
Application granted granted Critical
Publication of JP7692482B2 publication Critical patent/JP7692482B2/ja
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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 OR CALCULATING; 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
    • G06N3/0455—Auto-encoder networks; Encoder-decoder networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/0499—Feedforward networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
    • G06N3/09—Supervised learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/0985—Hyperparameter optimisation; Meta-learning; Learning-to-learn

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)
  • Machine Translation (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
JP2023532791A 2020-11-30 2021-11-17 ニューラルネットワークにおける過剰予測のための方法およびシステム Active JP7692482B2 (ja)

Applications Claiming Priority (5)

Application Number Priority Date Filing Date Title
US202063119566P 2020-11-30 2020-11-30
US63/119,566 2020-11-30
US17/455,181 2021-11-16
US17/455,181 US12518129B2 (en) 2020-11-30 2021-11-16 Method and system for over-prediction in neural networks
PCT/US2021/059686 WO2022115291A1 (en) 2020-11-30 2021-11-17 Method and system for over-prediction in neural networks

Publications (3)

Publication Number Publication Date
JP2023551325A JP2023551325A (ja) 2023-12-07
JP2023551325A5 JP2023551325A5 (https=) 2024-06-13
JP7692482B2 true JP7692482B2 (ja) 2025-06-13

Family

ID=81751544

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2023532791A Active JP7692482B2 (ja) 2020-11-30 2021-11-17 ニューラルネットワークにおける過剰予測のための方法およびシステム

Country Status (5)

Country Link
US (1) US12518129B2 (https=)
EP (1) EP4252149A1 (https=)
JP (1) JP7692482B2 (https=)
CN (1) CN116490879A (https=)
WO (1) WO2022115291A1 (https=)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12499313B2 (en) * 2021-01-21 2025-12-16 Servicenow, Inc. Ensemble scoring system for a natural language understanding (NLU) framework
US11842737B2 (en) 2021-03-24 2023-12-12 Google Llc Automated assistant interaction prediction using fusion of visual and audio input
US20230237589A1 (en) * 2022-01-21 2023-07-27 Intuit Inc. Model output calibration
US12010075B2 (en) * 2022-06-29 2024-06-11 Chime Financial, Inc. Utilizing machine learning models to generate interactive digital text threads with personalized digital text reply options
US12608373B2 (en) 2022-08-22 2026-04-21 Oracle International Corporation Detecting out-of-domain, out-of-scope, and confusion-span (OOCS) input for a natural language to logical form model
US12430330B2 (en) * 2022-08-22 2025-09-30 Oracle International Corporation Calibrating confidence scores of a machine learning model trained as a natural language interface
US12536283B2 (en) * 2022-11-09 2026-01-27 Saudi Arabian Oil Company Multi-layered machine learning model and use thereof
US11936814B1 (en) 2022-11-22 2024-03-19 Chime Financial, Inc. Utilizing machine learning models to generate interactive digital text threads with personalized agent escalation digital text reply options

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2014049118A (ja) 2012-08-31 2014-03-17 Fujitsu Ltd 畳み込みニューラルネットワーク分類器システム、その訓練方法、分類方法および用途
JP2020168233A (ja) 2019-04-04 2020-10-15 株式会社日立製作所 超音波撮像装置、および、画像処理装置
US20200342850A1 (en) 2019-04-26 2020-10-29 Oracle International Corporation Routing for chatbots

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10353905B2 (en) * 2015-04-24 2019-07-16 Salesforce.Com, Inc. Identifying entities in semi-structured content
CN107590153B (zh) * 2016-07-08 2021-04-27 微软技术许可有限责任公司 使用卷积神经网络的对话相关性建模
US10617959B2 (en) 2018-01-18 2020-04-14 Moveworks, Inc. Method and system for training a chatbot
CN108874972B (zh) 2018-06-08 2021-10-19 合肥工业大学 一种基于深度学习的多轮情感对话方法
US10693872B1 (en) * 2019-05-17 2020-06-23 Q5ID, Inc. Identity verification system
WO2020241772A1 (ja) * 2019-05-31 2020-12-03 国立大学法人京都大学 情報処理装置、スクリーニング装置、情報処理方法、スクリーニング方法、及びプログラム
KR102814913B1 (ko) * 2019-10-02 2025-05-30 삼성전자주식회사 응답 추론 방법 및 장치

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2014049118A (ja) 2012-08-31 2014-03-17 Fujitsu Ltd 畳み込みニューラルネットワーク分類器システム、その訓練方法、分類方法および用途
JP2020168233A (ja) 2019-04-04 2020-10-15 株式会社日立製作所 超音波撮像装置、および、画像処理装置
US20200342850A1 (en) 2019-04-26 2020-10-29 Oracle International Corporation Routing for chatbots

Also Published As

Publication number Publication date
WO2022115291A1 (en) 2022-06-02
EP4252149A1 (en) 2023-10-04
US20220172021A1 (en) 2022-06-02
US12518129B2 (en) 2026-01-06
CN116490879A (zh) 2023-07-25
JP2023551325A (ja) 2023-12-07

Similar Documents

Publication Publication Date Title
JP7692432B2 (ja) 制約に基づくハイパーパラメータチューニングのための方法およびシステム
US12236321B2 (en) Batching techniques for handling unbalanced training data for a chatbot
JP7851913B2 (ja) テキスト分類についての説明を与えるための技術
US12249314B2 (en) Routing for chatbots
JP7682202B2 (ja) ドメイン外（ｏｏｄ）検出のための改良された技術
US12099816B2 (en) Multi-factor modelling for natural language processing
US12288550B2 (en) Framework for focused training of language models and techniques for end-to-end hypertuning of the framework
JP7692482B2 (ja) ニューラルネットワークにおける過剰予測のための方法およびシステム
JP7771196B2 (ja) 自然言語プロセッサのための複数特徴均衡化
KR20240089615A (ko) 사전-트레이닝된 언어 모델의 단일 트랜스포머 계층으로부터의 다중-헤드 네트워크의 미세-튜닝
JP2023544328A (ja) チャットボットの自動スコープ外遷移
US12210830B2 (en) System and techniques for handling long text for pre-trained language models
JP2024540111A (ja) 文書からの埋め込まれるデータの抽出のための深層学習技術
US12112560B2 (en) Usage based resource utilization of training pool for chatbots
KR20240111760A (ko) 자연어 프로세싱을 위한 경로 드롭아웃
US20230136965A1 (en) Prohibiting inconsistent named entity recognition tag sequences
JP2025530343A (ja) ターゲットベースのハイパーパラメータチューニングにおける目的関数最適化
WO2023091436A1 (en) System and techniques for handling long text for pre-trained language models

Legal Events

Date Code Title Description
A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20240605

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20240605

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20250318

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20250319

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20250416

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: 20250507

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20250603

R150 Certificate of patent or registration of utility model

Ref document number: 7692482

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150