GB2635811A - Anomalous event prediction using contrastive learning - Google Patents

Anomalous event prediction using contrastive learning Download PDF

Info

Publication number
GB2635811A
GB2635811A GB2412570.0A GB202412570A GB2635811A GB 2635811 A GB2635811 A GB 2635811A GB 202412570 A GB202412570 A GB 202412570A GB 2635811 A GB2635811 A GB 2635811A
Authority
GB
United Kingdom
Prior art keywords
training
feature vector
data
contextual
feature
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.)
Pending
Application number
GB2412570.0A
Other languages
English (en)
Other versions
GB202412570D0 (en
Inventor
Hossein Rezaeian Amir
Polleri Alberto
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.)
Oracle International Corp
Original Assignee
Oracle International Corp
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 Oracle International Corp filed Critical Oracle International Corp
Publication of GB202412570D0 publication Critical patent/GB202412570D0/en
Publication of GB2635811A publication Critical patent/GB2635811A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/40—Document-oriented image-based pattern recognition
    • G06V30/41—Analysis of document content
    • G06V30/413—Classification of content, e.g. text, photographs or tables
    • 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
    • G06N3/044—Recurrent networks, e.g. Hopfield 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
    • 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
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • 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
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • G06N3/0895—Weakly supervised learning, e.g. semi-supervised or self-supervised learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
GB2412570.0A 2022-03-15 2022-11-21 Anomalous event prediction using contrastive learning Pending GB2635811A (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US17/654,891 US20230298371A1 (en) 2022-03-15 2022-03-15 Anomalous event prediction using contrastive learning
PCT/US2022/050531 WO2023177426A1 (en) 2022-03-15 2022-11-21 Anomalous event prediction using contrastive learning

Publications (2)

Publication Number Publication Date
GB202412570D0 GB202412570D0 (en) 2024-10-09
GB2635811A true GB2635811A (en) 2025-05-28

Family

ID=84830018

Family Applications (1)

Application Number Title Priority Date Filing Date
GB2412570.0A Pending GB2635811A (en) 2022-03-15 2022-11-21 Anomalous event prediction using contrastive learning

Country Status (5)

Country Link
US (1) US20230298371A1 (https=)
JP (1) JP2025512750A (https=)
CN (1) CN118871930A (https=)
GB (1) GB2635811A (https=)
WO (1) WO2023177426A1 (https=)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12455896B2 (en) * 2023-04-12 2025-10-28 Tyco Fire & Security Gmbh Building management system with generative AI-based interactive service tool
US12406232B2 (en) 2023-04-12 2025-09-02 Tyco Fire & Security Gmbh Building management system with generative AI-based automated flexible customer report generation and standardization
US12282305B2 (en) 2023-04-12 2025-04-22 Tyco Fire & Security Gmbh Building management system with generative AI-based predictive maintenance
US12242937B1 (en) 2023-04-12 2025-03-04 Tyco Fire & Security Gmbh Building management system with generative AI-based root cause prediction
US12181844B2 (en) 2023-04-12 2024-12-31 Tyco Fire & Security Gmbh Building management system with natural language model-based data structure generation
CN119443195A (zh) * 2023-07-30 2025-02-14 鸿海精密工业股份有限公司 机器学习方法
CN119046541B (zh) * 2024-10-31 2025-03-04 山东科技大学 一种基于社区感知与多尺度图对比学习的推荐方法
CN121502692A (zh) * 2026-01-12 2026-02-10 国网安徽省电力有限公司合肥供电公司 一种基于多源数据融合的人才全景画像及动态评价方法

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210374570A1 (en) * 2020-05-26 2021-12-02 Apple Inc. Subject-aware contrastive learning for biosignals

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010541415A (ja) * 2007-09-28 2010-12-24 グレースノート インコーポレイテッド マルチメディアイベントのプレゼンテーションの合成
US20160253597A1 (en) * 2015-02-27 2016-09-01 Xerox Corporation Content-aware domain adaptation for cross-domain classification
US20210334645A1 (en) * 2020-04-28 2021-10-28 Nvidia Corporation Notifications determined using one or more neural networks
US11900336B2 (en) * 2020-05-05 2024-02-13 Capital One Services, Llc Computer-based systems configured for automated activity verification based on optical character recognition models and methods of use thereof

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210374570A1 (en) * 2020-05-26 2021-12-02 Apple Inc. Subject-aware contrastive learning for biosignals

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
JIHOON TACK ET AL, "CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 21 October 2020 (2020-10-21), the whole document *
SNEHASHIS MAJHI ET AL, "Two-Stream CNN Architecture for Anomalous Event Detection in Real World Scenarios : 4th International Conference, CVIP 2019, Jaipur, India, September 27-29, 2019, Revised Selected Papers, Part II", COMPUTER VISION, PATTERN RECOGNITION, IMAGE PROCESSING, AND GRAPHICS *

Also Published As

Publication number Publication date
JP2025512750A (ja) 2025-04-22
CN118871930A (zh) 2024-10-29
US20230298371A1 (en) 2023-09-21
WO2023177426A1 (en) 2023-09-21
GB202412570D0 (en) 2024-10-09

Similar Documents

Publication Publication Date Title
GB2635811A (en) Anomalous event prediction using contrastive learning
Wu et al. Imitation learning from imperfect demonstration
JP2025512750A5 (https=)
Chen et al. Co-training for domain adaptation
Ao et al. Fast generalized distillation for semi-supervised domain adaptation
Zhang et al. A fast online learning algorithm for distributed mining of bigdata
WO2025048983A1 (en) System and method for generating a trained neural network from a pretrained machine learning model
Zhang et al. FAT-DeepFFM: Field attentive deep field-aware factorization machine
GB2629950A (en) Attention neural networks with gated attention units
WO2021064856A1 (ja) ロバスト学習装置、ロバスト学習方法、プログラム及び記憶装置
US20230108177A1 (en) Hardware-Aware Progressive Training Of Machine Learning Models
Feofilov et al. Application of Recurrent Neural Networks in Closed Loop Tracking Systems for Controlling Essentially Nonlinear Objects
JP2000517447A (ja) ニューラルネットワーク用の少なくとも１つの人工的トレーニングデータベクトルをコンピュータ支援により生成するための方法及び装置
CN112784984A (zh) 一种模型训练方法及装置
Chou et al. The importance of calibration: Rethinking confidence and performance of speech multi-label emotion classifiers
Esaki et al. One-shot domain incremental learning
Solo The second order properties of a time series recursion
Unceta et al. Sampling unknown decision functions to build classifier copies
Jovanovic et al. Generative adversarial networks for synthetic training data replacement in phishing email detection using natural language processing
EP4124887A1 (en) Methods and systems for predicting trajectory data of an object and methods and systems for training a machine learning method for predicting trajectory data of an object
CN120180226A (zh) 基于双低秩适应的视觉-文本预训练模型在开放类别测试时的训练方法和系统
Kůrková et al. Classification of Large Data Sets by Neural Networks: A Probabilistic Viewpoint
CN112926302A (zh) 语音识别文本的断句与标点预测方法及其装置、存储介质
Guo et al. Weighted L 2-gain analysis and fault-tolerant control of nonlinear discrete-time saturated switched systems with time-varying delays
Kumar et al. Performance Evaluation of Text Classifier for NLP using Machine Learning Techniques