JP2022549844A - 加重平均近傍埋め込みの学習 - Google Patents
加重平均近傍埋め込みの学習 Download PDFInfo
- Publication number
- JP2022549844A JP2022549844A JP2022518841A JP2022518841A JP2022549844A JP 2022549844 A JP2022549844 A JP 2022549844A JP 2022518841 A JP2022518841 A JP 2022518841A JP 2022518841 A JP2022518841 A JP 2022518841A JP 2022549844 A JP2022549844 A JP 2022549844A
- Authority
- JP
- Japan
- Prior art keywords
- training
- layer
- neighborhood
- input
- umap
- 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
Links
- 238000012549 training Methods 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 claims abstract description 62
- 238000013528 artificial neural network Methods 0.000 claims abstract description 26
- 230000009467 reduction Effects 0.000 claims abstract description 16
- 238000013507 mapping Methods 0.000 claims description 19
- 238000009826 distribution Methods 0.000 claims description 14
- 230000036962 time dependent Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 230000003190 augmentative effect Effects 0.000 claims 1
- 238000013434 data augmentation Methods 0.000 claims 1
- 230000008901 benefit Effects 0.000 abstract description 6
- 238000010801 machine learning Methods 0.000 abstract description 2
- 239000010410 layer Substances 0.000 description 98
- 230000006870 function Effects 0.000 description 31
- 238000010586 diagram Methods 0.000 description 24
- 238000013459 approach Methods 0.000 description 19
- 230000008859 change Effects 0.000 description 16
- 238000012360 testing method Methods 0.000 description 15
- 238000005070 sampling Methods 0.000 description 10
- 238000002474 experimental method Methods 0.000 description 9
- 230000000875 corresponding effect Effects 0.000 description 8
- 239000000284 extract Substances 0.000 description 7
- 238000013527 convolutional neural network Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000001537 neural effect Effects 0.000 description 4
- 230000002123 temporal effect Effects 0.000 description 4
- 230000009466 transformation Effects 0.000 description 4
- 238000009827 uniform distribution Methods 0.000 description 4
- 230000006978 adaptation Effects 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 238000009795 derivation Methods 0.000 description 2
- 230000008450 motivation Effects 0.000 description 2
- 230000036961 partial effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 239000003292 glue Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 230000008929 regeneration Effects 0.000 description 1
- 238000011069 regeneration method Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
- 238000012800 visualization Methods 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
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/043—Architecture, e.g. interconnection topology based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
-
- 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
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computational Mathematics (AREA)
- Automation & Control Theory (AREA)
- Fuzzy Systems (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Error Detection And Correction (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Complex Calculations (AREA)
Abstract
Description
新しいデータは、定期的に経時変化(aging)データ構造に結合される新しい近傍データ構造に継続的に追加される。
単体集合は、集合のカテゴリである
証明。いずれにせよ、二つの高次元ボールの交差の体積とそれらの対称差を計算することができる。(Li2011)を参照すると、
Claims (17)
- ニューラルネットワークを訓練する方法であって、
加重平均近傍層の勾配バックプロパゲーションが入力ドメインエントリに修正されることを特徴する方法。 - 事前入力プロセス(エンコーダ)が入力ドメインエントリと共に学習されることを特徴とする、請求項1に記載の方法。
- 固定サイズの埋め込み層が無制限の訓練データを有する入力領域分布に適応することを特徴とする、請求項2に記載の方法。
- ニューラルネットワークのデータ拡張訓練または敵対的訓練を特徴とする、請求項3に記載の方法。
- 固定サイズの入力データセットのための黙示的に維持された入力空間エントリを特徴とする、請求項1に記載の方法。
- ニューラルネットワークを訓練する方法であって、
時間依存入力分布に適応する経時割引近傍重みを特徴とする方法。 - ストリーミングデータに適用される可変数の時間適応写像エントリを特徴とする、請求項6に記載の方法。
- 結合動作を介して結合されたメモリ使用を特徴とする、請求項7に記載の方法。
- 入力ドメインエントリに修正された加重平均近傍層の勾配バックプロパゲーションを特徴とする、請求項6に記載の方法。
- 時間依存の入力分布を有する入力のストリームが適用されるときに、近傍埋め込み層を学習することを特徴とする、請求項9に記載の方法。
- ニューラルネットワークにおいて次元削減層を実現する方法であって、
前記次元削減層は、有限集合の入力(基準入力)と所望の低次元出力(基準出力)によってパラメータ化されることを特徴とする方法。 - 前記次元削減層を通って前のニューラルネットワーク層に誤差逆伝播することを特徴とする、請求項11に記載の方法。
- データ拡張または敵対的訓練により前記次元削減層を訓練することを特徴とする、請求項12に記載の方法。
- 基準入力は、メモリに保持されず、ニューラルネットワークの先行する層が維持される前のプレイメージのみが保持されることを特徴とする、請求項12に記載の方法。
- 前記次元削減層は誤差逆伝播され、それによって基準出力および基準入力の両方を更新することを特徴とする、請求項11に記載の方法。
- オンライン訓練プロセス中に、新しい基準入力と基準出力を追加し、定期的に結合して、基準入力の総数が制限されたままになるようにすることを特徴とする、請求項11に記載の方法。
- 基準点の加重平均に使用される経時割引近傍加重を特徴とする、請求項11に記載の方法。
Applications Claiming Priority (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201962904737P | 2019-09-24 | 2019-09-24 | |
US62/904,737 | 2019-09-24 | ||
US17/030,299 | 2020-09-23 | ||
US17/030,299 US20210089924A1 (en) | 2019-09-24 | 2020-09-23 | Learning weighted-average neighbor embeddings |
PCT/US2020/052577 WO2021062052A1 (en) | 2019-09-24 | 2020-09-24 | Learning weighted-average neighbor embeddings |
Publications (1)
Publication Number | Publication Date |
---|---|
JP2022549844A true JP2022549844A (ja) | 2022-11-29 |
Family
ID=74880996
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2022518841A Pending JP2022549844A (ja) | 2019-09-24 | 2020-09-24 | 加重平均近傍埋め込みの学習 |
Country Status (3)
Country | Link |
---|---|
US (1) | US20210089924A1 (ja) |
JP (1) | JP2022549844A (ja) |
WO (1) | WO2021062052A1 (ja) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11785024B2 (en) * | 2021-03-22 | 2023-10-10 | University Of South Florida | Deploying neural-trojan-resistant convolutional neural networks |
US20220343179A1 (en) * | 2021-04-26 | 2022-10-27 | International Business Machines Corporation | Localization-based test generation for individual fairness testing of artificial intelligence models |
US20220358360A1 (en) * | 2021-05-07 | 2022-11-10 | Bentley Systems, Incorporated | Classifying elements and predicting properties in an infrastructure model through prototype networks and weakly supervised learning |
CN116658492B (zh) * | 2023-07-28 | 2023-10-27 | 新疆塔林投资(集团)有限责任公司 | 智能动力猫道及其方法 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009516246A (ja) * | 2005-11-15 | 2009-04-16 | ベルナデット ガーナー | ニューラルネットワークのトレーニング方法 |
JP2012014617A (ja) * | 2010-07-05 | 2012-01-19 | Honda Motor Co Ltd | ニューラルネットワーク学習装置 |
JP2012038240A (ja) * | 2010-08-11 | 2012-02-23 | Sony Corp | 情報処理装置、情報処理方法、及び、プログラム |
CN108229479A (zh) * | 2017-08-01 | 2018-06-29 | 北京市商汤科技开发有限公司 | 语义分割模型的训练方法和装置、电子设备、存储介质 |
US20180342050A1 (en) * | 2016-04-28 | 2018-11-29 | Yougetitback Limited | System and method for detection of mobile device fault conditions |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8775341B1 (en) * | 2010-10-26 | 2014-07-08 | Michael Lamport Commons | Intelligent control with hierarchical stacked neural networks |
US9324022B2 (en) * | 2014-03-04 | 2016-04-26 | Signal/Sense, Inc. | Classifying data with deep learning neural records incrementally refined through expert input |
US20170091619A1 (en) * | 2015-09-29 | 2017-03-30 | Qualcomm Incorporated | Selective backpropagation |
US20170337682A1 (en) * | 2016-05-18 | 2017-11-23 | Siemens Healthcare Gmbh | Method and System for Image Registration Using an Intelligent Artificial Agent |
US11017761B2 (en) * | 2017-10-19 | 2021-05-25 | Baidu Usa Llc | Parallel neural text-to-speech |
-
2020
- 2020-09-23 US US17/030,299 patent/US20210089924A1/en not_active Abandoned
- 2020-09-24 JP JP2022518841A patent/JP2022549844A/ja active Pending
- 2020-09-24 WO PCT/US2020/052577 patent/WO2021062052A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009516246A (ja) * | 2005-11-15 | 2009-04-16 | ベルナデット ガーナー | ニューラルネットワークのトレーニング方法 |
JP2012014617A (ja) * | 2010-07-05 | 2012-01-19 | Honda Motor Co Ltd | ニューラルネットワーク学習装置 |
JP2012038240A (ja) * | 2010-08-11 | 2012-02-23 | Sony Corp | 情報処理装置、情報処理方法、及び、プログラム |
US20180342050A1 (en) * | 2016-04-28 | 2018-11-29 | Yougetitback Limited | System and method for detection of mobile device fault conditions |
CN108229479A (zh) * | 2017-08-01 | 2018-06-29 | 北京市商汤科技开发有限公司 | 语义分割模型的训练方法和装置、电子设备、存储介质 |
Non-Patent Citations (2)
Title |
---|
ARILD NOKLAND: "IMPROVING BACK-PROPAGATION BY ADDING AN ADVERSARIAL GRADIENT", ARXIV, vol. arXiv:1510.04189v2, JPN6023014758, 6 April 2016 (2016-04-06), pages 1 - 8, XP055794859, ISSN: 0005039795 * |
岩澤 有祐 ほか: "敵対的訓練を利用したドメイン不変な表現の学習", 一般社団法人 人工知能学会 第31回全国大会論文集DVD [DVD−ROM], vol. 1A2−OS−05b−3, JPN6023014757, 23 May 2017 (2017-05-23), JP, pages 1 - 4, ISSN: 0005039794 * |
Also Published As
Publication number | Publication date |
---|---|
US20210089924A1 (en) | 2021-03-25 |
WO2021062052A1 (en) | 2021-04-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
You et al. | Graphrnn: Generating realistic graphs with deep auto-regressive models | |
Vahdat et al. | Score-based generative modeling in latent space | |
Bottou et al. | Optimization methods for large-scale machine learning | |
JP6989387B2 (ja) | 古典的なプロセッサで量子類似計算をエミュレートするためのquanton表現 | |
JP2022549844A (ja) | 加重平均近傍埋め込みの学習 | |
Gong et al. | A multiobjective sparse feature learning model for deep neural networks | |
Magris et al. | Bayesian learning for neural networks: an algorithmic survey | |
Carreira-Perpinán et al. | Model compression as constrained optimization, with application to neural nets. Part II: Quantization | |
Gong et al. | Multiobjective sparse non-negative matrix factorization | |
US11544571B2 (en) | Optimizing unsupervised generative adversarial networks via latent space regularizations | |
CN115661550B (zh) | 基于生成对抗网络的图数据类别不平衡分类方法及装置 | |
Manisha et al. | Generative Adversarial Networks (GANs): What it can generate and What it cannot? | |
Tan et al. | Knowledge transfer in evolutionary multi-task optimization: A survey | |
Geyer et al. | Low-rank regularization and solution uniqueness in over-parameterized matrix sensing | |
Huynh et al. | Quantum-inspired machine learning: a survey | |
Zhou et al. | Communication-efficient and Byzantine-robust distributed learning with statistical guarantee | |
Wen et al. | A structure-adaptive hybrid RBF-BP classifier with an optimized learning strategy | |
Dikkala et al. | For manifold learning, deep neural networks can be locality sensitive hash functions | |
Chang | Latent variable modeling for generative concept representations and deep generative models | |
Tang et al. | Concrete subspace learning based interference elimination for multi-task model fusion | |
Li et al. | Analogical Learning-Based Few-Shot Class-Incremental Learning | |
Hasanzadeh et al. | Bayesian graph contrastive learning | |
Pooladzandi | Fast Training of Generalizable Deep Neural Networks | |
Pezeshkpour | Compact factorization of matrices using generalized round-rank | |
Chen et al. | SNAP: Shaping neural architectures progressively via information density criterion |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A621 | Written request for application examination |
Free format text: JAPANESE INTERMEDIATE CODE: A621 Effective date: 20220328 |
|
A977 | Report on retrieval |
Free format text: JAPANESE INTERMEDIATE CODE: A971007 Effective date: 20230322 |
|
A131 | Notification of reasons for refusal |
Free format text: JAPANESE INTERMEDIATE CODE: A131 Effective date: 20230418 |
|
A521 | Request for written amendment filed |
Free format text: JAPANESE INTERMEDIATE CODE: A523 Effective date: 20230621 |
|
A02 | Decision of refusal |
Free format text: JAPANESE INTERMEDIATE CODE: A02 Effective date: 20230912 |