Upgrade to Pro — share decks privately, control downloads, hide ads and more …

OpenTalks.AI - Александр Артеменков, Towards Sc...

Avatar for OpenTalks.AI OpenTalks.AI
February 21, 2020
Science
2.2k
0

OpenTalks.AI - Александр Артеменков, Towards Scalable Dimensionality Reduction via Noise Contrastive Estimation

Avatar for OpenTalks.AI

OpenTalks.AI

February 21, 2020

More Decks by OpenTalks.AI

See All by OpenTalks.AI
OpenTalks.AI - Виктор Лемпицкий, Моделирование 3Д сцен: новые подходы в 2020 году
Avatar for OpenTalks.AI opentalks
0
500
OpenTalks.AI - Алексей Чернявский, Нейросетевые алгоритмы для повышения качества медицинских изображений
Avatar for OpenTalks.AI opentalks
0
450
OpenTalks.AI - Александр Громов, Устойчивость нейросетевых моделей при анализе КТ/НДКТ-исследований
Avatar for OpenTalks.AI opentalks
0
390
OpenTalks.AI - Денис Тимонин, Megatron-LM: Обучение мультимиллиардных LMs при помощи техники Model Parallelism
Avatar for OpenTalks.AI opentalks
0
540
OpenTalks.AI - Егор Филимонов, Возможности платформы Huawei Atlas и эффективный гетерогенный инференс.
Avatar for OpenTalks.AI opentalks
0
180
OpenTalks.AI - Александр Прозоров, Референсная архитектура робота сервисного центра в отраслях с изменчивыми бизнес-процессами
Avatar for OpenTalks.AI opentalks
0
400
OpenTalks.AI - Наталья Лукашевич, Анализ тональности по отношению к компании — с чем не справился BERT
Avatar for OpenTalks.AI opentalks
0
350
OpenTalks.AI - Константин Воронцов, Фейковые новости и другие типы потенциально опасного дискурса: типология, подходы, датасеты, соревнования
Avatar for OpenTalks.AI opentalks
0
460
OpenTalks.AI - Дмитрий Ветров, Фрактальность функции потерь, эффект двойного спуска и степенные законы в глубинном обучении - фрагменты одной мозаики
Avatar for OpenTalks.AI opentalks
0
500

Other Decks in Science

See All in Science
How a camera trap data standard enabled an ecosystem of interoperable tools
Avatar for Peter Desmet peterdesmet
0
110
TypeScript で WebAssembly を用いた 型安全なプラグイン設計
Avatar for glassmonenkey nagano
2
600
ハミルトン・ヤコビ方程式の解の性質と物理的意味
Avatar for Etsuji Nakai enakai00
0
870
データベース12: 正規化(2/2) - データ従属性に基づく正規化
Avatar for Y. Yamamoto trycycle
PRO
0
1.7k
データベース05: SQL(2/3) 結合質問
Avatar for Y. Yamamoto trycycle
PRO
0
1.3k
機械学習 - 決定木からはじめる機械学習
Avatar for Y. Yamamoto trycycle
PRO
0
1.6k
不動産業界における業界特化のデータ整備とAI活用 ─Vertical DataとVertical AI─
Avatar for estie | エスティ estie
1
930
J-STAGE全文XML登載必須化について
Avatar for XSPA xspa2012
0
1.4k
水耕栽培：古代の知恵から宇宙農業まで
Avatar for 栽培設計室 grow_design_lab
0
210
AI bij literatuuronderzoek in de wetenschap
Avatar for voginip voginip
0
240
データベース03: 関係データモデル
Avatar for Y. Yamamoto trycycle
PRO
1
800
データベース08: 実体関連モデルとは?
Avatar for Y. Yamamoto trycycle
PRO
0
1.6k

Featured

See All Featured
Google's AI Overviews - The New Search
Avatar for Barry Adams badams
0
1.6k
Intergalactic Javascript Robots from Outer Space
Avatar for Vicent Martí tanoku
273
27k
The Hidden Cost of Media on the Web [PixelPalooza 2025]
Avatar for Tammy Everts tammyeverts
2
480
Build your cross-platform service in a week with App Engine
Avatar for Jose L jlugia
234
19k
Keith and Marios Guide to Fast Websites
Avatar for Keith Pitt keithpitt
413
23k
How to Align SEO within the Product Triangle To Get 
Buy-In & Support - #RIMC
Avatar for Aleyda Solis aleyda
2
1.8k
Rails Girls Zürich Keynote
Avatar for Gregor Martynus gr2m
96
14k
DBのスキルで生き残る技術 - AI時代におけるテーブル設計の勘所
Avatar for soudai sone soudai
PRO
68
57k
SEO Brein meetup: CTRL+C is not how to scale international SEO
Avatar for Linda Hogenes lindahogenes
1
2.8k
SEO in 2025: How to Prepare for the Future of Search
Avatar for Michael King ipullrank
3
3.8k
How to optimise 3,500 product descriptions for ecommerce in one day using ChatGPT
Avatar for Katarina Dahlin katarinadahlin
PRO
2
3.8k
ラッコキーワード サービス紹介資料
Avatar for ラッコ株式会社 rakko
1
4.6M

Transcript

  1. Towards Scalable Dimensionality Reduction Aleksandr Artemenkov joint work with Maxim

    Panov via Noise Contrastive Estimation

  2. News Headlines Of India 3 million topics you are unfamiliar

    with Kaggle Dataset
  3. None

  4. Just repeat 3 million times! (not a good idea)

  5. Is there a better approach? (visualization)

  6. None

  7. Noise Contrastive Estimation (without a single formula) (check out the

    poster for them)

  8. Building Representation “cold” “frosty” “cold” “warm” “cold” “first” similar different

    unrelated (noisy) ? ? ?

  9. Simple Insight • similar points = closer than predefined noisy

    distance • different points = further than predefined noisy distance Any benefits from such approach?

  10. Parallelized Batch Optimization • noisy distance is predefined • repel

    different points • attract similar points • adjustments are independent of each other to distinguish them from noise Meet NCVis! (Noise Contrastive Visualization) GitHub Repository

  11. Why use NCVis? (there are reasons) Paper

  12. None
  13. None

  14. Thank you for your attention! (find me near the poster)