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
0
2.1k

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

Avatar for OpenTalks.AI

OpenTalks.AI

February 21, 2020
Tweet

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
490
OpenTalks.AI - Алексей Чернявский, Нейросетевые алгоритмы для повышения качества медицинских изображений
Avatar for OpenTalks.AI opentalks
0
430
OpenTalks.AI - Александр Громов, Устойчивость нейросетевых моделей при анализе КТ/НДКТ-исследований
Avatar for OpenTalks.AI opentalks
0
370
OpenTalks.AI - Денис Тимонин, Megatron-LM: Обучение мультимиллиардных LMs при помощи техники Model Parallelism
Avatar for OpenTalks.AI opentalks
0
510
OpenTalks.AI - Егор Филимонов, Возможности платформы Huawei Atlas и эффективный гетерогенный инференс.
Avatar for OpenTalks.AI opentalks
0
150
OpenTalks.AI - Александр Прозоров, Референсная архитектура робота сервисного центра в отраслях с изменчивыми бизнес-процессами
Avatar for OpenTalks.AI opentalks
0
370
OpenTalks.AI - Наталья Лукашевич, Анализ тональности по отношению к компании — с чем не справился BERT
Avatar for OpenTalks.AI opentalks
0
340
OpenTalks.AI - Константин Воронцов, Фейковые новости и другие типы потенциально опасного дискурса: типология, подходы, датасеты, соревнования
Avatar for OpenTalks.AI opentalks
0
430
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
470

Other Decks in Science

See All in Science
データベース03: 関係データモデル
Avatar for Y. Yamamoto trycycle
PRO
1
270
SciPyDataJapan 2025
Avatar for k schwalbe10
0
270
機械学習 - 決定木からはじめる機械学習
Avatar for Y. Yamamoto trycycle
PRO
0
1.1k
データベース10: 拡張実体関連モデル
Avatar for Y. Yamamoto trycycle
PRO
0
990
05_山中真也_室蘭工業大学大学院工学研究科教授_だてプロの挑戦.pdf
Avatar for Sip3ristex sip3ristex
0
660
知能とはなにかーヒトとAIのあいだー
Avatar for Y-h. Taguchi tagtag
0
140
07_浮世満理子_アイディア高等学院学院長_一般社団法人全国心理業連合会代表理事_紹介資料.pdf
Avatar for Sip3ristex sip3ristex
0
630
会社でMLモデルを作るとは @電気通信大学 データアントレプレナーフェロープログラム
Avatar for yuto16 yuto16
1
270
安心・効率的な医療現場の実現へ　～オンプレAI & ノーコードワークフローで進める業務改革～
Avatar for W&B Si siyoo
0
360
Quelles valorisations des logiciels vers le monde socio-économique dans un contexte de Science Ouverte ?
Avatar for BlueHats bluehats
1
530
研究って何だっけ / What is Research?
Avatar for Kenji Saito ks91
PRO
1
130
Machine Learning for Materials (Challenge)
Avatar for Aron Walsh aronwalsh
0
340

Featured

See All Featured
Navigating Team Friction
Avatar for Lara Hogan lara
189
15k
Agile that works and the tools we love
Avatar for Rasmus Luckow-Nielsen rasmusluckow
331
21k
Build your cross-platform service in a week with App Engine
Avatar for Jose L jlugia
232
18k
Fight the Zombie Pattern Library - RWD Summit 2016
Avatar for Marcelo Somers marcelosomers
234
17k
Chrome DevTools: State of the Union 2024 - Debugging React & Beyond
Avatar for Addy Osmani addyosmani
7
900
Embracing the Ebb and Flow
Avatar for Simon Collison colly
88
4.8k
Intergalactic Javascript Robots from Outer Space
Avatar for Vicent Martí tanoku
273
27k
GraphQLの誤解/rethinking-graphql
Avatar for sonatard sonatard
73
11k
Performance Is Good for Brains [We Love Speed 2024]
Avatar for Tammy Everts tammyeverts
12
1.2k
Rails Girls Zürich Keynote
Avatar for Gregor Martynus gr2m
95
14k
The Cult of Friendly URLs
Avatar for Andy Hume andyhume
79
6.6k
Context Engineering - Making Every Token Count
Avatar for Addy Osmani addyosmani
5
220

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)