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
2.2k

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
440
OpenTalks.AI - Александр Громов, Устойчивость нейросетевых моделей при анализе КТ/НДКТ-исследований
Avatar for OpenTalks.AI opentalks
0
380
OpenTalks.AI - Денис Тимонин, Megatron-LM: Обучение мультимиллиардных LMs при помощи техники Model Parallelism
Avatar for OpenTalks.AI opentalks
0
520
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
390
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
450
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
480

Other Decks in Science

See All in Science
次代のデータサイエンティストへ～スキルチェックリスト、タスクリスト更新～
Avatar for The Japan DataScientist Society datascientistsociety
PRO
2
28k
【論文紹介】Is CLIP ideal? No. Can we fix it?Yes! 第65回 コンピュータビジョン勉強会＠関東
Avatar for Shun Makino shun6211
5
2.3k
Navigating Weather and Climate Data
Avatar for Ryan Abernathey rabernat
0
110
Distributional Regression
Avatar for takyas tackyas
0
340
凸最適化からDC最適化まで
Avatar for ざきまつ santana_hammer
1
350
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
460
2025-05-31-pycon_italia
Avatar for Sofie Van Landeghem sofievl
0
140
Accelerating operator Sinkhorn iteration with overrelaxation
Avatar for Tasuku Soma tasusu
0
200
NASの容量不足のお悩み解決！災害対策も兼ねた「Wasabi Cloud NAS」はここがスゴイ
Avatar for Climb climbteam
1
340
Text-to-SQLの既存の評価指標を問い直す
Avatar for Gota gotalab555
1
170
知能とはなにかーヒトとAIのあいだー
Avatar for Y-h. Taguchi tagtag
PRO
0
150
データベース06: SQL (3/3) 副問い合わせ
Avatar for Y. Yamamoto trycycle
PRO
1
720

Featured

See All Featured
Building the Perfect Custom Keyboard
Avatar for Naoto Takai takai
2
690
VelocityConf: Rendering Performance Case Studies
Avatar for Addy Osmani addyosmani
333
24k
Conquering PDFs: document understanding beyond plain text
Avatar for Ines Montani inesmontani
PRO
4
2.3k
Typedesign – Prime Four
Avatar for Hannes Fritz hannesfritz
42
3k
The World Runs on Bad Software
Avatar for Brandon Keepers bkeepers
PRO
72
12k
Building Experiences: Design Systems, User Experience, and Full Site Editing
Avatar for Michelle Schulp Hunt marktimemedia
0
410
Winning Ecommerce Organic Search in an AI Era - #searchnstuff2025
Avatar for Aleyda Solis aleyda
1
1.9k
Exploring anti-patterns in Rails
Avatar for Elle Meredith aemeredith
2
260
A Tale of Four Properties
Avatar for Chris Coyier chriscoyier
162
24k
Ten Tips & Tricks for a 🌱 transition
Avatar for Manu Carrasco Molina stuffmc
0
72
Deep Space Network (abreviated)
Avatar for Tony Rice tonyrice
0
67
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
Avatar for Eileen M. Uchitelle eileencodes
141
34k

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)