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
170
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
490

Other Decks in Science

See All in Science
プロジェクト「Azayaka」のSARの数式とジオメトリ
Avatar for じゃらしまる syuchimu
0
380
機械学習 - K近傍法 & 機械学習のお作法
Avatar for Y. Yamamoto trycycle
PRO
1
1.6k
見上公一.pdf
Avatar for Genomethica genomethica
0
170
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
1.4k
データベース14: B+木 & ハッシュ索引
Avatar for Y. Yamamoto trycycle
PRO
0
710
(CVPR2026) Back to Basics: Let Denoising Generative Models Denoise
Avatar for Shumpei Takezaki shumpei777
0
220
[第67回 CV勉強会＠関東] CV × Scientific Figures / kantoCV 67th CVPR 2026
Avatar for ライチ lychee1223
0
150
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
JSAI2026企画セッションKS-14 インタビュー集『⼈⼯知能と哲学と四つの問い』が提起する⼈⼯知能のこれからの課題 趣旨説明 / JSAI2026 Special Session: A Collection of Interviews, “Artificial Intelligence, Philosophy, and Four Questions”
Avatar for Kiyota Yoji, Ph.D. ykiyota
0
380
Wet Active Matter
Avatar for Rajesh Singh rajeshrinet
0
120
（メタ）科学コミュニケーターからみたAI for Scienceの同床異夢
Avatar for Ryuichi Maruyama rmaruy
0
260
機械学習 - pandas入門
Avatar for Y. Yamamoto trycycle
PRO
0
660

Featured

See All Featured
Game over? The fight for quality and originality in the time of robots
Avatar for Wayne Barker wayneb77
1
220
What does AI have to do with Human Rights?
Avatar for Per Axbom axbom
PRO
1
2.3k
From π to Pie charts
Avatar for Rasagy Sharma rasagy
0
240
Color Theory Basics | Prateek | Gurzu
Avatar for Gurzu gurzu
0
390
WENDY [Excerpt]
Avatar for Tessa Abrams tessaabrams
11
38k
Darren the Foodie - Storyboard
Avatar for Kevinho.art khoart
PRO
3
3.4k
Context Engineering - Making Every Token Count
Avatar for Addy Osmani addyosmani
9
1k
10 Git Anti Patterns You Should be Aware of
Avatar for Lemi Orhan Ergin lemiorhan
PRO
659
62k
Documentation Writing (for coders)
Avatar for Carmen Chung carmenintech
77
5.4k
StorybookのUI Testing Handbookを読んだ
Avatar for Shingo Yamazaki zakiyama
31
6.8k
Being A Developer After 40
Avatar for Adrian Kosmaczewski akosma
91
590k
The Curse of the Amulet
Avatar for Matthew Lei leimatthew05
2
13k

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)