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
480
OpenTalks.AI - Алексей Чернявский, Нейросетевые алгоритмы для повышения качества медицинских изображений
Avatar for OpenTalks.AI opentalks
0
420
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
500
OpenTalks.AI - Егор Филимонов, Возможности платформы Huawei Atlas и эффективный гетерогенный инференс.
Avatar for OpenTalks.AI opentalks
0
140
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
330
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
460

Other Decks in Science

See All in Science
機械学習 - 決定木からはじめる機械学習
Avatar for Y. Yamamoto trycycle
PRO
0
960
機械学習 - K-means & 階層的クラスタリング
Avatar for Y. Yamamoto trycycle
PRO
0
920
02_西村訓弘_プログラムディレクター_人口減少を機にひらく未来社会.pdf
Avatar for Sip3ristex sip3ristex
0
480
統計学入門講座 第1回スライド
Avatar for TechmathProject techmathproject
0
340
ウェブ・ソーシャルメディア論文読み会 第25回: Differences in misinformation sharing can lead to politically asymmetric sanctions (Nature, 2024)
Avatar for taichi_murayama hkefka385
0
110
Explanatory material
Avatar for InnovativeSpaceCerrier yuki1986
0
310
2025-06-11-ai_belgium
Avatar for Sofie Van Landeghem sofievl
1
120
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
480
MoveItを使った産業用ロボット向け動作作成方法の紹介 / Introduction to creating motion for industrial robots using MoveIt
Avatar for Ryo Kabutan ry0_ka
0
490
Masseyのレーティングを用いたフォーミュラレースドライバーの実績評価手法の開発 / Development of a Performance Evaluation Method for Formula Race Drivers Using Massey Ratings
Avatar for konakalab konakalab
0
160
baseballrによるMLBデータの抽出と階層ベイズモデルによる打率の推定 / TokyoR118
Avatar for 森下光之助 dropout009
1
440
トラブルがあったコンペに学ぶデータ分析
Avatar for tereka114 tereka114
2
1.6k

Featured

See All Featured
Docker and Python
Avatar for Tania Allard trallard
44
3.4k
A Modern Web Designer's Workflow
Avatar for Chris Coyier chriscoyier
694
190k
The Cult of Friendly URLs
Avatar for Andy Hume andyhume
79
6.5k
GitHub's CSS Performance
Avatar for Jon Rohan jonrohan
1031
460k
How To Stay Up To Date on Web Technology
Avatar for Chris Coyier chriscoyier
790
250k
4 Signs Your Business is Dying
Avatar for Josh Pigford shpigford
184
22k
The Illustrated Children's Guide to Kubernetes
Avatar for Chris Short chrisshort
48
50k
Fantastic passwords and where to find them - at NoRuKo
Avatar for Phil Nash philnash
51
3.3k
Performance Is Good for Brains [We Love Speed 2024]
Avatar for Tammy Everts tammyeverts
10
930
Stop Working from a Prison Cell
Avatar for Chris Michel hatefulcrawdad
270
20k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
Avatar for Stéphanie Walter stephaniewalter
281
13k
Become a Pro
Avatar for Speaker Deck speakerdeck
PRO
28
5.4k

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)