$30 off During Our Annual Pro Sale. View Details »

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
380
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
440
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
CV_5_3dVision
Avatar for Mohammed Hachama hachama
0
170
データベース05: SQL(2/3) 結合質問
Avatar for Y. Yamamoto trycycle
PRO
0
840
Text-to-SQLの既存の評価指標を問い直す
Avatar for Gota gotalab555
1
130
データベース03: 関係データモデル
Avatar for Y. Yamamoto trycycle
PRO
1
310
生成検索エンジン最適化に関する研究の紹介
Avatar for Yu Nakano / 中野優 ynakano
2
1.4k
凸最適化からDC最適化まで
Avatar for ざきまつ santana_hammer
1
320
Accelerated Computing for Climate forecast
Avatar for Jeongkyu Shin inureyes
PRO
0
130
機械学習 - SVM
Avatar for Y. Yamamoto trycycle
PRO
1
920
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
2
620
【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
1.9k
サイコロで理解する原子核崩壊と拡散現象 〜単純化されたモデルで本質を理解する〜
Avatar for Syota-Sasaki syotasasaki593876
0
120
NDCG is NOT All I Need
Avatar for statditto statditto
2
2.4k

Featured

See All Featured
Typedesign – Prime Four
Avatar for Hannes Fritz hannesfritz
42
2.9k
Bootstrapping a Software Product
Avatar for Garrett Dimon garrettdimon
PRO
307
110k
How to Ace a Technical Interview
Avatar for Jacob Kaplan-Moss jacobian
280
24k
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
Avatar for Kevin Liebholz kevinliebholz
36
6.1k
Statistics for Hackers
Avatar for Jake VanderPlas jakevdp
799
230k
Designing Dashboards & Data Visualisations in Web Apps
Avatar for Des Traynor destraynor
231
54k
ReactJS: Keep Simple. Everything can be a component!
Avatar for Pedro Nauck pedronauck
666
130k
Refactoring Trust on Your Teams (GOTO; Chicago 2020)
Avatar for Rebecca Miller-Webster rmw
35
3.2k
How to Create Impact in a Changing Tech Landscape [PerfNow 2023]
Avatar for Tammy Everts tammyeverts
55
3.1k
The Hidden Cost of Media on the Web [PixelPalooza 2025]
Avatar for Tammy Everts tammyeverts
1
62
Done Done
Avatar for chrislema chrislema
186
16k
The Psychology of Web Performance [Beyond Tellerrand 2023]
Avatar for Tammy Everts tammyeverts
49
3.2k

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)