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
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
【RSJ2025】PAMIQ Core: リアルタイム継続学習のための⾮同期推論・学習フレームワーク
Avatar for Geson Anko gesonanko
0
230
AIに仕事を奪われる
最初の医師たちへ
Avatar for iKora128 ikora128
0
990
データマイニング - コミュニティ発見
Avatar for Y. Yamamoto trycycle
PRO
0
170
Gemini Prompt Engineering: Practical Techniques for Tangible AI Outcomes
Avatar for Mfonobong Umondia mfonobong
2
190
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
390
機械学習 - K近傍法 & 機械学習のお作法
Avatar for Y. Yamamoto trycycle
PRO
0
1.2k
Accelerated Computing for Climate forecast
Avatar for Jeongkyu Shin inureyes
PRO
0
130
Explanatory material
Avatar for InnovativeSpaceCerrier yuki1986
0
420
AI(人工知能)の過去・現在・未来 —AIは人間を超えるのか—
Avatar for Y-h. Taguchi tagtag
0
110
データから見る勝敗の法則 / The principle of victory discovered by science (open lecture in NSSU)
Avatar for konakalab konakalab
1
210
タンパク質間相互作⽤を利⽤した⼈⼯知能による新しい薬剤遺伝⼦-疾患相互作⽤の同定
Avatar for Y-h. Taguchi tagtag
0
100
白金鉱業Meetup_Vol.20 効果検証ことはじめ / Introduction to Impact Evaluation
Avatar for BrainPad brainpadpr
2
1.3k

Featured

See All Featured
Measuring & Analyzing Core Web Vitals
Avatar for Philip Tellis bluesmoon
9
660
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
Avatar for Kevin Liebholz kevinliebholz
36
6.1k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
Avatar for panda_program panda_program
116
20k
GraphQLの誤解/rethinking-graphql
Avatar for sonatard sonatard
73
11k
4 Signs Your Business is Dying
Avatar for Josh Pigford shpigford
186
22k
Writing Fast Ruby
Avatar for Erik Berlin sferik
630
62k
Automating Front-end Workflow
Avatar for Addy Osmani addyosmani
1371
200k
Fantastic passwords and where to find them - at NoRuKo
Avatar for Phil Nash philnash
52
3.5k
Learning to Love Humans: Emotional Interface Design
Avatar for Aarron Walter aarron
274
41k
Music & Morning Musume
Avatar for Bryan Veloso bryan
46
6.9k
Making the Leap to Tech Lead
Avatar for Ryan Cromwell cromwellryan
135
9.6k
Documentation Writing (for coders)
Avatar for Carmen Chung carmenintech
76
5.1k

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)