Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Intro to ConvNets: The backbone of modern compu...

Avatar for Tryolabs Tryolabs
April 10, 2019
Technology
2.3k
0

Intro to ConvNets: The backbone of modern computer vision

Avatar for Tryolabs

Tryolabs

April 10, 2019

More Decks by Tryolabs

See All by Tryolabs
An Introduction to Machine Learning and How to Teach Machines to See
Avatar for Tryolabs tryolabs
0
2.3k
Tryolabs Workshop: Object Detection with Deep Learning
Avatar for Tryolabs tryolabs
0
520
PyImageConf Workshop: Object Detection with Deep Learning
Avatar for Tryolabs tryolabs
0
300
Introduction to Object Detection - PyCon APAC 2018
Avatar for Tryolabs tryolabs
0
2.8k
Building an Object Detection toolkit with TensorFlow (ODSC West 2017)
Avatar for Tryolabs tryolabs
1
2.6k
Building an Object Detection toolkit with TensorFlow (PyLadies Meetup)
Avatar for Tryolabs tryolabs
1
430
Building an Object Detection toolkit with TensorFlow (ODSC Europe 2017)
Avatar for Tryolabs tryolabs
1
220
Tryolabs Working Trip NYC 2017 in pictures.
Avatar for Tryolabs tryolabs
0
1.7k
Machine Learning 101 - Tryolabs
Avatar for Tryolabs tryolabs
0
230

Other Decks in Technology

See All in Technology
ホームラボ紹介
Avatar for 世良泰明 y_sera15
0
190
ソフトウェアサプライチェーンの構造的リスクとコンテナ環境の保護
Avatar for Kyohei Mizumoto kyohmizu
4
300
Sets in Go
Avatar for Luciano Ramalho ramalho
1
850
なぜ Temporal の大小比較には compare しかないのか / Why Does Temporal Only Have compare() for Comparisons
Avatar for KazukiHayase kazukihayase
1
130
【CEDEC2026】『ウマ娘 プリティーダービー』 英語版のキャラクターの方言や口調をローカライズするための創造的アプローチ
Avatar for Cygames, Inc. cygames
PRO
2
1.1k
MIRU 2026 チュートリアル
Avatar for Keisuke Fujii keisuke198619
0
950
その“隠したつもり”が命取り ── 自前と平文をやめて「正解」に委ねる
Avatar for kuroneko kuroneko13
0
120
QAエンジニア起点で進める、SmartHRにおける信頼性向上について
Avatar for kaomi kaomi_wombat
1
140
FORENSIA: ローカルLLMフォレンジックハーネス
Avatar for S.Nakano sumeshi
2
400
サイバー捜査員研修（前半）
Avatar for Nomizo Nomizo nomizone
1
2k
SO-101×VLAによる3色キューブのピック＆プレース
Avatar for ABEJA abeja
0
210
Agent 時代の Kaggle 展望 / kaggle-in-the-agentic-era
Avatar for Shotaro Ishihara upura
1
770

Featured

See All Featured
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
Avatar for Marc Duiker marcduiker
35
2.5k
Marketing to machines
Avatar for Jono Alderson jonoalderson
1
5.7k
Agile that works and the tools we love
Avatar for Rasmus Luckow-Nielsen rasmusluckow
331
22k
Kristin Tynski - Automating Marketing Tasks With AI
Avatar for Tech SEO Connect techseoconnect
PRO
0
470
Ruling the World: When Life Gets Gamed
Avatar for Sebastian Deterding codingconduct
0
300
ReactJS: Keep Simple. Everything can be a component!
Avatar for Pedro Nauck pedronauck
666
130k
The Power of CSS Pseudo Elements
Avatar for Geoffrey Crofte geoffreycrofte
82
6.5k
Building Experiences: Design Systems, User Experience, and Full Site Editing
Avatar for Michelle Schulp Hunt marktimemedia
0
580
Leveraging LLMs for student feedback in introductory data science courses - posit::conf(2025)
Avatar for Mine Cetinkaya-Rundel minecr
1
340
Building AI with AI
Avatar for Ines Montani inesmontani
PRO
1
1.1k
Done Done
Avatar for chrislema chrislema
186
16k
WENDY [Excerpt]
Avatar for Tessa Abrams tessaabrams
11
39k

Transcript

  1. The backbone of modern computer vision Intro to ConvNets

  2. 2

  3. 3 =

  4. 4

  5. Convolutional Network

  6. 6 ⊙ = Σ input output kernel

  7. 7 input output ⊙ = kernel Σ

  8. 8 input output = kernel Σ ⊙

  9. 9 input output ⊙ = kernel Σ

  10. 10 kernel input output

  11. 11

  12. 12 Optimization Label: Bird ConvNet Loss Function Prediction: Cat

  13. 13 Optimization ConvNet Prediction: Bird Loss Function Label: Bird

  14. 14 Non-linear function from: wikipedia.org Sigmoid Function

  15. 15 Pooling operation from: computersciencewiki.org

  16. 16

  17. 17 Conv layer Non-linear function Convolution & Non-linear function &

    Pooling Pooling Conv layer Non-linear function Pooling Conv layer Non-linear function

  18. 18 AlexNet (2012)

  19. Thanks!