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
0
2.1k

Intro to ConvNets: The backbone of modern computer vision

Avatar for Tryolabs

Tryolabs

April 10, 2019
Tweet

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
2.1k
Tryolabs Workshop: Object Detection with Deep Learning
Avatar for Tryolabs tryolabs
0
430
PyImageConf Workshop: Object Detection with Deep Learning
Avatar for Tryolabs tryolabs
0
270
Introduction to Object Detection - PyCon APAC 2018
Avatar for Tryolabs tryolabs
0
2.5k
Building an Object Detection toolkit with TensorFlow (ODSC West 2017)
Avatar for Tryolabs tryolabs
1
2.3k
Building an Object Detection toolkit with TensorFlow (PyLadies Meetup)
Avatar for Tryolabs tryolabs
1
410
Building an Object Detection toolkit with TensorFlow (ODSC Europe 2017)
Avatar for Tryolabs tryolabs
1
210
Tryolabs Working Trip NYC 2017 in pictures.
Avatar for Tryolabs tryolabs
0
1.6k
Machine Learning 101 - Tryolabs
Avatar for Tryolabs tryolabs
0
210

Other Decks in Technology

See All in Technology
Adapty_東京AI祭ハッカソン2025ピッチスライド
Avatar for shino shinoyamada
0
280
綺麗なデータマートをつくろう_データ整備を前向きに考える会 / Let's create clean data mart
Avatar for BrainPad brainpadpr
3
450
「使い方教えて」「事例教えて」じゃもう遅い！ Microsoft 365 Copilot を触り倒そう！
Avatar for Taichi Nakamura taichinakamura
0
360
ガバメントクラウドの概要と自治体事例（名古屋市）
Avatar for 高橋広和 techniczna
2
230
リーダーになったら未来を語れるようになろう/Speak the Future
Avatar for Genki Sano sanogemaru
0
390
なぜAWSを活かしきれないのか？技術と組織への処方箋
Avatar for NRI Netcom nrinetcom
PRO
4
800
【Kaigi on Rails 事後勉強会LT】MeはどうしてGirlsに？ 私とRubyを繋いだRail(s)
Avatar for joy joyfrommasara
0
240
Exadata Database Service on Dedicated Infrastructure(ExaDB-D) UI スクリーン・キャプチャ集
Avatar for oracle4engineer oracle4engineer
PRO
3
5.5k
ComposeではないコードをCompose化する case ビズリーチ / DroidKaigi 2025 koyasai
Avatar for Visional Engineering ＆ Design visional_engineering_and_design
0
110
Simplifying Cloud Native app testing across environments with Dapr and Microcks
Avatar for Salaboy salaboy
0
150
能登半島地震で見えた災害対応の課題と組織変革の重要性
Avatar for Masakatsu Sugii ditccsugii
0
660
Escaping_the_Kraken_-_October_2025.pdf
Avatar for Maarten Dalmijn mdalmijn
0
170

Featured

See All Featured
Mobile First: as difficult as doing things right
Avatar for Swwweet swwweet
224
10k
Distributed Sagas: A Protocol for Coordinating Microservices
Avatar for Caitie McCaffrey caitiem20
333
22k
Balancing Empowerment & Direction
Avatar for Lara Hogan lara
4
690
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
Avatar for Marc Duiker marcduiker
32
2.3k
Producing Creativity
Avatar for Steve Smith orderedlist
PRO
347
40k
Designing for humans not robots
Avatar for Tammie Lister tammielis
254
26k
Testing 201, or: Great Expectations
Avatar for Joseph Mastey jmmastey
45
7.7k
The MySQL Ecosystem @ GitHub 2015
Avatar for Sam Lambert samlambert
251
13k
Speed Design
Avatar for Sergey Chernyshev sergeychernyshev
32
1.2k
Practical Orchestrator
Avatar for Shlomi Noach shlominoach
190
11k
Making Projects Easy
Avatar for Brett Harned brettharned
119
6.4k
Measuring & Analyzing Core Web Vitals
Avatar for Philip Tellis bluesmoon
9
620

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!