Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Intro to ConvNets: The backbone of modern compu...
Search
Tryolabs
April 10, 2019
Technology
2.3k
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Intro to ConvNets: The backbone of modern computer vision
Tryolabs
April 10, 2019
More Decks by Tryolabs
See All by Tryolabs
An Introduction to Machine Learning and How to Teach Machines to See
tryolabs
0
2.3k
Tryolabs Workshop: Object Detection with Deep Learning
tryolabs
0
520
PyImageConf Workshop: Object Detection with Deep Learning
tryolabs
0
300
Introduction to Object Detection - PyCon APAC 2018
tryolabs
0
2.8k
Building an Object Detection toolkit with TensorFlow (ODSC West 2017)
tryolabs
1
2.6k
Building an Object Detection toolkit with TensorFlow (PyLadies Meetup)
tryolabs
1
420
Building an Object Detection toolkit with TensorFlow (ODSC Europe 2017)
tryolabs
1
220
Tryolabs Working Trip NYC 2017 in pictures.
tryolabs
0
1.7k
Machine Learning 101 - Tryolabs
tryolabs
0
230
Other Decks in Technology
See All in Technology
MCPをつなげて作る組織横断のAIエージェント基盤
tsubakimoto_s
0
140
AI時代におけるテストの基礎の再定義 / Rethinking the Fundamentals of Testing in the AI Era
mineo_matsuya
14
5.4k
Webの技術とガジェットで子どもも大人も楽しめるワクワク体験を提供する / Qiita Tech Festa Day 2026
you
PRO
1
270
AIエージェントがあれば技術書なんてすぐ書けるでしょ→無理でした
watany
4
380
2年前に削除したPHPクラスが、 ある日突然決済をエラーにした
ykagano
1
810
AI時代こそ、スケールしないことをしよう -「作る人」から「なぜ作るか」を考える人へ / Do Things That Don't Scale in the AI Era — From How to Why
kaminashi
1
120
AIが当たり前の組織で エンジニアはどう育つか
nishihira
1
1.2k
ダッシュボード"開発"について 〜使われるダッシュボードのつくりかた〜
kimichan
0
220
「休む」重要さ
smt7174
6
1.7k
伝票作成AIエージェントを支える、LLMOpsとインフラの選択肢 / AICon2026_takeda
rakus_dev
0
270
クラウドを使う側から、作る側へ / 大吉祥寺.pm 2026前夜祭
fujiwara3
6
1.3k
そのドキュメント、自動化しませんか?
yuksew
1
430
Featured
See All Featured
Why You Should Never Use an ORM
jnunemaker
PRO
61
9.9k
Testing 201, or: Great Expectations
jmmastey
46
8.2k
Automating Front-end Workflow
addyosmani
1370
210k
The untapped power of vector embeddings
frankvandijk
2
1.8k
Designing for Timeless Needs
cassininazir
1
400
So, you think you're a good person
axbom
PRO
2
2.1k
Noah Learner - AI + Me: how we built a GSC Bulk Export data pipeline
techseoconnect
PRO
0
340
Bash Introduction
62gerente
615
220k
Leading Effective Engineering Teams in the AI Era
addyosmani
9
2.2k
How to Ace a Technical Interview
jacobian
281
24k
SEO in 2025: How to Prepare for the Future of Search
ipullrank
3
3.7k
AI Search: Implications for SEO and How to Move Forward - #ShenzhenSEOConference
aleyda
1
1.3k
Transcript
The backbone of modern computer vision Intro to ConvNets
2
3 =
4
Convolutional Network
6 ⊙ = Σ input output kernel
7 input output ⊙ = kernel Σ
8 input output = kernel Σ ⊙
9 input output ⊙ = kernel Σ
10 kernel input output
11
12 Optimization Label: Bird ConvNet Loss Function Prediction: Cat
13 Optimization ConvNet Prediction: Bird Loss Function Label: Bird
14 Non-linear function from: wikipedia.org Sigmoid Function
15 Pooling operation from: computersciencewiki.org
16
17 Conv layer Non-linear function Convolution & Non-linear function &
Pooling Pooling Conv layer Non-linear function Pooling Conv layer Non-linear function
18 AlexNet (2012)
Thanks!