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
0
2.2k
Intro to ConvNets: The backbone of modern computer vision
Tryolabs
April 10, 2019
Tweet
Share
More Decks by Tryolabs
See All by Tryolabs
An Introduction to Machine Learning and How to Teach Machines to See
tryolabs
0
2.2k
Tryolabs Workshop: Object Detection with Deep Learning
tryolabs
0
500
PyImageConf Workshop: Object Detection with Deep Learning
tryolabs
0
280
Introduction to Object Detection - PyCon APAC 2018
tryolabs
0
2.6k
Building an Object Detection toolkit with TensorFlow (ODSC West 2017)
tryolabs
1
2.5k
Building an Object Detection toolkit with TensorFlow (PyLadies Meetup)
tryolabs
1
410
Building an Object Detection toolkit with TensorFlow (ODSC Europe 2017)
tryolabs
1
220
Tryolabs Working Trip NYC 2017 in pictures.
tryolabs
0
1.6k
Machine Learning 101 - Tryolabs
tryolabs
0
220
Other Decks in Technology
See All in Technology
S3はフラットである –AWS公式SDKにも存在した、 署名付きURLにおけるパストラバーサル脆弱性– / JAWS DAYS 2026
flatt_security
0
1.8k
Claude Codeが爆速進化してプラグイン追従がつらいので半自動化した話 ver.2
rfdnxbro
0
530
PMとしての意思決定とAI活用状況について
lycorptech_jp
PRO
0
120
Evolution of Claude Code & How to use features
oikon48
1
600
AI時代の「本当の」ハイブリッドクラウド — エージェントが実現した、あの頃の夢
ebibibi
0
110
20260311 ビジネスSWG活動報告(デジタルアイデンティティ人材育成推進WG Ph2 活動報告会)
oidfj
0
300
[JAWS DAYS 2026]私の AWS DevOps Agent 推しポイント
furuton
0
150
進化するBits AI SREと私と組織
nulabinc
PRO
0
140
今のWordPress の制作手法ってなにがあんねん?(改) / What’s the Deal with WordPress Development These Days?
tbshiki
0
440
CyberAgentの生成AI戦略 〜変わるものと変わらないもの〜
katayan
0
140
猫でもわかるKiro CLI(AI 駆動開発への道編)
kentapapa
0
180
クラウド × シリコンの Mashup - AWS チップ開発で広がる AI 基盤の選択肢
htokoyo
2
240
Featured
See All Featured
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
141
35k
Site-Speed That Sticks
csswizardry
13
1.1k
Claude Code どこまでも/ Claude Code Everywhere
nwiizo
64
53k
Joys of Absence: A Defence of Solitary Play
codingconduct
1
310
Ruling the World: When Life Gets Gamed
codingconduct
0
170
Thoughts on Productivity
jonyablonski
75
5.1k
AI in Enterprises - Java and Open Source to the Rescue
ivargrimstad
0
1.2k
Tell your own story through comics
letsgokoyo
1
840
Fashionably flexible responsive web design (full day workshop)
malarkey
408
66k
How to audit for AI Accessibility on your Front & Back End
davetheseo
0
210
Bridging the Design Gap: How Collaborative Modelling removes blockers to flow between stakeholders and teams @FastFlow conf
baasie
0
480
The Art of Delivering Value - GDevCon NA Keynote
reverentgeek
16
1.9k
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!