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
1.8k
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
1.7k
Tryolabs Workshop: Object Detection with Deep Learning
tryolabs
0
340
PyImageConf Workshop: Object Detection with Deep Learning
tryolabs
0
240
Introduction to Object Detection - PyCon APAC 2018
tryolabs
0
2.2k
Building an Object Detection toolkit with TensorFlow (ODSC West 2017)
tryolabs
1
2k
Building an Object Detection toolkit with TensorFlow (PyLadies Meetup)
tryolabs
1
400
Building an Object Detection toolkit with TensorFlow (ODSC Europe 2017)
tryolabs
1
200
Tryolabs Working Trip NYC 2017 in pictures.
tryolabs
0
1.3k
Machine Learning 101 - Tryolabs
tryolabs
0
190
Other Decks in Technology
See All in Technology
Oracle Database 23ai 新機能#4 Rolling Maintenance
oracle4engineer
PRO
0
110
AWSへのNIST SP800-171管理策 導入に向けての整備/20240930 Mitsutoshi Matsuo
shift_evolve
0
180
Oracle GoldenGate 23ai 導入Tips
oracle4engineer
PRO
1
220
YAPC::Hakodateの映像記録を支える技術
godan
4
180
Rubyはなぜ「たのしい」のか? / Why is Ruby a programmers' best friend? #tqrk15
expajp
4
1.8k
令和最新版 Perlコーディングガイド
anatofuz
3
2.5k
映像・音声伝送システム
jtes
0
200
C# 13 / .NET 9 の新機能 (RC 1 時点)
nenonaninu
1
1.2k
低コストで実現する社内文書RAG機能を搭載したAIチャットボット開発
takapy
3
650
AWS Lambdaで実現するスケーラブルで低コストなWebサービス構築/YAPC::Hakodate2024
fujiwara3
6
1.7k
分析者起点の企画を成功させた連携面の工夫
lycorptech_jp
PRO
1
230
【shownet.conf_】ShowNet伝送改めShowNet APN 2024
shownet
PRO
0
380
Featured
See All Featured
How to train your dragon (web standard)
notwaldorf
87
5.6k
Infographics Made Easy
chrislema
239
18k
Creatively Recalculating Your Daily Design Routine
revolveconf
217
12k
What's in a price? How to price your products and services
michaelherold
243
11k
The Brand Is Dead. Long Live the Brand.
mthomps
53
38k
Done Done
chrislema
181
16k
Designing for Performance
lara
604
68k
A Philosophy of Restraint
colly
202
16k
Six Lessons from altMBA
skipperchong
26
3.4k
The Cost Of JavaScript in 2023
addyosmani
43
5.8k
Principles of Awesome APIs and How to Build Them.
keavy
126
17k
Bootstrapping a Software Product
garrettdimon
PRO
304
110k
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!