Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
Knowns and unknowns
Search
Xyggy
February 21, 2019
Technology
460
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Knowns and unknowns
Xyggy
February 21, 2019
More Decks by Xyggy
See All by Xyggy
Add and remove images from query
xyggy
0
1k
More like this or these
xyggy
0
960
More of these, less of the others
xyggy
0
920
Taking photos is free
xyggy
0
500
Realtime AI is Not a Myth
xyggy
0
1.7k
Litmus test
xyggy
0
880
3 minute Thingy
xyggy
0
170
pop-your-filter-bubble.pdf
xyggy
0
330
Other Decks in Technology
See All in Technology
12 個 Tool と、 4,096 Token
hlum
0
110
カンファレンスに参加した後の浮遊感とセルフケア
pauli
0
320
V8のArray.prototype.flatを最大約20倍速くするまでと、巨大OSSへの大規模コミットの道のり
riyaamemiya
0
170
freeeらしさをAIとともに作る / Creating the freee Experience with AI
ymrl
0
220
夫婦で子育てするための育児標準化
codmoninc
PRO
0
130
分析の民主化を支えるメタデータ整備の実践
kakehashi
PRO
4
1.2k
ビジネスを止めない技術的負債の返済のための戦略とその手法 - 技術的負債と向き合う / Complexity and Simplicity
soudai
PRO
3
680
予測不能な実行エージェントを安全にサクッと試せるサンドボックス環境の話
sansantech
PRO
1
140
Claude Code本は、どのように執筆チームで書かれたか
oikon48
1
360
宣言型部分更新は何を解決しどこへ向かうのか
shuta13
0
300
契約書画像からの情報抽出に特化した視覚接地モデルを育てる話
sansantech
PRO
1
160
More Freedom on the Same Shared GPU Cluster: A Small Team’s Experience with vCluster
nttcom
0
150
Featured
See All Featured
A brief & incomplete history of UX Design for the World Wide Web: 1989–2019
jct
2
530
Unsuck your backbone
ammeep
672
58k
コードの90%をAIが書く世界で何が待っているのか / What awaits us in a world where 90% of the code is written by AI
rkaga
63
46k
Raft: Consensus for Rubyists
vanstee
142
7.7k
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
37
6.6k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
12
1.3k
A Guide to Academic Writing Using Generative AI - A Workshop
ks91
PRO
1
510
Principles of Awesome APIs and How to Build Them.
keavy
128
18k
brightonSEO & MeasureFest 2025 - Winning Strategies for Black Friday CRO & PPC - Christian Goodrich
cargoodrich
3
860
Mozcon NYC 2025: Stop Losing SEO Traffic
samtorres
1
570
Practical Orchestrator
shlominoach
192
12k
How Software Deployment tools have changed in the past 20 years
geshan
2
35k
Transcript
1 Knowns and unknowns Query images Result images Dataset: wikiart
images - https://www.wikiart.org/. No image pre-processing performed. No textual data used. Feature vectors generated automatically with deep learning. www.xyggy.com © 2019
2 Known image An image is defined as known if
it has been added to Thingy with a unique id. In conventional machine learning, this image would be part of the “seen” data employed for building trained models. www.xyggy.com © 2019
3 Unknown image An image is defined as unknown if
it has not been added to Thingy. In conventional machine learning, this image would be “unseen” data for obtaining a prediction of. www.xyggy.com © 2019
4 Known and unknown images A query can contain both
known and unknown images. A data item is represented by a feature vector and is either known or unknown to Thingy but both can be used in a query. www.xyggy.com © 2019
5 Thingy www.xyggy.com © 2019