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
Knowns and unknowns
Search
Xyggy
February 21, 2019
Technology
0
430
Knowns and unknowns
Xyggy
February 21, 2019
Tweet
Share
More Decks by Xyggy
See All by Xyggy
Add and remove images from query
xyggy
0
960
More like this or these
xyggy
0
940
More of these, less of the others
xyggy
0
910
Taking photos is free
xyggy
0
480
Realtime AI is Not a Myth
xyggy
0
1.7k
Litmus test
xyggy
0
870
3 minute Thingy
xyggy
0
160
pop-your-filter-bubble.pdf
xyggy
0
300
Other Decks in Technology
See All in Technology
Oracle Cloud Infrastructure:2026年2月度サービス・アップデート
oracle4engineer
PRO
0
170
【SLO】"多様な期待値" と向き合ってみた
z63d
2
290
ソフトウェアアーキテクトのための意思決定術: Create Decision Readiness—The Real Skill Behind Architectural Decision
snoozer05
PRO
27
8.3k
Oracle Base Database Service 技術詳細
oracle4engineer
PRO
15
95k
EMからVPoEを経てCTOへ:マネジメントキャリアパスにおける葛藤と成長
kakehashi
PRO
5
360
JAWS DAYS 2026 CDP道場 事前説明会 / JAWS DAYS 2026 CDP Dojo briefing document
naospon
0
110
クラウド時代における一時権限取得
krrrr38
1
150
Claude Cowork Plugins を読む - Skills駆動型業務エージェント設計の実像と構造
knishioka
0
230
primeNumber DATA MANAGEMENT CAMP #2:
masatoshi0205
1
660
LLM活用の壁を超える:リクルートR&Dの戦略と打ち手
recruitengineers
PRO
1
200
社内でAWS BuilderCards体験会を立ち上げ、得られた気づき / 20260225 Masaki Okuda
shift_evolve
PRO
1
150
LINE Messengerの次世代ストレージ選定
lycorptech_jp
PRO
17
6.9k
Featured
See All Featured
Avoiding the “Bad Training, Faster” Trap in the Age of AI
tmiket
0
96
Ethics towards AI in product and experience design
skipperchong
2
210
Prompt Engineering for Job Search
mfonobong
0
180
Documentation Writing (for coders)
carmenintech
77
5.3k
brightonSEO & MeasureFest 2025 - Christian Goodrich - Winning strategies for Black Friday CRO & PPC
cargoodrich
3
110
Connecting the Dots Between Site Speed, User Experience & Your Business [WebExpo 2025]
tammyeverts
11
850
The Director’s Chair: Orchestrating AI for Truly Effective Learning
tmiket
1
110
Principles of Awesome APIs and How to Build Them.
keavy
128
17k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
231
22k
Measuring Dark Social's Impact On Conversion and Attribution
stephenakadiri
1
140
What’s in a name? Adding method to the madness
productmarketing
PRO
24
4k
Un-Boring Meetings
codingconduct
0
220
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