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
More of these, less of the others
Search
Xyggy
February 21, 2019
Technology
0
890
More of these, less of the others
Xyggy
February 21, 2019
Tweet
Share
More Decks by Xyggy
See All by Xyggy
Add and remove images from query
xyggy
0
940
More like this or these
xyggy
0
910
Taking photos is free
xyggy
0
460
Knowns and unknowns
xyggy
0
410
Realtime AI is Not a Myth
xyggy
0
1.7k
Litmus test
xyggy
0
850
3 minute Thingy
xyggy
0
130
pop-your-filter-bubble.pdf
xyggy
0
260
Other Decks in Technology
See All in Technology
JSX - 歴史を振り返り、⾯⽩がって、エモくなろう
pal4de
3
880
自分を理解するAI時代の準備 〜マイプロフィールMCPの実装〜
edo_m18
0
110
原則から考える保守しやすいComposable関数設計
moriatsushi
3
430
Perk アプリの技術選定とリリースから1年弱経ってのふりかえり
stomk
0
100
New Cache Hierarchy for Container Images and OCI Artifacts in Kubernetes Clusters using Containerd / KubeCon + CloudNativeCon Japan
pfn
PRO
0
160
kubellが挑むBPaaSにおける、人とAIエージェントによるサービス開発の最前線と技術展望
kubell_hr
1
310
データ戦略部門 紹介資料
sansan33
PRO
1
3.2k
"SaaS is Dead" は本当か!? 生成AI時代の医療 Vertical SaaS のリアル
kakehashi
PRO
3
210
Contract One Engineering Unit 紹介資料
sansan33
PRO
0
6.4k
開発効率と信頼性を両立する Ubieのプラットフォームエンジニアリング
teru0x1
0
140
QAはソフトウェアエンジニアリングを学んで実践するのが大事なの
ymty
1
400
IAMのマニアックな話 2025を執筆して、 見えてきたAWSアカウント管理の現在
nrinetcom
PRO
4
570
Featured
See All Featured
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
47
2.8k
Into the Great Unknown - MozCon
thekraken
39
1.8k
Making Projects Easy
brettharned
116
6.2k
Writing Fast Ruby
sferik
628
61k
Adopting Sorbet at Scale
ufuk
77
9.4k
Music & Morning Musume
bryan
46
6.6k
How STYLIGHT went responsive
nonsquared
100
5.6k
Docker and Python
trallard
44
3.4k
Typedesign – Prime Four
hannesfritz
42
2.7k
Embracing the Ebb and Flow
colly
86
4.7k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
233
17k
How to train your dragon (web standard)
notwaldorf
92
6.1k
Transcript
1 More of these, less of the others 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 More like positives, less like negatives www.xyggy.com © 2019
3 www.xyggy.com © 2019
4 More like negatives, less like positives www.xyggy.com © 2019
5 www.xyggy.com © 2019
6 What’s going on? Think “yin and yang”. The positive
has a little of the negative. The negative has a little of the positive. www.xyggy.com © 2019
7 yin and yang Discover more like the positive images
and less like the negative ones. Discover more like the negative images and less like the positive ones. www.xyggy.com © 2019
8 Thingy www.xyggy.com © 2019