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
Taking ML to production - a journey
Search
Arnon Rotem-Gal-Oz
July 06, 2021
Technology
0
110
Taking ML to production - a journey
Go over some of the complexities of turning a machine learning solution to one used in production
Arnon Rotem-Gal-Oz
July 06, 2021
Tweet
Share
More Decks by Arnon Rotem-Gal-Oz
See All by Arnon Rotem-Gal-Oz
Brownfield Architecture transformations
arnonrgo
0
86
Software architecture 101
arnonrgo
0
1.3k
Apache Spark - Overview
arnonrgo
0
38
Topics in Distributed Systems
arnonrgo
0
24
Docker & Kubernetes
arnonrgo
0
20
Data Security @ the personal level
arnonrgo
0
24
Microservices it's deja vu all over again
arnonrgo
0
22
Big Data in the Cloud - Welcome to cost oriented design
arnonrgo
0
19
Big Data Overview
arnonrgo
0
10
Other Decks in Technology
See All in Technology
AIエージェントについてまとめてみた
pharma_x_tech
10
6.9k
extensionとschema
yahonda
1
100
サーバーレスで楽しよう!お気軽に始められる3つのポイント / Have fun with Serverless!
_kensh
2
230
ソフトウェアアーキテクトのための意思決定術: Software Architecture and Decision-Making
snoozer05
PRO
17
4k
Microsoft Ignite 2024 最新情報!Microsoft 365 Agents SDK 概要 / Microsoft Ignite 2024 latest news Microsoft 365 Agents SDK overview
karamem0
0
190
RevOpsへ至る道 データ活用による事業革新への挑戦 / path-to-revops
pei0804
3
800
AWSエンジニアに捧ぐLangChainの歩き方
tsukuboshi
0
220
アクセシブルなマークアップの上に成り立つユーザーファーストなドロップダウンメニューの実装 / 20250127_cloudsign_User1st_FE
bengo4com
2
1.2k
HCP TerraformとAzure:イオンスマートテクノロジーのインフラ革新 / HCP Terraform and Azure AEON Smart Technology's Infrastructure Innovation
aeonpeople
3
980
CNAPPから考えるAWSガバナンスの実践と最適化
nrinetcom
PRO
1
330
[2024年10月版] Notebook 2.0のご紹介 / Notebook2.0
databricksjapan
0
1.6k
“自分”を大切に、フラットに。キャリアチェンジしてからの一年 三ヶ月で見えたもの。
maimyyym
0
300
Featured
See All Featured
Embracing the Ebb and Flow
colly
84
4.5k
What’s in a name? Adding method to the madness
productmarketing
PRO
22
3.3k
We Have a Design System, Now What?
morganepeng
51
7.4k
Improving Core Web Vitals using Speculation Rules API
sergeychernyshev
6
220
Unsuck your backbone
ammeep
669
57k
Learning to Love Humans: Emotional Interface Design
aarron
274
40k
Music & Morning Musume
bryan
46
6.3k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
27
1.5k
Templates, Plugins, & Blocks: Oh My! Creating the theme that thinks of everything
marktimemedia
28
2.2k
Rails Girls Zürich Keynote
gr2m
94
13k
It's Worth the Effort
3n
184
28k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
20
2.4k
Transcript
Taking ML to production - A journey Arnon Rotem-Gal-Oz
Mental model of the probelm Admission Intubation Alert >6 hours
Challlenge 1 defining the problem
A Perfect Representation of the Machine Learning Cycle from start
to end | Image Source: MLOps (Published under Creative Commons Attribution 4.0 International Public License and used with attribution (“INNOQ”))
None
Challenge 2 – how we measure
Challenge 3 Data quality
None
Challenge 5 different types of data Model(s) text time series
categorical
Challenge 6 labeling Admission Intubation
Challenge 7 dealing with imballance
Challenge 8 Model experimentation cycle
Modeling
Challenge 9 – Overfit
None
Moving to production…
Challenge 10 – model degredation in production Theory Reality
Challenge11 – Is it really generalized?
Challenge 12 model validation and verification
The road to production…