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
Predicting the future in 10 minutes or less - a...
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Vlad Iliescu
May 13, 2017
Programming
79
0
Share
Predicting the future in 10 minutes or less - an introduction to Azure Machine Learning
Vlad Iliescu
May 13, 2017
More Decks by Vlad Iliescu
See All by Vlad Iliescu
Poor Man’s BingChat – Building an Internet-connected Search Assistant from scratch*
vladiliescu
0
820
Training Better Models Using Automated Machine Learning
vladiliescu
0
75
Machine Learning in Azure: Service versus Studio
vladiliescu
1
2.2k
Getting Started with Machine Learning Using Azure Machine Learning Studio and Kaggle Competitions
vladiliescu
1
1.9k
Boy meets Girl: A Machine Learning Deployment Story
vladiliescu
0
2.2k
Mind Reading - Understanding Recommender Systems
vladiliescu
0
95
Privacy-First Development
vladiliescu
0
100
TypeScript vs CoffeeScript
vladiliescu
0
2.1k
Micro Web Frameworks in .NET
vladiliescu
2
330
Other Decks in Programming
See All in Programming
条件判定に名前、つけてますか? #phperkaigi #c
77web
2
950
ローカルで稼働するAI エージェントを超えて / beyond-local-ai-agents
gawa
1
240
KagglerがMixSeekを触ってみた
morim
0
370
車輪の再発明をしよう!PHP で実装して学ぶ、Web サーバーの仕組みと HTTP の正体
h1r0
3
500
年間50登壇、単著出版、雑誌寄稿、Podcast出演、YouTube、CM、カンファレンス主催……全部やってみたので面白さ等を比較してみよう / I’ve tried them all, so let’s compare how interesting they are.
nrslib
4
700
「速くなった気がする」をデータで疑う
senleaf24
0
140
我々はなぜ「層」を分けるのか〜「関心の分離」と「抽象化」で手に入れる変更に強いシンプルな設計〜 #phperkaigi / PHPerKaigi 2026
shogogg
2
790
「接続」—パフォーマンスチューニングの最後の一手 〜点と点を結ぶ、その一瞬のために〜
kentaroutakeda
5
2.4k
Kubernetes上でAgentを動かすための最新動向と押さえるべき概念まとめ
sotamaki0421
2
390
PHP 7.4でもOpenTelemetryゼロコード計装がしたい! / PHPerKaigi 2026
arthur1
1
490
PHPで TLSのプロトコルを実装してみる
higaki_program
0
730
Codex CLIのSubagentsによる並列API実装 / Parallel API Implementation with Codex CLI Subagents
takatty
2
830
Featured
See All Featured
Designing for humans not robots
tammielis
254
26k
Sam Torres - BigQuery for SEOs
techseoconnect
PRO
0
230
SEOcharity - Dark patterns in SEO and UX: How to avoid them and build a more ethical web
sarafernandez
0
160
The untapped power of vector embeddings
frankvandijk
2
1.7k
Unsuck your backbone
ammeep
672
58k
Typedesign – Prime Four
hannesfritz
42
3k
GraphQLとの向き合い方2022年版
quramy
50
14k
SEO for Brand Visibility & Recognition
aleyda
0
4.4k
ピンチをチャンスに:未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
128
55k
The Language of Interfaces
destraynor
162
26k
Digital Ethics as a Driver of Design Innovation
axbom
PRO
1
250
How to build an LLM SEO readiness audit: a practical framework
nmsamuel
1
700
Transcript
Predicting the Future in 10 Minutes or Less
...a 45-minute presentation by @vladiliescu
What do you mean, “Predict the future”?
Predict the future
Predict the future grades of a student
Predict the future grades of a student at math
Predict the future grades of a student at math using...
a) Divination
b) Statistics
c) Machine Learning
c) Machine Learning A way to write programs that we
don’t exactly know how to write.
c) Machine Learning A way to write programs that we
don’t exactly know how to write.
Predict the future grades of a student at math using
machine learning…
Apache Spark MLlib Microsoft Azure ML Studio Google Prediction API
Google TensorFlow Amazon Machine Learning Samsung Veles
Microsoft Azure ML Studio
What have we picked so far? ✔ A well-defined problem
✔ An approach for predicting the future ✔ A machine learning framework
What are we missing?
The Data
UCI Student Performance Data Set
https://archive.ics.uci.edu/ml/datasets/Student+Performance
G3 - final grade (numeric: from 0 to 20, output
target)
Ready?
Steady?
GO!
Open the Azure experiment here https://gallery.cortanaintelligence.com/Experiment/Predict-Student-Grades-at-Math (or take a look
at the following slides)
None
None
None
None
None
None
None
None
None
None
None
None
What have we done so far? (continued) ✔ Trained&deployed the
simplest model we could ✔ Consumed the web service using Excel ✔ Learned how to evaluate a trained model
Thanks for watching! Vlad Iliescu ↪vladiliescu.ro