Serverless Machine Learning on Amazon Web Services clda.co/awsroma 10/15/2016 AWS @ Rome Applicazioni di Intelligenza Ar:ficiale con AWS Lambda
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Serverless Machine Learning on Amazon Web Services
clda.co/aws-‐roma10/15/2016 AWS @ Rome
Applicazioni di Intelligenza Ar:ficiale con AWS Lambda
@alex_casalboni
clda.co/aws-‐roma AWS @ Rome
Web Developer (6+ years)
Sr. SoFware Engineer @ Cloud Academy
Master in Computer Science
About me
What is Machine Learning?
Back to 1959 (Arthur Samuel)
How computers learn from Data
How to solve decision problems
AWS @ Romeclda.co/aws-‐roma
Machine Learning pipeline
Training Predic3on
batch real-‐Cme
Feature extrac3on
batch
data informa:on
features ML models
AWS @ Romeclda.co/aws-‐roma
?
Machine Learning taxonomy
Supervised Learning
Unsupervised Learning
AWS @ Romeclda.co/aws-‐roma
?Machine Learning taxonomy
classifica9on
regression 170cm
Supervised Learning
Unsupervised Learning
AWS @ Romeclda.co/aws-‐roma
Machine Learning taxonomy
Supervised Learning
Unsupervised Learning
AWS @ Romeclda.co/aws-‐roma
Machine Learning taxonomy
clustering
rule extrac9on
group A group B
A, B C
Supervised Learning
Unsupervised Learning
AWS @ Romeclda.co/aws-‐roma
What problems can ML solve for you?
Supervised Learning
Unsupervised Learning
classifica'on
regression
clustering
rule extrac'on
?
170cm
gro gro
A, B C
AWS @ Romeclda.co/aws-‐roma
What problems can ML solve for you?
Supervised Learning
Unsupervised Learning
classifica'on
regression
clustering
rule extrac'on
?fraud detec:on
170cm
gro gro
A, B C
price of a stock over :me
purchase likelihood
user segmenta:on
AWS @ Romeclda.co/aws-‐roma
LearningDataMachine
Cloud
Big
Science
Information
Internet
Statistics
Technology
Python Future
Mining Social
Deep
IOT
AlgorithmsManagement
Storage Petabytes
Parallel
Network
Privacy
MillionNoSQL
PaaS
SQL
Database
Exabytes
Billion
Dataset
Hadoop
R
AWS @ Romeclda.co/aws-‐roma
Generated data started growing ~10 years ago…
“90% of the data in the world today has been created in the last two years alone” -‐ IBM
“300+ hours worth of video content is being uploaded to the site every minute” -‐ Youtube
AWS @ Romeclda.co/aws-‐roma
Big data challenges
Manual explora:on is not an op:on
Data-‐driven decisions are a must
Distributed/parallel compu:ng
The curse of dimensionality
AWS @ Romeclda.co/aws-‐roma
Why is deploying ML models a challenge?
AWS @ Romeclda.co/aws-‐roma
+
+
Data Scien:st
Data
Time
Why is deploying ML models a challenge?
AWS @ Romeclda.co/aws-‐roma
+
+
Data Scien:st
Data
Time
ML Model
Data Visualisa:on
Prototype
+
+
Why is deploying ML models a challenge?
AWS @ Romeclda.co/aws-‐roma
Produc:on Code
+
+
Data Scien:st
Data
Time
ML Model
Data Visualisa:on
Prototype
+
+
Why is deploying ML models a challenge?
AWS @ Romeclda.co/aws-‐roma
+
+
Data Scien:st
Data
Time
ML Model
Data Visualisa:on
Prototype
+
+
Web Developer
DevOps
A lot of Time
+
+
Why is deploying ML models a challenge?
1. Prototyping != Produc:on-‐ready
2. We need Elas:city
4. Mul:-‐model architectures
3. Too many nice-‐to-‐have features
5. Avoid lack of ownership
AWS @ Romeclda.co/aws-‐roma
Machine Learning as a Service (MLaaS)
AmazonMachine Learning
AzureMachine Learning
GooglePredicCon API
IMBWatson AnalyCcs
BigML
AWS @ Romeclda.co/aws-‐roma
cloudacademy.com/blog/machine-‐learning
Amazon Machine Learning
AmazonML
One of the first MLaaS solu:ons (Apr 2015)
It’s great for classifica:on and regression problems
Only linear models (linear & logis:c regression + SGD)
No support for advanced scenarios yet
AWS @ Romeclda.co/aws-‐roma
AmazonML @ Cloud Academy
clda.co/7-‐day-‐free(no credit card required!)
AWS @ Romeclda.co/aws-‐roma
Serverless compuCng to the rescue!
Transparent scalability, elas:city and availability
Developer-‐friendly maintenance (versioning + aliases)
AWS Lambda
Event-‐driven approach & never pay for idle
Microservices culture
AWS @ Romeclda.co/aws-‐roma
Quick Example
clda.co/ML-‐Lambda
AWS @ Romeclda.co/aws-‐roma
AWS @ Rome
Serverless ML @ Cloud Academy
Mul:-‐model architecture
RESTful interface for each ML model
1 Lambda Func:on for each ML model
S3 + RDS for storage
Periodic training (offline)
Real-‐world Example
clda.co/aws-‐roma
AWS @ Romeclda.co/aws-‐roma
AWS Lambda
No real-‐:me models (only pseudo real-‐:me)
Deployment package management: size limit and OS libraries
Not suitable for model training yet (5 min max execu:on :me)
Cold start :me is long and hard to avoid
Unit/integra:on tests help, but not enough
LimitaCons of Serverless ML
Related Documents
