http://www.sfbayacm.org/event/scalable-data-science-and-deep-learning-h2o H2O is fast scalable open-source machine learning and deep learning for Smarter Applications. Using in-memory compression techniques, H2O can handle billions of data rows in-memory — even on small compute clusters. The platform includes interfaces for R, Python, Scala, Java, JS and JSON, along with its interactive graphical Flow interface that make it easier for non-engineers to stitch together complete analytic workflows. H2O was built alongside (and on top of) both Hadoop and Spark clusters and is deployed within minutes. Sparkling Water combines the flexibility of Spark with the speed and accuracy of H2O's Machine Learning solution. In this talk, we explain H2O's scalable in-memory architecture and design principles and outline the implementation of distributed machine learning algorithms such as Elastic Net, Random Forest, Gradient Boosting and Deep Learning. We will present a broad range of use cases and live demos that include world-record deep learning models, anomaly detection tools and approaches for Kaggle data science competitions. We also demonstrate the applicability of H2O in enterprise environments for real-world customer production use cases. We will cover data ingest, feature engineering, model tuning, model validation and model selection; and how to take models into production. Live demos will be run on distributed systems. By the end of this presentation, you will know how to create your own machine learning models on your data using R, Python (iPython Notebooks) or Flow. Speaker Bio Arno is the Chief Architect of H2O, a distributed and scalable open-source machine learning platform. He is also the main author of H2O's Deep Learning. Before joining H2O, Arno was a founding Senior MTS at Skytree where he designed and implemented high-performance machine learning algorithms. He has over a decade of experience in HPC with C++/MPI and had access to the world’s largest supercomputers as a Staff Scientist at SLAC National Accelerator Laboratory where he participated in US DOE scientific computing initiatives and collaborated with CERN on next-generation particle accelerators. Arno holds a PhD and Masters summa cum laude in Physics from ETH Zurich, Switzerland. He has authored dozens of scientific papers and is a sought-after conference speaker. Arno was named “2014 Big Data All-Star” by Fortune Magazine. Twitter: @ArnoCandel. - Powered by the open source machine learning software H2O.ai. Contributors welcome at: https://github.com/h2oai - To view videos on H2O open source machine learning software, go to: https://www.youtube.com/user/0xdata

1. H2O.ai
Machine Intelligence
Scalable Data Science
and Deep Learning
with H2O
1
SF Bay ACM Chapter Meetup
eBay Whitman Campus, June 3 2015
Arno Candel, PhD
Chief Architect, H2O.ai

2. H2O.ai
Machine Intelligence
Who Am I?
Arno Candel
Chief Architect,
Physicist & Hacker at H2O.ai
PhD Physics, ETH Zurich 2005
10+ yrs Supercomputing (HPC)
6 yrs at SLAC (Stanford Lin. Accel.)
3.5 yrs Machine Learning
1.5 yrs at H2O.ai
Fortune Magazine
Big Data All Star 2014
Follow me @ArnoCandel 2

3. H2O.ai
Machine Intelligence
Outline
• Introduction
• H2O Deep Learning Architecture
• Live Demos:
Flow GUI - Airline Dataset
R - MNIST World Record + Anomaly Detection
Flow GUI - Higgs Boson Classification
Sparkling Water - Chicago Crime Prediction
Sparkling Water - Craigslist Jobs Word2Vec
iPython - CitiBike Demand Prediction
Scoring Engine - Million Songs Classification
• Outlook
3

4. H2O.ai
Machine Intelligence
In-Memory ML
Distributed
Open Source
APIs
4
Memory-Efficient Data Structures
Cutting-Edge Algorithms
Use all your Data (No Sampling)
Accuracy with Speed and Scale
Ownership of Methods - Apache V2
Easy to Deploy: Bare, Hadoop, Spark, etc.
Java, Scala, R, Python, JavaScript, JSON
NanoFast Scoring Engine (POJO)
H2O - Product Overview

5. H2O.ai
Machine Intelligence
25,000 commits / 3yrs
H2O World Conference 2014
Team Work @ H2O.ai
5
Join H2O World 2015!

6. H2O.ai
Machine Intelligence
103 634 2789
463 2,887 13,237
Companies
Users
Mar 2014 July 2014 Mar 2015
Active Users
150+
6
Strong Community & Growth
5/25/15 @kdnuggets t.co/4xSgleSIdY

7. H2O.ai
Machine Intelligence
7
HDFS
S3
SQL
NoSQL
Classification
Regression
Feature
Engineering
Distributed In-Memory
Map Reduce/Fork Join
Columnar Compression
GLM, Deep Learning
K-Means, PCA, NB,
Cox
Random Forest / GBM
Ensembles
Fast Modeling Engine
Streaming
Nano Fast Java Scoring Engines
(POJO code generation)
Matrix
Factorization Clustering
Munging
Unsupervised
Supervised
Accuracy with Speed and Scale
Most code is written
in-house from scratch

8. H2O.ai
Machine Intelligence
8
Ad Optimization (200% CPA Lift with H2O)
P2B Model Factory (60k models,
15x faster with H2O than before)
Fraud Detection (11% higher accuracy with
H2O Deep Learning - saves millions)
…and many large insurance and financial
services companies!
Real-time marketing (H2O is 10x faster than
anything else)
Actual Customer Use Cases

9. H2O.ai
Machine Intelligence
9
h2o.ai/download & Run!

10. H2O.ai
Machine Intelligence
10
Airline Data: Predict Delayed Departure
Predict dep. delay Y/N
116M rows
31 colums
12 GB CSV
4 GB compressed
20 years of domestic
airline flight data

11. H2O.ai
Machine Intelligence
11
Results in Seconds on Big Data
Logistic Regression: ~20s
elastic net, alpha=0.5, lambda=1.379e-4 (auto)
Deep Learning: ~70s
4 hidden ReLU layers of 20 neurons, 2 epochs
8-node EC2 cluster: 64 virtual cores, 1GbE
Year, Month, Sched.
Dep. Time have
non-linear impact
Chicago, Atlanta,
Dallas:
often delayed
All cores maxed out
+9% AUC
+--+++

12. H2O.ai
Machine Intelligence
Multi-layer feed-forward Neural Network
Trained with back-propagation (SGD, ADADELTA)
+ distributed processing for big data
(fine-grain in-memory MapReduce on distributed data)
+ multi-threaded speedup
(async fork/join worker threads operate at FORTRAN speeds)
+ smart algorithms for fast & accurate results
(automatic standardization, one-hot encoding of categoricals, missing value imputation, weight &
bias initialization, adaptive learning rate, momentum, dropout/l1/L2 regularization, grid search,
N-fold cross-validation, checkpointing, load balancing, auto-tuning, model averaging, etc.)
= powerful tool for (un)supervised machine
learning on real-world data
12
H2O Deep Learning
all 320 cores maxed out

13. H2O.ai
Machine Intelligence
threads: async
13
H2O Deep Learning Architecture
K-V
K-V
HTTPD
HTTPD
nodes/JVMs: sync
communication
w
w w
w w w w
w1
w3 w2
w4
w2+w4
w1+w3
w* = (w1+w2+w3+w4)/4
map:
each node trains a copy of
the weights and biases with
(some* or all of) its local
data with asynchronous F/J
threads
initial model: weights and biases w
updated model: w*
H2O in-memory non-
blocking hash map:
K-V store
reduce:
model averaging: average weights
and biases from all nodes,
speedup is at least #nodes/
log(#rows)
http://arxiv.org/abs/1209.4129
Keep iterating over the data (“epochs”), score at user-given times
Query & display the
model via JSON, WWW
2
2 4
31
1
1
1
4
3 2
1 2
1
i
*auto-tuned (default) or user-
specified number of rows per
MapReduce iteration
Main Loop:

14. H2O.ai
Machine Intelligence
14
H2O Deep Learning beats MNIST
MNIST: Handwritten digits: 28^2=784 gray-scale pixel values
full run: 10 hours on 10-node cluster
2 hours on desktop gets to 0.9% test set error
Just supervised training
on original 60k/10k dataset:
No data augmentation
No distortions
No convolutions
No pre-training
No ensemble
0.83% test set error:
current world record
1-liner: call h2o.deeplearning() in R

15. H2O.ai
Machine Intelligence
15
Unsupervised Anomaly Detection
The good The bad The ugly
Try it yourself!
Auto-Encoder learns
“Compressed Identity”

16. H2O.ai
Machine Intelligence
16
Images courtesy CERN / LHC
Higgs
vs
Background
Large Hadron Collider: Largest experiment of mankind!
$13+ billion, 16.8 miles long, 120 MegaWatts, -456F, 1PB/day, etc.
Higgs boson discovery (July ’12) led to 2013 Nobel prize!
Higgs Boson - Classification Problem

17. H2O.ai
Machine Intelligence
17
UCI Higgs Dataset: 11M rows, 29 cols
C2-C22: 21 low-level features
(detector data)
7 high-level features
(physics formulae)
Assume we don’t know Physics…

18. H2O.ai
Machine Intelligence
18
? ? ?
Former CERN baseline for AUC: 0.733 and 0.816
H2O Algorithm low-level H2O AUC all features H2O AUC
Generalized Linear Model 0.596 0.684
Random Forest 0.764 0.840
Gradient Boosted Trees 0.753 0.839
Neural Net 1 hidden layer 0.760 0.830
H2O Deep Learning ?
add
derived
features
Deep Learning for Higgs Detection?
Q: Can Deep Learning learn Physics for us?

19. H2O.ai
Machine Intelligence
19
EC2 Demo Cluster: 8 nodes, 64 cores
H2O Deep Learning:
Expect good cluster
utilization :)

20. H2O.ai
Machine Intelligence
20
Deep DL model on
low-level features
only
train 10M rows
valid 500k rows
test 500k rows
H2O Deep Learning Higgs Demo
H2O: same results as Nature paper
Deep Learning just learned Particle Physics!
8 EC2 nodes:
AUC = 0.86 after 100 mins
AUC = 0.87+ overnight

21. H2O.ai
Machine Intelligence
21
http://www.slideshare.net/0xdata/crime-deeplearningkey
http://www.datanami.com/2015/05/07/what-police-can-learn-from-deep-learning/
H2O Deep Learning in the News
Alex, Michal,
et al.

22. H2O.ai
Machine Intelligence
22
Weather + Census + Crime Data

23. H2O.ai
Machine Intelligence 23
Spark + H2O = Sparkling Water

24. H2O.ai
Machine Intelligence
24
Sparkling Water Demo
Instructions at h2o.ai/download

25. H2O.ai
Machine Intelligence
25
Parse & Munge with H2O, Convert to RDD
H2O Parser: Robust & Fast
Simple Column Selection

26. H2O.ai
Machine Intelligence
26
Parse & Munge with H2O, Convert to RDD
Munging: Date Manipulations
Conversion to DataFrame

27. H2O.ai
Machine Intelligence
27
Join RDDs with SQL, Convert to H2O
Spark SQL Query Execution
Convert back to H2OFrame
Split into Train 80% / Test 20%

28. H2O.ai
Machine Intelligence
28
Build H2O Deep Learning Model
Train a H2O Deep Learning
Model on Data obtained by
Spark SQL Query
Predict whether Arrest will be
made with AUC of 0.90+

29. H2O.ai
Machine Intelligence
29
Visualize Results with Flow
Using Flow to interactively plot
Arrest Rate (blue)
vs
Relative Occurrence (red)
per crime type.

30. H2O.ai
Machine Intelligence
30
Word2Vec Demo: CraigsList Jobs
Task: Predict the job category from the Ad Title
Alex et al.

31. H2O.ai
Machine Intelligence
31
Load Data into Spark (ling Water)
14k jobs, 700kB
6 job classes

32. H2O.ai
Machine Intelligence
32
Data Cleaning

33. H2O.ai
Machine Intelligence
33
Spark Word2Vec Results into H2OFrame
Compute average Word2Vec vector
(length 100) for each job title
Convert Spark Word2Vec
Frame to H2OFrame

34. H2O.ai
Machine Intelligence
34
Run H2O GBM on Word2Vec Data
In Flow, split data 75%/25%, and train GBM classifier for 6-class problem
80% accuracy in 9 seconds!
(priors: ~16%)

35. H2O.ai
Machine Intelligence
35
Predict Rental Bike Demand in NYC
Cliff et al.

36. H2O.ai
Machine Intelligence
iPython
Notebook Demo
36
Group-By Aggregation

37. H2O.ai
Machine Intelligence
iPython
Notebook Demo
37
Model Building And Scoring
91% AUC baseline

38. H2O.ai
Machine Intelligence
38
Joining Bikes-Per-Day with Weather

39. H2O.ai
Machine Intelligence
39
Improved Models with Weather Data
93% AUC after joining
bike and weather data

40. H2O.ai
Machine Intelligence
40
Example: First GBM tree
Fast and easy path to Production (batch or real-time)!
POJO Scoring Engine
Standalone Java scoring code is auto-generated!
Note:
no heap allocation,
pure decision-making

41. H2O.ai
Machine Intelligence
More Info in H2O Booklets
https://leanpub.com/u/h2oai
http://learn.h2o.ai
41

42. H2O.ai
Machine Intelligence
42
Kaggle - H2O Starter Scripts

43. H2O.ai
Machine Intelligence
43
Kaggle - Active H2O Community
18k+ views in 2 weeks

44. H2O.ai
Machine Intelligence
44
Hyper-Parameter Tuning
93 numerical features
9 output classes
62k training set rows
144k test set rows
Ensemble of H2O DL + GBM => Top 10%
R script by DataGeek

45. H2O.ai
Machine Intelligence
45
Mastering Kaggle with H2O
DL + GBM
GBM
GBM + GLM
DRF + GLM
Stay tuned: Kaggle Master
@Mark_A_Landry recently
joined H2O as Competitive
Data Scientist!
www.meetup.com/Silicon-
Valley-Big-Data-Science/
events/222303884/

46. H2O.ai
Machine Intelligence
46
R’s data.table now in H2O!

47. H2O.ai
Machine Intelligence
Outlook - Algorithm Roadmap
• Ensembles (Erin LeDell et al.)
• Automated Hyper-Parameter Tuning
• Convolutional Layers for Deep Learning
• Natural Language Processing: tf-idf, Word2Vec, …
• Generalized Low Rank Models
• PCA, SVD, K-Means, Matrix Factorization
• Recommender Systems
And many more!
47
Public JIRAs - Join H2O!

48. H2O.ai
Machine Intelligence
Key Take-Aways
H2O is an open source predictive analytics
platform for data scientists and business analysts
who need scalable, fast and accurate machine
learning.
H2O Deep Learning is ready to take your
advanced analytics to the next level.
Try it on your data!
48
https://github.com/h2oai
H2O Google Group
http://h2o.ai
@h2oai
Thank You!