Operationalizing Machine Learning (Rajeev Dutt, CEO, Co-Founder, DimensionalMechanics) :: AWS Techforum 2018

Amazon Web Services Korea
Amazon Web Services KoreaAmazon Web Services Korea
© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Rajeev Dutt
DimensionalMechanics Inc.
Operationalizing Machine Learning
Challenge: ML is not IT Ready
Data
Provenance
Scope
Quality Versioning
Integration Deployment
Discoverability Security
Monitoring Support
Lifetime
Key considerations for enterprise AI:
For AI to become ubiquitous IT has to be
able to manage AI model development
and deployment process!
Copyright DimensionalMechanics 20185
NeoPulse™ automates the creation, distribution and management of AI
Humans don’t have to create AI Models – AI Studio can do this for you
Ubiquitous (adjective): present, appearing, or
found everywhere.
NeoPulse™ is about making AI ubiquitous –
on every device, in the cloud, and on premise
for every business large and small for any
machine learning problem.
NeoPulse™ reduces the barrier to entry so
that any developer, regardless of machine
learning experience, can create, deploy and
manage custom AI models in one third the
time and at 10% of the cost of comparable
platforms.
Data
Provenance
Scope
Quality Versioning
Integration Deployment
Discoverability Security
Monitoring Support
Lifetime
NeoPulse® can help with
Introducing NeoPulse™:
One platform for all Enterprise AI needs
Integrate
Plan
Deploy
Design
Train
Analyze
Manage
Portable Inference Models (PIM)
A neural network that is encapsulated in a container that can be queried using a runtime layer,
also referred to as an AI Model
NeoPulse® AI Studio: AI to build AI
Server application with a powerful AI called “the oracle” that is capable of automating the
process of creating sophisticated AI Models
NeoPulse™ Query Runtime
A program that is licensed by the organization to allow any application in the enterprise to
access the AI model using a web-based (REST) API
NeoPulse™ Modeling Language (NML)
An intuitive DSL (domain specific language) developed by DimensionalMechanics™ that is
executed by the NeoPulse™ AI Studio to automate the creation of new AI Models
NeoPulse® Framework
Learning methods
Classification
Regression
Some unsupervised (eg. Auto-encoders, GAN)
Data types supported
 Audio
 Video – single frame
 Video – multiple frames (motion video)
 Images
 Text
 Numerical
 Time Series
 Medical data (DICOM)
Enterprise Features
 Automated AI engineering
 Multi-platform (Cloud, PCs, ARM64 devices)
 RESTful Interfaces
 Extensive logging
 Integration with enterprise workflows
 Enterprise scaling
 Nvidia CUDA GPU computing
Capabilities
PIM
NeoPulse® AI Studio NeoPulse® Query
Runtime
NML File
.CSV
NeoPulse® Workflow
REST
Application
PIMNeoPulse™ AI Studio
NML File
.CSV
With a simple
command, the PIM can
be deployed anywhere
there is a runtime
including on ARM64
devices
NeoPulse® Workflow
Create intelligent applications in 7 steps
With tumors
Without tumors
0
1
label path
0 /images/negative/img_n_0001.jpg
0 /images/negative/img_n_0002.jpg
0 /images/negative/img_n_0003.jpg
…
0 /images/negative/img_n_<…>.jpg
1 /images/positive/img_p_0001.jpg
1 /images/positive/img_p_0002.jpg
1 /images/positive/img_p_0003.jpg
…
1 /images/positive/img_p_<…>.jpg
Curate your data and construct a CSV file
1
lung.csv
Assuming that you have high quality images and properly formatted, a simple script can construct the csv
file – less than an hour
Create the NML script
2
lung_classify.nml
Copy one of the examples listed on the DM Github page and modify it for your needs – less
than an hour
oracle("mode") = "classification"
source:
bind = "/DM-Dash/medical/lungtumor/lung.csv" ;
input: x ~ from “path" -> image: [shape=[28, 28], channels=1] -> ImageDataGenerator: [rescale= 0.003921568627451];
output: y ~ from “label”-> flat: [2] -> FlatDataGenerator: [] ;
params: batch_size=32, number_validation=10000 ;
architecture:
input: x ~ image: [shape=[28, 28], channels=1] ;
output: y ~ flat: [2] ;
x -> auto -> y ;
train:
compile: optimizer = auto, loss = auto, metrics = ['accuracy'] ;
run: epochs = 4 ;
dashboard: ;
1
2
3
4
5
6
7
8
9
10
11
12
13
14
Compile and start training
3
Compiling the NML code (assuming no syntax errors) is immediate – seconds
…training is another matter
NeoPulse™ AI Studio
lung_classify.nml
lung.csv
Training…
4
Training can take time depending on the volume of data and the compute resources available. There’s nothing for
you to do but the machine will be busy for a couple of days or more for a decent model
Fortunately AI Studio employs a queuing model – so it doesn’t stop you from starting the next project
NeoPulse™ AI Studio
Export a PIM file
NeoPulse™ AI Studio
Exporting a PIM file is simple – choose from a set of models based on accuracy (for example) and simply
export in a single call. The PIM is a file that can be moved from one machine to another (either locally or in
the cloud)
lung_tumor_model.pim
5
Import a PIM file
6
NeoPulse™ Query Runtime
lung_tumor_model.pim
Once the model has been built, you can move the resulting PIM file from machine to machine as long as the
NeoPulse Query Runtime has been installed. Importing the model into the runtime is a simple command –
takes just a couple of seconds.
Call the model via a REST API from an application
7
NeoPulse™ Query Runtime
After importing the model, NeoPulse™ Query Runtime automatically generates a RESTful API that allows
applications to query the model directly. You don’t need to build any custom APIs to call your model.
NeoPulse® Advantages
50x less code
18x lower project cost
4x lower developer cost
3x shorter project duration 3 4
18
50
1 1 1 1
0
10
20
30
40
50
60
Project Duration Development
Cost
Project Cost Lines of Code
Competition DM
CASE STUDY: AMORE PACIFIC
Sept 2015: Amore Pacific added to Forbes “Most Innovative
Company” list. Revenue: $4.5B
May 2018: Amore Pacific sent a team of four engineers without
ML experience for a 1 month training session on NeoPulse®
June 2018: Four engineers develop 20 models in 20 days during
initial training. Return to South Korea with 100%
recommending DM as company platform for AI model
development.
Sept 2018: Company hires Chief Digital Technology Officer to
oversee AI team.
 Amore Pacific puts first DNN Model into production with
$1200/month revenue stream to DM.
DimensionalMechanics has created a platform called
NeoPulse that maes it possible for companies like AMORE
PACIFIC to do machine learning at scale. We also found the
training useful and comprehensive. By using the NeoPulse, I
am confident that it will be a great help in achieving our # 1
beauty AI company vision."
-Kevin Choi, Leader, Digital IT Innovation Team, Amore
Pacific
Case Studies
A Seattle based staffing startup was quoted nearly $450,000
to develop a solution for their AI platform – NeoPulse
developed the solution for under $10,000.
A Seattle based medical startup was paying $20,000/month
for 6 months to develop and maintain a solution to create an
AI model that was 74% accurate. In three days, NeoPulse
built a solution with 86% accuracy costing the company only
$4,000.
Stanford University physicians could create a model to
differentiate between normal and abnormal PET/CT images
on NeoPulse with no prior knowledge of AI. Quality was high
enough that they published the results and the paper got
accepted at RSNA.
University of Washington ran a study comparing NeoPulse to
a standard vision recognition algorithm called VGG16. It took
20,000 iterations using VGG16 to get to 95% accuracy. It took
NeoPulse 30 iterations to reach the same accuracy.
Material Science
Auto-generation of materials:
• With University of Washington, we are running a program to automatically understand
material properties and then generate new materials with those properties
• Imagine designing new ultra-strong materials automatically and then 3D printing them…
AI generated materials
Original material
Available as AMIs on AWS AI Marketplace
NeoPulse® AI Studio
NeoPulse® Query Runtime
Watch out for a major announcement at
AWS re:Invent
Thank you
NeoPulse® AMI Architecture
Optional
Enterprise ML Pitfalls
Model Quality
How accurate is our model?
What is the false positive/false negative rate? RoC curve?
Is my model overfitted?
Bias vs. Variance of model?
Enterprise ML Pitfalls
Version Control
What version of the model am I working with?
When was it created?
Can I roll back to a previous model if the current model does not
perform?
Enterprise ML Pitfalls
Integration
Can the process of creating and deploying AI models be integrated
in an enterprise workflow?
How easy is it to integrate the models into enterprise
applications?
Are there any standards?
Enterprise ML Pitfalls
Deployment
Where has my model been deployed?
How many versions exist?
Who determines when and how the model is deployed?
What is the target environment (OS, Memory, Hardware config.)?
Enterprise ML Pitfalls
Discoverability
What models exist?
How do I access them?
Where do the models exist?
Enterprise ML Pitfalls
Monitoring
Can I retrieve statistics about my model?
 Number of queries
 Errors
 Time taken per query
 Batch vs. real time
 Overall performance metrics: CPU and memory utilization
Enterprise ML Pitfalls
Data Provenance
Where did the data to train the model come from?
How trustworthy is the data?
Is it biased?
Enterprise ML Pitfalls
Scope
What does my model do? (ex. classification of dogs/cats/lemurs)
What are its limits? – what can it do what can’t it do?
Who is the audience of the model?
What technology is used by the model?
Where can it run?
Who created it? For what purpose?
Enterprise ML Pitfalls
Security
Has anyone tampered with the training data? Can I tell?
How do I know that I can trust the model and that no one has
tampered with it?
Access controls on the model?
Is it possible to reverse engineer the model or the training data?*
Enterprise ML Pitfalls
Support
Do I have the staff with the right skills to support the solution?
What kind of problems am I likely to see?
How do I validate/test the model in the wild?
Enterprise ML Pitfalls
Lifetime & Deprecation
Does the underlying training data change?
How often?
Are the fundamental model statistics changing over time?
Should I retrain?
1 of 41

Recommended

엔터프라이즈의 AI/ML 활용을 돕는 Paxata 지능형 데이터 전처리 플랫폼 (최문규 이사, PAXATA) :: AWS Techforum... by
엔터프라이즈의 AI/ML 활용을 돕는 Paxata 지능형 데이터 전처리 플랫폼 (최문규 이사, PAXATA) :: AWS Techforum...엔터프라이즈의 AI/ML 활용을 돕는 Paxata 지능형 데이터 전처리 플랫폼 (최문규 이사, PAXATA) :: AWS Techforum...
엔터프라이즈의 AI/ML 활용을 돕는 Paxata 지능형 데이터 전처리 플랫폼 (최문규 이사, PAXATA) :: AWS Techforum...Amazon Web Services Korea
2.8K views22 slides
엔터프라이즈를 위한 머신러닝 그리고 AWS (김일호 솔루션즈 아키텍트, AWS) :: AWS Techforum 2018 by
엔터프라이즈를 위한 머신러닝 그리고 AWS (김일호 솔루션즈 아키텍트, AWS) :: AWS Techforum 2018엔터프라이즈를 위한 머신러닝 그리고 AWS (김일호 솔루션즈 아키텍트, AWS) :: AWS Techforum 2018
엔터프라이즈를 위한 머신러닝 그리고 AWS (김일호 솔루션즈 아키텍트, AWS) :: AWS Techforum 2018Amazon Web Services Korea
1.7K views55 slides
Why customers run SAP on AWS for Industry 4.0::Douglas Bellin::제조업 이노베이션 데이 S... by
Why customers run SAP on AWS for Industry 4.0::Douglas Bellin::제조업 이노베이션 데이 S...Why customers run SAP on AWS for Industry 4.0::Douglas Bellin::제조업 이노베이션 데이 S...
Why customers run SAP on AWS for Industry 4.0::Douglas Bellin::제조업 이노베이션 데이 S...Amazon Web Services Korea
2.1K views37 slides
Amazon SageMaker (December 2018) by
Amazon SageMaker (December 2018)Amazon SageMaker (December 2018)
Amazon SageMaker (December 2018)Julien SIMON
2.3K views36 slides
MLops workshop AWS by
MLops workshop AWSMLops workshop AWS
MLops workshop AWSGili Nachum
649 views30 slides
Data Analytics를 통한 비지니스 혁신::Craig Stries::AWS Summit Seoul 2018 by
Data Analytics를 통한 비지니스 혁신::Craig Stries::AWS Summit Seoul 2018Data Analytics를 통한 비지니스 혁신::Craig Stries::AWS Summit Seoul 2018
Data Analytics를 통한 비지니스 혁신::Craig Stries::AWS Summit Seoul 2018Amazon Web Services Korea
3.1K views35 slides

More Related Content

What's hot

글로벌 미디어 고객사의 AWS 활용 사례-워싱턴 포스트 ::지정아::AWS Summit Seoul 2018 by
글로벌 미디어 고객사의 AWS 활용 사례-워싱턴 포스트 ::지정아::AWS Summit Seoul 2018글로벌 미디어 고객사의 AWS 활용 사례-워싱턴 포스트 ::지정아::AWS Summit Seoul 2018
글로벌 미디어 고객사의 AWS 활용 사례-워싱턴 포스트 ::지정아::AWS Summit Seoul 2018Amazon Web Services Korea
2.7K views41 slides
Tensors for topic modeling and deep learning on AWS Sagemaker by
Tensors for topic modeling and deep learning on AWS SagemakerTensors for topic modeling and deep learning on AWS Sagemaker
Tensors for topic modeling and deep learning on AWS SagemakerAnima Anandkumar
2.8K views65 slides
大會主題演說 2: AI x 機器學習,無所不在!Ubiquity of AI and Machine Learning in our Everyday ... by
大會主題演說 2: AI x 機器學習,無所不在!Ubiquity of AI and Machine Learning in our Everyday ...大會主題演說 2: AI x 機器學習,無所不在!Ubiquity of AI and Machine Learning in our Everyday ...
大會主題演說 2: AI x 機器學習,無所不在!Ubiquity of AI and Machine Learning in our Everyday ...Amazon Web Services
716 views58 slides
Transforming Enterprise IT - AWS Transformation Days Raleigh 2018.pdf by
Transforming Enterprise IT - AWS Transformation Days Raleigh 2018.pdfTransforming Enterprise IT - AWS Transformation Days Raleigh 2018.pdf
Transforming Enterprise IT - AWS Transformation Days Raleigh 2018.pdfAmazon Web Services
769 views40 slides
Building Deep Learning Applications with TensorFlow and SageMaker on AWS - Te... by
Building Deep Learning Applications with TensorFlow and SageMaker on AWS - Te...Building Deep Learning Applications with TensorFlow and SageMaker on AWS - Te...
Building Deep Learning Applications with TensorFlow and SageMaker on AWS - Te...Amazon Web Services
1.2K views55 slides
Mcl345 re invent_sagemaker_dmbanga by
Mcl345 re invent_sagemaker_dmbangaMcl345 re invent_sagemaker_dmbanga
Mcl345 re invent_sagemaker_dmbangaDan Romuald Mbanga
309 views32 slides

What's hot(20)

글로벌 미디어 고객사의 AWS 활용 사례-워싱턴 포스트 ::지정아::AWS Summit Seoul 2018 by Amazon Web Services Korea
글로벌 미디어 고객사의 AWS 활용 사례-워싱턴 포스트 ::지정아::AWS Summit Seoul 2018글로벌 미디어 고객사의 AWS 활용 사례-워싱턴 포스트 ::지정아::AWS Summit Seoul 2018
글로벌 미디어 고객사의 AWS 활용 사례-워싱턴 포스트 ::지정아::AWS Summit Seoul 2018
Tensors for topic modeling and deep learning on AWS Sagemaker by Anima Anandkumar
Tensors for topic modeling and deep learning on AWS SagemakerTensors for topic modeling and deep learning on AWS Sagemaker
Tensors for topic modeling and deep learning on AWS Sagemaker
Anima Anandkumar2.8K views
大會主題演說 2: AI x 機器學習,無所不在!Ubiquity of AI and Machine Learning in our Everyday ... by Amazon Web Services
大會主題演說 2: AI x 機器學習,無所不在!Ubiquity of AI and Machine Learning in our Everyday ...大會主題演說 2: AI x 機器學習,無所不在!Ubiquity of AI and Machine Learning in our Everyday ...
大會主題演說 2: AI x 機器學習,無所不在!Ubiquity of AI and Machine Learning in our Everyday ...
Transforming Enterprise IT - AWS Transformation Days Raleigh 2018.pdf by Amazon Web Services
Transforming Enterprise IT - AWS Transformation Days Raleigh 2018.pdfTransforming Enterprise IT - AWS Transformation Days Raleigh 2018.pdf
Transforming Enterprise IT - AWS Transformation Days Raleigh 2018.pdf
Building Deep Learning Applications with TensorFlow and SageMaker on AWS - Te... by Amazon Web Services
Building Deep Learning Applications with TensorFlow and SageMaker on AWS - Te...Building Deep Learning Applications with TensorFlow and SageMaker on AWS - Te...
Building Deep Learning Applications with TensorFlow and SageMaker on AWS - Te...
Amazon Web Services1.2K views
NLP in Healthcare to Predict Adverse Events with Amazon SageMaker (AIM346) - ... by Amazon Web Services
NLP in Healthcare to Predict Adverse Events with Amazon SageMaker (AIM346) - ...NLP in Healthcare to Predict Adverse Events with Amazon SageMaker (AIM346) - ...
NLP in Healthcare to Predict Adverse Events with Amazon SageMaker (AIM346) - ...
Amazon Web Services2.2K views
Artificial Intelligence nella realtà di oggi: come utilizzarla al meglio by Amazon Web Services
Artificial Intelligence nella realtà di oggi: come utilizzarla al meglioArtificial Intelligence nella realtà di oggi: come utilizzarla al meglio
Artificial Intelligence nella realtà di oggi: come utilizzarla al meglio
Build a Custom Model for Object & Logo Detection (AIM421) - AWS re:Invent 2018 by Amazon Web Services
Build a Custom Model for Object & Logo Detection (AIM421) - AWS re:Invent 2018Build a Custom Model for Object & Logo Detection (AIM421) - AWS re:Invent 2018
Build a Custom Model for Object & Logo Detection (AIM421) - AWS re:Invent 2018
Amazon Web Services4.5K views
An Introduction to Amazon SageMaker (October 2018) by Julien SIMON
An Introduction to Amazon SageMaker (October 2018)An Introduction to Amazon SageMaker (October 2018)
An Introduction to Amazon SageMaker (October 2018)
Julien SIMON1.1K views
Predicting the Future with Amazon SageMaker - AWS Summit Sydney 2018 by Amazon Web Services
Predicting the Future with Amazon SageMaker - AWS Summit Sydney 2018Predicting the Future with Amazon SageMaker - AWS Summit Sydney 2018
Predicting the Future with Amazon SageMaker - AWS Summit Sydney 2018
Integrating Amazon SageMaker into your Enterprise - AWS Online Tech Talks by Amazon Web Services
Integrating Amazon SageMaker into your Enterprise - AWS Online Tech TalksIntegrating Amazon SageMaker into your Enterprise - AWS Online Tech Talks
Integrating Amazon SageMaker into your Enterprise - AWS Online Tech Talks
Amazon Web Services1.3K views
Microsoft AI Platform - AETHER Introduction by Karthik Murugesan
Microsoft AI Platform - AETHER IntroductionMicrosoft AI Platform - AETHER Introduction
Microsoft AI Platform - AETHER Introduction
From notebook to production with Amazon Sagemaker by Amazon Web Services
From notebook to production with Amazon SagemakerFrom notebook to production with Amazon Sagemaker
From notebook to production with Amazon Sagemaker
Supercharge Your ML Model with SageMaker - AWS Summit Sydney 2018 by Amazon Web Services
Supercharge Your ML Model with SageMaker - AWS Summit Sydney 2018Supercharge Your ML Model with SageMaker - AWS Summit Sydney 2018
Supercharge Your ML Model with SageMaker - AWS Summit Sydney 2018
An Introduction to Reinforcement Learning (December 2018) by Julien SIMON
An Introduction to Reinforcement Learning (December 2018)An Introduction to Reinforcement Learning (December 2018)
An Introduction to Reinforcement Learning (December 2018)
Julien SIMON1.1K views

Similar to Operationalizing Machine Learning (Rajeev Dutt, CEO, Co-Founder, DimensionalMechanics) :: AWS Techforum 2018

OpenPOWER/POWER9 AI webinar by
OpenPOWER/POWER9 AI webinar OpenPOWER/POWER9 AI webinar
OpenPOWER/POWER9 AI webinar Ganesan Narayanasamy
330 views32 slides
InTTrust -IBM Artificial Intelligence Event by
InTTrust -IBM Artificial Intelligence  EventInTTrust -IBM Artificial Intelligence  Event
InTTrust -IBM Artificial Intelligence EventMichail Pagiatakis
175 views32 slides
Data Science at Speed. At Scale. by
Data Science at Speed. At Scale.Data Science at Speed. At Scale.
Data Science at Speed. At Scale.DataWorks Summit
5K views14 slides
Generative AI at the edge.pdf by
Generative AI at the edge.pdfGenerative AI at the edge.pdf
Generative AI at the edge.pdfQualcomm Research
171 views37 slides
World Artificial Intelligence Conference Shanghai 2018 by
World Artificial Intelligence Conference Shanghai 2018World Artificial Intelligence Conference Shanghai 2018
World Artificial Intelligence Conference Shanghai 2018Adam Gibson
893 views64 slides
Continuous Intelligence Workshop by
Continuous Intelligence WorkshopContinuous Intelligence Workshop
Continuous Intelligence WorkshopDavid Tan
193 views38 slides

Similar to Operationalizing Machine Learning (Rajeev Dutt, CEO, Co-Founder, DimensionalMechanics) :: AWS Techforum 2018(20)

World Artificial Intelligence Conference Shanghai 2018 by Adam Gibson
World Artificial Intelligence Conference Shanghai 2018World Artificial Intelligence Conference Shanghai 2018
World Artificial Intelligence Conference Shanghai 2018
Adam Gibson893 views
Continuous Intelligence Workshop by David Tan
Continuous Intelligence WorkshopContinuous Intelligence Workshop
Continuous Intelligence Workshop
David Tan193 views
Emerging engineering issues for building large scale AI systems By Srinivas P... by Analytics India Magazine
Emerging engineering issues for building large scale AI systems By Srinivas P...Emerging engineering issues for building large scale AI systems By Srinivas P...
Emerging engineering issues for building large scale AI systems By Srinivas P...
Hyf azure ml_1 by KatoK1
Hyf azure ml_1Hyf azure ml_1
Hyf azure ml_1
KatoK166 views
For linked in part 2 no template by Pankaj Tomar
For linked in part 2  no templateFor linked in part 2  no template
For linked in part 2 no template
Pankaj Tomar88 views
Software Quality Management in Wipro and case tools ,Wipro Introduction and c... by Preethi T G
Software Quality Management in Wipro and case tools ,Wipro Introduction and c...Software Quality Management in Wipro and case tools ,Wipro Introduction and c...
Software Quality Management in Wipro and case tools ,Wipro Introduction and c...
Preethi T G99 views
DEV Meet-Up Q2 2022 Amsterdam Slides.pdf by Cristina Vidu
DEV Meet-Up Q2 2022 Amsterdam Slides.pdfDEV Meet-Up Q2 2022 Amsterdam Slides.pdf
DEV Meet-Up Q2 2022 Amsterdam Slides.pdf
Cristina Vidu221 views
DevOps : Consulting with Foresight by InfoSeption
DevOps : Consulting with ForesightDevOps : Consulting with Foresight
DevOps : Consulting with Foresight
InfoSeption1.8K views
Platform approach to scaling machine learning across the enterprise by Olalekan Fuad Elesin
Platform approach to scaling machine learning across the enterprisePlatform approach to scaling machine learning across the enterprise
Platform approach to scaling machine learning across the enterprise

More from Amazon Web Services Korea

AWS Modern Infra with Storage Roadshow 2023 - Day 2 by
AWS Modern Infra with Storage Roadshow 2023 - Day 2AWS Modern Infra with Storage Roadshow 2023 - Day 2
AWS Modern Infra with Storage Roadshow 2023 - Day 2Amazon Web Services Korea
172 views146 slides
AWS Modern Infra with Storage Roadshow 2023 - Day 1 by
AWS Modern Infra with Storage Roadshow 2023 - Day 1AWS Modern Infra with Storage Roadshow 2023 - Day 1
AWS Modern Infra with Storage Roadshow 2023 - Day 1Amazon Web Services Korea
102 views173 slides
사례로 알아보는 Database Migration Service : 데이터베이스 및 데이터 이관, 통합, 분리, 분석의 도구 - 발표자: ... by
사례로 알아보는 Database Migration Service : 데이터베이스 및 데이터 이관, 통합, 분리, 분석의 도구 - 발표자: ...사례로 알아보는 Database Migration Service : 데이터베이스 및 데이터 이관, 통합, 분리, 분석의 도구 - 발표자: ...
사례로 알아보는 Database Migration Service : 데이터베이스 및 데이터 이관, 통합, 분리, 분석의 도구 - 발표자: ...Amazon Web Services Korea
304 views24 slides
Amazon DocumentDB - Architecture 및 Best Practice (Level 200) - 발표자: 장동훈, Sr. ... by
Amazon DocumentDB - Architecture 및 Best Practice (Level 200) - 발표자: 장동훈, Sr. ...Amazon DocumentDB - Architecture 및 Best Practice (Level 200) - 발표자: 장동훈, Sr. ...
Amazon DocumentDB - Architecture 및 Best Practice (Level 200) - 발표자: 장동훈, Sr. ...Amazon Web Services Korea
219 views86 slides
Amazon Elasticache - Fully managed, Redis & Memcached Compatible Service (Lev... by
Amazon Elasticache - Fully managed, Redis & Memcached Compatible Service (Lev...Amazon Elasticache - Fully managed, Redis & Memcached Compatible Service (Lev...
Amazon Elasticache - Fully managed, Redis & Memcached Compatible Service (Lev...Amazon Web Services Korea
218 views81 slides
Internal Architecture of Amazon Aurora (Level 400) - 발표자: 정달영, APAC RDS Speci... by
Internal Architecture of Amazon Aurora (Level 400) - 발표자: 정달영, APAC RDS Speci...Internal Architecture of Amazon Aurora (Level 400) - 발표자: 정달영, APAC RDS Speci...
Internal Architecture of Amazon Aurora (Level 400) - 발표자: 정달영, APAC RDS Speci...Amazon Web Services Korea
473 views65 slides

More from Amazon Web Services Korea(20)

사례로 알아보는 Database Migration Service : 데이터베이스 및 데이터 이관, 통합, 분리, 분석의 도구 - 발표자: ... by Amazon Web Services Korea
사례로 알아보는 Database Migration Service : 데이터베이스 및 데이터 이관, 통합, 분리, 분석의 도구 - 발표자: ...사례로 알아보는 Database Migration Service : 데이터베이스 및 데이터 이관, 통합, 분리, 분석의 도구 - 발표자: ...
사례로 알아보는 Database Migration Service : 데이터베이스 및 데이터 이관, 통합, 분리, 분석의 도구 - 발표자: ...
Amazon DocumentDB - Architecture 및 Best Practice (Level 200) - 발표자: 장동훈, Sr. ... by Amazon Web Services Korea
Amazon DocumentDB - Architecture 및 Best Practice (Level 200) - 발표자: 장동훈, Sr. ...Amazon DocumentDB - Architecture 및 Best Practice (Level 200) - 발표자: 장동훈, Sr. ...
Amazon DocumentDB - Architecture 및 Best Practice (Level 200) - 발표자: 장동훈, Sr. ...
Amazon Elasticache - Fully managed, Redis & Memcached Compatible Service (Lev... by Amazon Web Services Korea
Amazon Elasticache - Fully managed, Redis & Memcached Compatible Service (Lev...Amazon Elasticache - Fully managed, Redis & Memcached Compatible Service (Lev...
Amazon Elasticache - Fully managed, Redis & Memcached Compatible Service (Lev...
Internal Architecture of Amazon Aurora (Level 400) - 발표자: 정달영, APAC RDS Speci... by Amazon Web Services Korea
Internal Architecture of Amazon Aurora (Level 400) - 발표자: 정달영, APAC RDS Speci...Internal Architecture of Amazon Aurora (Level 400) - 발표자: 정달영, APAC RDS Speci...
Internal Architecture of Amazon Aurora (Level 400) - 발표자: 정달영, APAC RDS Speci...
[Keynote] 슬기로운 AWS 데이터베이스 선택하기 - 발표자: 강민석, Korea Database SA Manager, WWSO, A... by Amazon Web Services Korea
[Keynote] 슬기로운 AWS 데이터베이스 선택하기 - 발표자: 강민석, Korea Database SA Manager, WWSO, A...[Keynote] 슬기로운 AWS 데이터베이스 선택하기 - 발표자: 강민석, Korea Database SA Manager, WWSO, A...
[Keynote] 슬기로운 AWS 데이터베이스 선택하기 - 발표자: 강민석, Korea Database SA Manager, WWSO, A...
Demystify Streaming on AWS - 발표자: 이종혁, Sr Analytics Specialist, WWSO, AWS :::... by Amazon Web Services Korea
Demystify Streaming on AWS - 발표자: 이종혁, Sr Analytics Specialist, WWSO, AWS :::...Demystify Streaming on AWS - 발표자: 이종혁, Sr Analytics Specialist, WWSO, AWS :::...
Demystify Streaming on AWS - 발표자: 이종혁, Sr Analytics Specialist, WWSO, AWS :::...
Amazon EMR - Enhancements on Cost/Performance, Serverless - 발표자: 김기영, Sr Anal... by Amazon Web Services Korea
Amazon EMR - Enhancements on Cost/Performance, Serverless - 발표자: 김기영, Sr Anal...Amazon EMR - Enhancements on Cost/Performance, Serverless - 발표자: 김기영, Sr Anal...
Amazon EMR - Enhancements on Cost/Performance, Serverless - 발표자: 김기영, Sr Anal...
Amazon OpenSearch - Use Cases, Security/Observability, Serverless and Enhance... by Amazon Web Services Korea
Amazon OpenSearch - Use Cases, Security/Observability, Serverless and Enhance...Amazon OpenSearch - Use Cases, Security/Observability, Serverless and Enhance...
Amazon OpenSearch - Use Cases, Security/Observability, Serverless and Enhance...
Enabling Agility with Data Governance - 발표자: 김성연, Analytics Specialist, WWSO,... by Amazon Web Services Korea
Enabling Agility with Data Governance - 발표자: 김성연, Analytics Specialist, WWSO,...Enabling Agility with Data Governance - 발표자: 김성연, Analytics Specialist, WWSO,...
Enabling Agility with Data Governance - 발표자: 김성연, Analytics Specialist, WWSO,...
Amazon Redshift Deep Dive - Serverless, Streaming, ML, Auto Copy (New feature... by Amazon Web Services Korea
Amazon Redshift Deep Dive - Serverless, Streaming, ML, Auto Copy (New feature...Amazon Redshift Deep Dive - Serverless, Streaming, ML, Auto Copy (New feature...
Amazon Redshift Deep Dive - Serverless, Streaming, ML, Auto Copy (New feature...
From Insights to Action, How to build and maintain a Data Driven Organization... by Amazon Web Services Korea
From Insights to Action, How to build and maintain a Data Driven Organization...From Insights to Action, How to build and maintain a Data Driven Organization...
From Insights to Action, How to build and maintain a Data Driven Organization...
Amazon DynamoDB - Use Cases and Cost Optimization - 발표자: 이혁, DynamoDB Special... by Amazon Web Services Korea
Amazon DynamoDB - Use Cases and Cost Optimization - 발표자: 이혁, DynamoDB Special...Amazon DynamoDB - Use Cases and Cost Optimization - 발표자: 이혁, DynamoDB Special...
Amazon DynamoDB - Use Cases and Cost Optimization - 발표자: 이혁, DynamoDB Special...
LG전자 - Amazon Aurora 및 RDS 블루/그린 배포를 이용한 데이터베이스 업그레이드 안정성 확보 - 발표자: 이은경 책임, L... by Amazon Web Services Korea
LG전자 - Amazon Aurora 및 RDS 블루/그린 배포를 이용한 데이터베이스 업그레이드 안정성 확보 - 발표자: 이은경 책임, L...LG전자 - Amazon Aurora 및 RDS 블루/그린 배포를 이용한 데이터베이스 업그레이드 안정성 확보 - 발표자: 이은경 책임, L...
LG전자 - Amazon Aurora 및 RDS 블루/그린 배포를 이용한 데이터베이스 업그레이드 안정성 확보 - 발표자: 이은경 책임, L...
KB국민카드 - 클라우드 기반 분석 플랫폼 혁신 여정 - 발표자: 박창용 과장, 데이터전략본부, AI혁신부, KB카드│강병억, Soluti... by Amazon Web Services Korea
KB국민카드 - 클라우드 기반 분석 플랫폼 혁신 여정 - 발표자: 박창용 과장, 데이터전략본부, AI혁신부, KB카드│강병억, Soluti...KB국민카드 - 클라우드 기반 분석 플랫폼 혁신 여정 - 발표자: 박창용 과장, 데이터전략본부, AI혁신부, KB카드│강병억, Soluti...
KB국민카드 - 클라우드 기반 분석 플랫폼 혁신 여정 - 발표자: 박창용 과장, 데이터전략본부, AI혁신부, KB카드│강병억, Soluti...
SK Telecom - 망관리 프로젝트 TANGO의 오픈소스 데이터베이스 전환 여정 - 발표자 : 박승전, Project Manager, ... by Amazon Web Services Korea
SK Telecom - 망관리 프로젝트 TANGO의 오픈소스 데이터베이스 전환 여정 - 발표자 : 박승전, Project Manager, ...SK Telecom - 망관리 프로젝트 TANGO의 오픈소스 데이터베이스 전환 여정 - 발표자 : 박승전, Project Manager, ...
SK Telecom - 망관리 프로젝트 TANGO의 오픈소스 데이터베이스 전환 여정 - 발표자 : 박승전, Project Manager, ...
코리안리 - 데이터 분석 플랫폼 구축 여정, 그 시작과 과제 - 발표자: 김석기 그룹장, 데이터비즈니스센터, 메가존클라우드 ::: AWS ... by Amazon Web Services Korea
코리안리 - 데이터 분석 플랫폼 구축 여정, 그 시작과 과제 - 발표자: 김석기 그룹장, 데이터비즈니스센터, 메가존클라우드 ::: AWS ...코리안리 - 데이터 분석 플랫폼 구축 여정, 그 시작과 과제 - 발표자: 김석기 그룹장, 데이터비즈니스센터, 메가존클라우드 ::: AWS ...
코리안리 - 데이터 분석 플랫폼 구축 여정, 그 시작과 과제 - 발표자: 김석기 그룹장, 데이터비즈니스센터, 메가존클라우드 ::: AWS ...
LG 이노텍 - Amazon Redshift Serverless를 활용한 데이터 분석 플랫폼 혁신 과정 - 발표자: 유재상 선임, LG이노... by Amazon Web Services Korea
LG 이노텍 - Amazon Redshift Serverless를 활용한 데이터 분석 플랫폼 혁신 과정 - 발표자: 유재상 선임, LG이노...LG 이노텍 - Amazon Redshift Serverless를 활용한 데이터 분석 플랫폼 혁신 과정 - 발표자: 유재상 선임, LG이노...
LG 이노텍 - Amazon Redshift Serverless를 활용한 데이터 분석 플랫폼 혁신 과정 - 발표자: 유재상 선임, LG이노...
AWS Summit Seoul 2023 | Amazon Neptune 및 Elastic을 이용한 추천 서비스 및 검색 플랫폼 구축하기 by Amazon Web Services Korea
AWS Summit Seoul 2023 | Amazon Neptune 및 Elastic을 이용한 추천 서비스 및 검색 플랫폼 구축하기AWS Summit Seoul 2023 | Amazon Neptune 및 Elastic을 이용한 추천 서비스 및 검색 플랫폼 구축하기
AWS Summit Seoul 2023 | Amazon Neptune 및 Elastic을 이용한 추천 서비스 및 검색 플랫폼 구축하기

Recently uploaded

Roadmap to Become Experts.pptx by
Roadmap to Become Experts.pptxRoadmap to Become Experts.pptx
Roadmap to Become Experts.pptxdscwidyatamanew
11 views45 slides
Spesifikasi Lengkap ASUS Vivobook Go 14 by
Spesifikasi Lengkap ASUS Vivobook Go 14Spesifikasi Lengkap ASUS Vivobook Go 14
Spesifikasi Lengkap ASUS Vivobook Go 14Dot Semarang
35 views1 slide
AMAZON PRODUCT RESEARCH.pdf by
AMAZON PRODUCT RESEARCH.pdfAMAZON PRODUCT RESEARCH.pdf
AMAZON PRODUCT RESEARCH.pdfJerikkLaureta
15 views13 slides
Web Dev - 1 PPT.pdf by
Web Dev - 1 PPT.pdfWeb Dev - 1 PPT.pdf
Web Dev - 1 PPT.pdfgdsczhcet
55 views45 slides
Report 2030 Digital Decade by
Report 2030 Digital DecadeReport 2030 Digital Decade
Report 2030 Digital DecadeMassimo Talia
14 views41 slides
Data-centric AI and the convergence of data and model engineering: opportunit... by
Data-centric AI and the convergence of data and model engineering:opportunit...Data-centric AI and the convergence of data and model engineering:opportunit...
Data-centric AI and the convergence of data and model engineering: opportunit...Paolo Missier
34 views40 slides

Recently uploaded(20)

Spesifikasi Lengkap ASUS Vivobook Go 14 by Dot Semarang
Spesifikasi Lengkap ASUS Vivobook Go 14Spesifikasi Lengkap ASUS Vivobook Go 14
Spesifikasi Lengkap ASUS Vivobook Go 14
Dot Semarang35 views
AMAZON PRODUCT RESEARCH.pdf by JerikkLaureta
AMAZON PRODUCT RESEARCH.pdfAMAZON PRODUCT RESEARCH.pdf
AMAZON PRODUCT RESEARCH.pdf
JerikkLaureta15 views
Web Dev - 1 PPT.pdf by gdsczhcet
Web Dev - 1 PPT.pdfWeb Dev - 1 PPT.pdf
Web Dev - 1 PPT.pdf
gdsczhcet55 views
Data-centric AI and the convergence of data and model engineering: opportunit... by Paolo Missier
Data-centric AI and the convergence of data and model engineering:opportunit...Data-centric AI and the convergence of data and model engineering:opportunit...
Data-centric AI and the convergence of data and model engineering: opportunit...
Paolo Missier34 views
Voice Logger - Telephony Integration Solution at Aegis by Nirmal Sharma
Voice Logger - Telephony Integration Solution at AegisVoice Logger - Telephony Integration Solution at Aegis
Voice Logger - Telephony Integration Solution at Aegis
Nirmal Sharma17 views
Black and White Modern Science Presentation.pptx by maryamkhalid2916
Black and White Modern Science Presentation.pptxBlack and White Modern Science Presentation.pptx
Black and White Modern Science Presentation.pptx
maryamkhalid291614 views
RADIUS-Omnichannel Interaction System by RADIUS
RADIUS-Omnichannel Interaction SystemRADIUS-Omnichannel Interaction System
RADIUS-Omnichannel Interaction System
RADIUS15 views
Attacking IoT Devices from a Web Perspective - Linux Day by Simone Onofri
Attacking IoT Devices from a Web Perspective - Linux Day Attacking IoT Devices from a Web Perspective - Linux Day
Attacking IoT Devices from a Web Perspective - Linux Day
Simone Onofri15 views
SAP Automation Using Bar Code and FIORI.pdf by Virendra Rai, PMP
SAP Automation Using Bar Code and FIORI.pdfSAP Automation Using Bar Code and FIORI.pdf
SAP Automation Using Bar Code and FIORI.pdf
How the World's Leading Independent Automotive Distributor is Reinventing Its... by NUS-ISS
How the World's Leading Independent Automotive Distributor is Reinventing Its...How the World's Leading Independent Automotive Distributor is Reinventing Its...
How the World's Leading Independent Automotive Distributor is Reinventing Its...
NUS-ISS15 views
Perth MeetUp November 2023 by Michael Price
Perth MeetUp November 2023 Perth MeetUp November 2023
Perth MeetUp November 2023
Michael Price15 views
AI: mind, matter, meaning, metaphors, being, becoming, life values by Twain Liu 刘秋艳
AI: mind, matter, meaning, metaphors, being, becoming, life valuesAI: mind, matter, meaning, metaphors, being, becoming, life values
AI: mind, matter, meaning, metaphors, being, becoming, life values
Transcript: The Details of Description Techniques tips and tangents on altern... by BookNet Canada
Transcript: The Details of Description Techniques tips and tangents on altern...Transcript: The Details of Description Techniques tips and tangents on altern...
Transcript: The Details of Description Techniques tips and tangents on altern...
BookNet Canada130 views

Operationalizing Machine Learning (Rajeev Dutt, CEO, Co-Founder, DimensionalMechanics) :: AWS Techforum 2018

  • 1. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Rajeev Dutt DimensionalMechanics Inc. Operationalizing Machine Learning
  • 2. Challenge: ML is not IT Ready
  • 3. Data Provenance Scope Quality Versioning Integration Deployment Discoverability Security Monitoring Support Lifetime Key considerations for enterprise AI:
  • 4. For AI to become ubiquitous IT has to be able to manage AI model development and deployment process!
  • 5. Copyright DimensionalMechanics 20185 NeoPulse™ automates the creation, distribution and management of AI Humans don’t have to create AI Models – AI Studio can do this for you
  • 6. Ubiquitous (adjective): present, appearing, or found everywhere. NeoPulse™ is about making AI ubiquitous – on every device, in the cloud, and on premise for every business large and small for any machine learning problem. NeoPulse™ reduces the barrier to entry so that any developer, regardless of machine learning experience, can create, deploy and manage custom AI models in one third the time and at 10% of the cost of comparable platforms.
  • 7. Data Provenance Scope Quality Versioning Integration Deployment Discoverability Security Monitoring Support Lifetime NeoPulse® can help with
  • 8. Introducing NeoPulse™: One platform for all Enterprise AI needs Integrate Plan Deploy Design Train Analyze Manage
  • 9. Portable Inference Models (PIM) A neural network that is encapsulated in a container that can be queried using a runtime layer, also referred to as an AI Model NeoPulse® AI Studio: AI to build AI Server application with a powerful AI called “the oracle” that is capable of automating the process of creating sophisticated AI Models NeoPulse™ Query Runtime A program that is licensed by the organization to allow any application in the enterprise to access the AI model using a web-based (REST) API NeoPulse™ Modeling Language (NML) An intuitive DSL (domain specific language) developed by DimensionalMechanics™ that is executed by the NeoPulse™ AI Studio to automate the creation of new AI Models NeoPulse® Framework
  • 10. Learning methods Classification Regression Some unsupervised (eg. Auto-encoders, GAN) Data types supported  Audio  Video – single frame  Video – multiple frames (motion video)  Images  Text  Numerical  Time Series  Medical data (DICOM) Enterprise Features  Automated AI engineering  Multi-platform (Cloud, PCs, ARM64 devices)  RESTful Interfaces  Extensive logging  Integration with enterprise workflows  Enterprise scaling  Nvidia CUDA GPU computing Capabilities
  • 11. PIM NeoPulse® AI Studio NeoPulse® Query Runtime NML File .CSV NeoPulse® Workflow REST Application
  • 12. PIMNeoPulse™ AI Studio NML File .CSV With a simple command, the PIM can be deployed anywhere there is a runtime including on ARM64 devices NeoPulse® Workflow
  • 14. With tumors Without tumors 0 1 label path 0 /images/negative/img_n_0001.jpg 0 /images/negative/img_n_0002.jpg 0 /images/negative/img_n_0003.jpg … 0 /images/negative/img_n_<…>.jpg 1 /images/positive/img_p_0001.jpg 1 /images/positive/img_p_0002.jpg 1 /images/positive/img_p_0003.jpg … 1 /images/positive/img_p_<…>.jpg Curate your data and construct a CSV file 1 lung.csv Assuming that you have high quality images and properly formatted, a simple script can construct the csv file – less than an hour
  • 15. Create the NML script 2 lung_classify.nml Copy one of the examples listed on the DM Github page and modify it for your needs – less than an hour oracle("mode") = "classification" source: bind = "/DM-Dash/medical/lungtumor/lung.csv" ; input: x ~ from “path" -> image: [shape=[28, 28], channels=1] -> ImageDataGenerator: [rescale= 0.003921568627451]; output: y ~ from “label”-> flat: [2] -> FlatDataGenerator: [] ; params: batch_size=32, number_validation=10000 ; architecture: input: x ~ image: [shape=[28, 28], channels=1] ; output: y ~ flat: [2] ; x -> auto -> y ; train: compile: optimizer = auto, loss = auto, metrics = ['accuracy'] ; run: epochs = 4 ; dashboard: ; 1 2 3 4 5 6 7 8 9 10 11 12 13 14
  • 16. Compile and start training 3 Compiling the NML code (assuming no syntax errors) is immediate – seconds …training is another matter NeoPulse™ AI Studio lung_classify.nml lung.csv
  • 17. Training… 4 Training can take time depending on the volume of data and the compute resources available. There’s nothing for you to do but the machine will be busy for a couple of days or more for a decent model Fortunately AI Studio employs a queuing model – so it doesn’t stop you from starting the next project NeoPulse™ AI Studio
  • 18. Export a PIM file NeoPulse™ AI Studio Exporting a PIM file is simple – choose from a set of models based on accuracy (for example) and simply export in a single call. The PIM is a file that can be moved from one machine to another (either locally or in the cloud) lung_tumor_model.pim 5
  • 19. Import a PIM file 6 NeoPulse™ Query Runtime lung_tumor_model.pim Once the model has been built, you can move the resulting PIM file from machine to machine as long as the NeoPulse Query Runtime has been installed. Importing the model into the runtime is a simple command – takes just a couple of seconds.
  • 20. Call the model via a REST API from an application 7 NeoPulse™ Query Runtime After importing the model, NeoPulse™ Query Runtime automatically generates a RESTful API that allows applications to query the model directly. You don’t need to build any custom APIs to call your model.
  • 21. NeoPulse® Advantages 50x less code 18x lower project cost 4x lower developer cost 3x shorter project duration 3 4 18 50 1 1 1 1 0 10 20 30 40 50 60 Project Duration Development Cost Project Cost Lines of Code Competition DM
  • 22. CASE STUDY: AMORE PACIFIC Sept 2015: Amore Pacific added to Forbes “Most Innovative Company” list. Revenue: $4.5B May 2018: Amore Pacific sent a team of four engineers without ML experience for a 1 month training session on NeoPulse® June 2018: Four engineers develop 20 models in 20 days during initial training. Return to South Korea with 100% recommending DM as company platform for AI model development. Sept 2018: Company hires Chief Digital Technology Officer to oversee AI team.  Amore Pacific puts first DNN Model into production with $1200/month revenue stream to DM. DimensionalMechanics has created a platform called NeoPulse that maes it possible for companies like AMORE PACIFIC to do machine learning at scale. We also found the training useful and comprehensive. By using the NeoPulse, I am confident that it will be a great help in achieving our # 1 beauty AI company vision." -Kevin Choi, Leader, Digital IT Innovation Team, Amore Pacific
  • 23. Case Studies A Seattle based staffing startup was quoted nearly $450,000 to develop a solution for their AI platform – NeoPulse developed the solution for under $10,000. A Seattle based medical startup was paying $20,000/month for 6 months to develop and maintain a solution to create an AI model that was 74% accurate. In three days, NeoPulse built a solution with 86% accuracy costing the company only $4,000. Stanford University physicians could create a model to differentiate between normal and abnormal PET/CT images on NeoPulse with no prior knowledge of AI. Quality was high enough that they published the results and the paper got accepted at RSNA. University of Washington ran a study comparing NeoPulse to a standard vision recognition algorithm called VGG16. It took 20,000 iterations using VGG16 to get to 95% accuracy. It took NeoPulse 30 iterations to reach the same accuracy.
  • 24. Material Science Auto-generation of materials: • With University of Washington, we are running a program to automatically understand material properties and then generate new materials with those properties • Imagine designing new ultra-strong materials automatically and then 3D printing them… AI generated materials Original material
  • 25. Available as AMIs on AWS AI Marketplace
  • 28. Watch out for a major announcement at AWS re:Invent
  • 31. Enterprise ML Pitfalls Model Quality How accurate is our model? What is the false positive/false negative rate? RoC curve? Is my model overfitted? Bias vs. Variance of model?
  • 32. Enterprise ML Pitfalls Version Control What version of the model am I working with? When was it created? Can I roll back to a previous model if the current model does not perform?
  • 33. Enterprise ML Pitfalls Integration Can the process of creating and deploying AI models be integrated in an enterprise workflow? How easy is it to integrate the models into enterprise applications? Are there any standards?
  • 34. Enterprise ML Pitfalls Deployment Where has my model been deployed? How many versions exist? Who determines when and how the model is deployed? What is the target environment (OS, Memory, Hardware config.)?
  • 35. Enterprise ML Pitfalls Discoverability What models exist? How do I access them? Where do the models exist?
  • 36. Enterprise ML Pitfalls Monitoring Can I retrieve statistics about my model?  Number of queries  Errors  Time taken per query  Batch vs. real time  Overall performance metrics: CPU and memory utilization
  • 37. Enterprise ML Pitfalls Data Provenance Where did the data to train the model come from? How trustworthy is the data? Is it biased?
  • 38. Enterprise ML Pitfalls Scope What does my model do? (ex. classification of dogs/cats/lemurs) What are its limits? – what can it do what can’t it do? Who is the audience of the model? What technology is used by the model? Where can it run? Who created it? For what purpose?
  • 39. Enterprise ML Pitfalls Security Has anyone tampered with the training data? Can I tell? How do I know that I can trust the model and that no one has tampered with it? Access controls on the model? Is it possible to reverse engineer the model or the training data?*
  • 40. Enterprise ML Pitfalls Support Do I have the staff with the right skills to support the solution? What kind of problems am I likely to see? How do I validate/test the model in the wild?
  • 41. Enterprise ML Pitfalls Lifetime & Deprecation Does the underlying training data change? How often? Are the fundamental model statistics changing over time? Should I retrain?