SlideShare una empresa de Scribd logo
1 de 39
Descargar para leer sin conexión
@seldon_io
hello@seldon.io
bit.ly/SeldonCoreSlack
Machine Learning
Deployment for Enterprise.
O’Reilly AI for IBM: Deploying ML Models at Scale
We help people shape the
future by bringing
machine learning
deployment to life.
Meet the Team.
Alex Housley
CEO & Founder
Clive Cox PhD
CTO
Gurminder Sunner
VP Engineering
Lee Baker
Commercial Director
Giovanni Vacanti PhD
Machine Learning
Engineer
Inga Veidmane
Operations Manager
Andrew Turner
Sales Manager
Janis Klaise PhD
Data Scientist
Arnaud Van Looveren
Data Scientist
@seldon_io hello@seldon.io bit.ly/SeldonCoreSlack
Mapping a global network of Seldon
installs
Organisers of the UK’s largest applied
meetup focused on their AI/ML tools
- now over 2000 members. Supported
by Google.
Organic traction and
a global community.
● Over 120,000 installs (Docker Hub pulls) since Dec ‘17.
● Community across 90 countries and across industries.
● 21% MoM growth in clusters, 138% MoM growth in
nodes.
● 98% growth in nodes per cluster is an indicator that people
are using it for more demanding workloads.
bit.ly/SeldonCoreSlack
Seldon serves the world’s largest companies in
technology and financial services.
Applied data science project followed by managed service.
Enterprise Sales
- Recommend products
and supporting
documentation to
sales reps.
- Increase performance
of sales reps and
campaigns.
1% increase = £52m
revenue.
Credit Risk
- Reduce credit default
amongst UK Card
customers.
- Support the customer
before they miss
payments.
- Aiming to reduce
default rate by 2%.
FX Trading
- Identify which way
currency markets
are likely to move
within a short
timeframe.
- 5% uplift over
baseline model
worth estimate £3m
/ month.
Churn Prediction
- Improve customer
retention by
identifying customers
likely to cancel.
- Aiming to increase
accuracy of churn
prediction by 10%.
NA Bank
@seldon_io
4th Industrial
Revolution
Source: Notes from the AI frontier: Applications and value of deep learning - McKinsey April 2018 - https://mck.co/2I5tMld
A Small Number of Machine Learning Techniques work across
many use cases and industries.
Source: Notes from the AI frontier: Applications and value of deep learning - McKinsey April 2018 - https://mck.co/2I5tMld
Deep learning and Reinforcement learning deliver 62%
incremental value on average.
High value ML use cases
“$20.2bn machine learning budget in banking in 2018.”
McKinsey 2018
Fraud Detection Compliance & Risk Capital Markets Customer
Experience
Customer
Engagement
Identify fraudulent
behaviour
● First and third
party
● Identify bad
actors
● KYC
● Outlier detection
Reduce risks and
streamline reporting
● Audit trails
● Early warning and
response to cyber
breach
● Automate risk
controls
AI in the investment
sector
● Fundamental and
technical trading
strategies
● Market
predictions
● FX, equities and
derivatives
Identifying patterns of
behaviour
● Product
recommendation
● Customer
retention and
churn prediction
● Customer journey
Customized and intelligent
products & services
● Chatbots & virtual
agents
● Task management
● CRM
● Personalisation
Finance + tech
niche skill
sets
Low latency & high
data volumes
Integration with
legacy ecosystem
Security & data
governance
Regulatory
requirements
Auditability &
provenance
6 Machine Learning Trends Seldon observe
Finance + tech
niche skillsets
Low latency & high
data volumes
Integration with
legacy ecosystem
Security & data
governance
Regulatory
requirements
Auditability &
provenance
6 Machine Learning Trends in Financial Services
Evolving Standards
R Regulatory compliance a group effort.
ML without a ‘human in the loop’ will require
Explainable AI, or ‘XAI’
Expect to see compliance teams adopt ML
Possible driver of M&A within the banking
community
Finance + tech
niche skillsets
Low latency & high
data volumes
Integration with
legacy ecosystem
Security & data
governance
Regulatory
requirements
Auditability &
provenance
6 Machine Learning Trends in Financial Services
Data management
● R Transparency of data governance
Regulate the Algo - ‘Play the ball, not the man’
Cloud portability - *Euro bank example of conflict
Vital nature of successful Data strategies -
"We don’t have better algorithms, we just have more
data."
Peter Norvig, Google's director of research
Finance + tech
niche skillsets
Low latency & high
data volumes
Integration with
legacy ecosystem
Security & data
governance
Auditability &
provenance
6 Machine Learning Trends in Financial Services
Security
● R As Cloud becomes standard, data & training will
become increasingly separate
Initiatives like the CNCF* will ally with traditional
regulatory bodies
Models will be a hybrid of open (Risk, KYC) and
proprietary (Trading, Fraud)
*Cloud Native Computing Foundation https://www.cncf.io
Finance + tech
niche skillsets
Low latency & high
data volumes
Integration with
legacy ecosystem
Security & data
governance
Auditability &
provenance
6 Machine Learning Trends in Financial Services
Citizen ‘Data Scientist’
$120,000 - Data Scientist annual salary*
Best tool for the job - commoditization of ML frameworks
ForwardLane seeing portfolios of >200 under
management
Curation will be the key skillset
*Glassdoor Salary Estimates FSI
Finance + tech
niche skillsets
Low latency & high
data volumes
Integration with
legacy ecosystem
Security & data
governance
Regulatory
requirements
Auditability &
provenance
6 Machine Learning Trends in Financial Services
Speed to market
Cost & speed of compute is your new competitive
advantage
New Revenue models - Can you extract meaning from
your data?
Model iteration needs to be rapid and optimal
Finance + tech
niche skillsets
Low latency & high
data volumes
Integration with
legacy ecosystem
Security & data
governance
Regulatory
requirements
Auditability &
provenance
6 Machine Learning Trends in Financial Services
Legacy tech
Key value of ‘Challenger Bank’ community
Growth in outsourced banking engine
New IT landscape demands ‘plug & play’ architecture
Open Source adoption to escalate
2018 Market Analysis
Machine Learning Deployment
● 25000 banks forecasted to spend $519bn
on IT in 2018 (Gartner)
● 26% early adopters of ML spent 15% of
their IT budget on ML
● $20.24bn ML budget in banking 2018
● 52% initial and broad ML implementation
● 71% Kubernetes adoption in
orchestration
● $7.47bn current ML budget for
Kubernetes users in banking
Seldon Core
Open platform for deploying
machine learning models
Seldon Focus
Seldon Core
Building
a
Model
Serving OptimizationMonitoringRoll-out
Data
Ingestion
Data
Analysis
Data
Transform
-ation
Data
Validation
Data
Splitting
Model
Validation
Trainer
Training
At Scale
Logging
Goal: Help Business succeed with Data Science
Data Scientist
● Analyzes the data
● Builds the predictive model
● Optimizes the model
DevOps Engineer
● Manages infrastructure
● Monitors the model in
production
● First response on issues
Business Manager
● Decides the project goals
● Defines business KPIs
● Evaluates ROI
● Provides Approval/Audits
Clive Cox
CTO, Seldon
Seldon Deploy
UI, Collaboration, Control, Audit
MAB
(Multi-Arm Bandits)
Outlier Detection Explanation
Seldon Core
(ML Control Plane)
80% of enterprises are hybrid or multi-cloud.
Over half use containers, of which 75% use Kubernetes.
Seldon Technology Stack
Cloud Native Tools : e.g., Ambassador, Argo, Istio
Bias Detection,
Concept Drift
Seldon Core : ML Tool Agnostic
Use any
ML Tool
Dockerise REST and gRPC
Handle
Seldon APIs
Deploy!
Deploy!
Seldon Core : ML Tool Agnostic
Any Language
Current wrappers incl:
● Python
● R
● Java
● NodeJS
Any ML Library
Current examples incl:
● SKLearn
● TensorFlow
● PyTorch
● H2O
Any ML Inference Engine
Current examples incl:
● Seldon wrapped inference code
● NVIDIA TensorRT Server
● TensorFlow Serving
● Intel nGraph
Title
Type Here Type Here Type Here Type Here
Seldon Core Wrappers : Source-to-Image
https://github.com/openshift/source-to-image
from sklearn.externals import joblib
class IrisClassifier(object):
def __init__(self):
self.model = joblib.load('/mnt/model/IrisClassifier.sav')
def predict(self,X,features_names):
return self.model.predict_proba(X)
User Source Code (Github/Local) Seldon Builder Images
seldonio/seldon-core-s2i-python2
seldonio/seldon-core-s2i-python3
seldonio/seldon-core-s2i-r
seldonio/seldon-core-s2i-java-build
seldonio/seldon-core-s2i-nodejs
● ./assemble
● ./run
● ./usage
Dependencies
S2I
User Image
Ready to deploy on seldon-core
#> s2i build .
Rich Processing Components
● Routing requests
○ AB Tests
○ Multi-Armed Bandit
● Transformations
○ Feature Normalization
○ Ensembles results
● Metrics
○ Concept drift
○ Outlier detection
Seldon Core : Powerful Inference Graphs
Flexible
● Custom
○ Build your own
○ 3rd Party
● Dynamic
○ Change graph at inference
time
● Pluggable
○ Reuse components in
different inference graphs
Title
Type Here Type Here Type Here Type Here
Seldon Core Inference Graphs
Seldon/3rd party
component
Model C
Model A
Feature
Transformation
Client component
API
(REST, gRPC)
Model B
A/B Test
Multi Armed
Bandit
Direct traffic to
the most optimal
model
Outlier
Detection
Key features to
identify outlier
anomalies (Fraud, KYC)
Explanation
Why is the model doing
what it’s doing?
Title
Type Here Type Here Type Here Type Here
Seldon Core Example Inference Graph
Seldon/3rd party
component
Tensorflow
model served
via NVIDIA
TensorRT Server
ONNX model
served via
Intel nGraph
Feature
Transformation in
Java
Client component
API
(REST, gRPC)
R Model
A/B Test
Multi Armed
Bandit
(e-greedy,python)
Outlier
Detection
Custom Router
using business
logic
Model Explanation
For example, a machine learning model flags a bank transaction as fraudulent;
it becomes necessary to explain what factors contributed to the decision.
Explaining complex "black box" models is a key problem.
Understanding why a model output a given prediction can….
1. Provide insight into the model
behaviour. Guide decision making
processes.
2. Facilitate compliance with
regulation.
Lime
● Locally interpretable
● Suited for images and text
Representation erasure
● Suited for run time explanations
● Return features importance for any
“black box” model
● Based on how much the model
prediction will change when then
input features are changed
Lime2
● Updated version of Lime
Title
Type Here Type Here Type Here Type Here
Multi-Armed Bandits
Model C
Model AAPI
Model B
A/B Test
Multi Armed
Bandit
Direct traffic to
the most optimal
model
● Deploy several models in parallel
● Optimize between models at inference time
● Generalizes A/B testing
● Exploration vs Exploitation
○ ε-greedy
○ Thompson Sampling
● State dependency
○ Contextual bandits
● Outlier Detection
○ Identify data anomalies
○ Measure the distance of an observation to the center of the distribution
○ Online learning, starts without knowledge of the feature distribution
● Concept Drift
○ Change in the relationship between input and output leads to lower prediction accuracy
○ Detection of drift allows to adjust the predictive models in time
● Bias Detection
○ Human bias in the data like gender bias or machine bias leads to biased predictions
○ Neutralizing bias avoids pitfalls of human decision making
Monitoring Machine Learning Models
Seldon Core : Production Deployment Options
Update Inference Graphs
● Rolling
● Canary
● Blue-Green*
● Shadow*
Resource Control
● GPUs, CPUs, Memory
● Data Volume Attachment
● Sidecar containers
○ DBs, Other Business logic
● Separate k8s deployments for
parts of graph
* roadmap
Example Seldon Deployment Manifest (Kubernetes Custom Resource)
Graph Definition
Pod Specification
Replicas
List of predictors
Title
Type Here Type Here Type Here Type Here
1. Package
Create REST or gRPC
dockerized microservice
2. Describe Deployment
Create/update Kubernetes
resource manifest for
deployment graph
3. Deploy
Manage and analyze the
performance of live deployments
Seldon Deployment Workflow
Title
Type Here Type Here Type Here Type Here
Get Started with Seldon Core
1. Install
a. https://github.com/SeldonIO/seldon-core
b. Helm Charts or Ksonnet Registry
c. Via GCP MarketPlace
d. Via Kubeflow
e. Via IBM FfDL
2. Run example charts
a. Helm :
https://github.com/SeldonIO/seldon-core/blob/master/notebooks/helm
_examples.ipynb
b. Ksonnet:
https://github.com/SeldonIO/seldon-core/blob/master/notebooks/kson
net_examples.ipynb
c. Provides example graphs - models, AB tests, multi-armed bandits,
Outlier detections
3. Customize to your models
a. Wrap components using S2i
b. Create your own graphs
Seldon Deploy
Machine Learning Deployment
for Data Science Teams.
Development in progress
Pilots Q4 2018, launch early 2019
>500 companies applied for beta
● Modern UX/UI for model management
● Manage multiple Seldon Core clusters
● Team workflows, approvals and audit trails
● Advanced experiments and CI/CD (GitOps)
● Explanations and compliance (GDPR)
Thank You.
Please get in touch with any further questions.
@seldon_io
hello@seldon.io
http://bit.ly/SeldonCoreSlack
Title
Type Here Type Here Type Here Type Here
Seldon Core Architecture
Data scientists,
engineers and
managers
Deployment Controller
(kubectl, CI/CD, Seldon Deploy)
Business
Applications
Pluggable
Authentication
REST API or gRPC
Kubernetes clusters
running Seldon Core
Service
Orchestrator
Kubernetes
API
Operator
1. N deployment
graphs
Reverse Proxy
(Ambassador)
Public docker
registry
Client docker
registry
Seldon docker
registry

Más contenido relacionado

La actualidad más candente

MLFlow: Platform for Complete Machine Learning Lifecycle
MLFlow: Platform for Complete Machine Learning Lifecycle MLFlow: Platform for Complete Machine Learning Lifecycle
MLFlow: Platform for Complete Machine Learning Lifecycle
Databricks
 
How to Utilize MLflow and Kubernetes to Build an Enterprise ML Platform
How to Utilize MLflow and Kubernetes to Build an Enterprise ML PlatformHow to Utilize MLflow and Kubernetes to Build an Enterprise ML Platform
How to Utilize MLflow and Kubernetes to Build an Enterprise ML Platform
Databricks
 

La actualidad más candente (20)

MLFlow: Platform for Complete Machine Learning Lifecycle
MLFlow: Platform for Complete Machine Learning Lifecycle MLFlow: Platform for Complete Machine Learning Lifecycle
MLFlow: Platform for Complete Machine Learning Lifecycle
 
Generative AI, WiDS 2023.pptx
Generative AI, WiDS 2023.pptxGenerative AI, WiDS 2023.pptx
Generative AI, WiDS 2023.pptx
 
MLOps Using MLflow
MLOps Using MLflowMLOps Using MLflow
MLOps Using MLflow
 
Vector databases and neural search
Vector databases and neural searchVector databases and neural search
Vector databases and neural search
 
Kubeflow
KubeflowKubeflow
Kubeflow
 
Ml ops intro session
Ml ops   intro sessionMl ops   intro session
Ml ops intro session
 
NVIDIA @ AI FEST
NVIDIA @ AI FESTNVIDIA @ AI FEST
NVIDIA @ AI FEST
 
Importance of ML Reproducibility & Applications with MLfLow
Importance of ML Reproducibility & Applications with MLfLowImportance of ML Reproducibility & Applications with MLfLow
Importance of ML Reproducibility & Applications with MLfLow
 
RESTful Machine Learning with Flask and TensorFlow Serving - Carlo Mazzaferro
RESTful Machine Learning with Flask and TensorFlow Serving - Carlo MazzaferroRESTful Machine Learning with Flask and TensorFlow Serving - Carlo Mazzaferro
RESTful Machine Learning with Flask and TensorFlow Serving - Carlo Mazzaferro
 
MLOps.pptx
MLOps.pptxMLOps.pptx
MLOps.pptx
 
Productionalizing Models through CI/CD Design with MLflow
Productionalizing Models through CI/CD Design with MLflowProductionalizing Models through CI/CD Design with MLflow
Productionalizing Models through CI/CD Design with MLflow
 
How to Utilize MLflow and Kubernetes to Build an Enterprise ML Platform
How to Utilize MLflow and Kubernetes to Build an Enterprise ML PlatformHow to Utilize MLflow and Kubernetes to Build an Enterprise ML Platform
How to Utilize MLflow and Kubernetes to Build an Enterprise ML Platform
 
Seamless MLOps with Seldon and MLflow
Seamless MLOps with Seldon and MLflowSeamless MLOps with Seldon and MLflow
Seamless MLOps with Seldon and MLflow
 
Machine Learning using Kubeflow and Kubernetes
Machine Learning using Kubeflow and KubernetesMachine Learning using Kubeflow and Kubernetes
Machine Learning using Kubeflow and Kubernetes
 
Unified Approach to Interpret Machine Learning Model: SHAP + LIME
Unified Approach to Interpret Machine Learning Model: SHAP + LIMEUnified Approach to Interpret Machine Learning Model: SHAP + LIME
Unified Approach to Interpret Machine Learning Model: SHAP + LIME
 
Introduction to MLflow
Introduction to MLflowIntroduction to MLflow
Introduction to MLflow
 
Omniverse for the Metaverse
Omniverse for the MetaverseOmniverse for the Metaverse
Omniverse for the Metaverse
 
How to deploy Apache Spark in a multi-tenant, on-premises environment
How to deploy Apache Spark in a multi-tenant, on-premises environmentHow to deploy Apache Spark in a multi-tenant, on-premises environment
How to deploy Apache Spark in a multi-tenant, on-premises environment
 
Mlflow with databricks
Mlflow with databricksMlflow with databricks
Mlflow with databricks
 
Airflow Best Practises & Roadmap to Airflow 2.0
Airflow Best Practises & Roadmap to Airflow 2.0Airflow Best Practises & Roadmap to Airflow 2.0
Airflow Best Practises & Roadmap to Airflow 2.0
 

Similar a Seldon: Deploying Models at Scale

The Data Platform for Today’s Intelligent Applications
The Data Platform for Today’s Intelligent ApplicationsThe Data Platform for Today’s Intelligent Applications
The Data Platform for Today’s Intelligent Applications
Neo4j
 
Customer Presentation - IBM Cloud Pak for Data Overview (Level 100).PPTX
Customer Presentation - IBM Cloud Pak for Data Overview (Level 100).PPTXCustomer Presentation - IBM Cloud Pak for Data Overview (Level 100).PPTX
Customer Presentation - IBM Cloud Pak for Data Overview (Level 100).PPTX
tsigitnist02
 

Similar a Seldon: Deploying Models at Scale (20)

Top 10 Most Demand IT Certifications Course in 2020 - MildainTrainings
Top 10 Most Demand IT Certifications Course in 2020 - MildainTrainingsTop 10 Most Demand IT Certifications Course in 2020 - MildainTrainings
Top 10 Most Demand IT Certifications Course in 2020 - MildainTrainings
 
Gartner: Top 10 Technology Trends 2015
Gartner: Top 10 Technology Trends 2015Gartner: Top 10 Technology Trends 2015
Gartner: Top 10 Technology Trends 2015
 
Secure, Strengthen, Automate, and Scale Modern Workloads with Red Hat & NGINX
Secure, Strengthen, Automate, and Scale Modern Workloads with Red Hat & NGINXSecure, Strengthen, Automate, and Scale Modern Workloads with Red Hat & NGINX
Secure, Strengthen, Automate, and Scale Modern Workloads with Red Hat & NGINX
 
Accelerate ML Deployment with H2O Driverless AI on AWS
Accelerate ML Deployment with H2O Driverless AI on AWSAccelerate ML Deployment with H2O Driverless AI on AWS
Accelerate ML Deployment with H2O Driverless AI on AWS
 
The Data Platform for Today’s Intelligent Applications
The Data Platform for Today’s Intelligent ApplicationsThe Data Platform for Today’s Intelligent Applications
The Data Platform for Today’s Intelligent Applications
 
Generative AI - The New Reality: How Key Players Are Progressing
Generative AI - The New Reality: How Key Players Are Progressing Generative AI - The New Reality: How Key Players Are Progressing
Generative AI - The New Reality: How Key Players Are Progressing
 
Infrastructure Solutions for Deploying AI/ML/DL Workloads at Scale
Infrastructure Solutions for Deploying AI/ML/DL Workloads at ScaleInfrastructure Solutions for Deploying AI/ML/DL Workloads at Scale
Infrastructure Solutions for Deploying AI/ML/DL Workloads at Scale
 
A Journey Through The Far Side Of Data Science
A Journey Through The Far Side Of Data ScienceA Journey Through The Far Side Of Data Science
A Journey Through The Far Side Of Data Science
 
Introducción al Aprendizaje Automatico con H2O-3 (1)
Introducción al Aprendizaje Automatico con H2O-3 (1)Introducción al Aprendizaje Automatico con H2O-3 (1)
Introducción al Aprendizaje Automatico con H2O-3 (1)
 
Artificial Intelligence As a Service
Artificial Intelligence As a ServiceArtificial Intelligence As a Service
Artificial Intelligence As a Service
 
Customer Presentation - IBM Cloud Pak for Data Overview (Level 100).PPTX
Customer Presentation - IBM Cloud Pak for Data Overview (Level 100).PPTXCustomer Presentation - IBM Cloud Pak for Data Overview (Level 100).PPTX
Customer Presentation - IBM Cloud Pak for Data Overview (Level 100).PPTX
 
Vertex Perspectives | AI-optimized Chipsets | Part I
Vertex Perspectives | AI-optimized Chipsets | Part IVertex Perspectives | AI-optimized Chipsets | Part I
Vertex Perspectives | AI-optimized Chipsets | Part I
 
Vertex perspectives ai optimized chipsets (part i)
Vertex perspectives   ai optimized chipsets (part i)Vertex perspectives   ai optimized chipsets (part i)
Vertex perspectives ai optimized chipsets (part i)
 
Introduction to Neo4j
Introduction to Neo4jIntroduction to Neo4j
Introduction to Neo4j
 
The Data Platform for Today's Intelligent Applications.pdf
The Data Platform for Today's Intelligent Applications.pdfThe Data Platform for Today's Intelligent Applications.pdf
The Data Platform for Today's Intelligent Applications.pdf
 
ADV Slides: How to Improve Your Analytic Data Architecture Maturity
ADV Slides: How to Improve Your Analytic Data Architecture MaturityADV Slides: How to Improve Your Analytic Data Architecture Maturity
ADV Slides: How to Improve Your Analytic Data Architecture Maturity
 
Dell Digital Transformation Through AI and Data Analytics Webinar
Dell Digital Transformation Through AI and  Data Analytics WebinarDell Digital Transformation Through AI and  Data Analytics Webinar
Dell Digital Transformation Through AI and Data Analytics Webinar
 
Dell AI Telecom Webinar
Dell AI Telecom WebinarDell AI Telecom Webinar
Dell AI Telecom Webinar
 
Building a reliable and scalable IoT platform with MongoDB and HiveMQ
Building a reliable and scalable IoT platform with MongoDB and HiveMQBuilding a reliable and scalable IoT platform with MongoDB and HiveMQ
Building a reliable and scalable IoT platform with MongoDB and HiveMQ
 
AI Overview and Capabilities
AI Overview and CapabilitiesAI Overview and Capabilities
AI Overview and Capabilities
 

Más de Seldon

TensorFlow London 18: Dr Alastair Moore, Towards the use of Graphical Models ...
TensorFlow London 18: Dr Alastair Moore, Towards the use of Graphical Models ...TensorFlow London 18: Dr Alastair Moore, Towards the use of Graphical Models ...
TensorFlow London 18: Dr Alastair Moore, Towards the use of Graphical Models ...
Seldon
 
TensorFlow London 15: Find bugs in the herd with debuggable TensorFlow code
TensorFlow London 15: Find bugs in the herd with debuggable TensorFlow code TensorFlow London 15: Find bugs in the herd with debuggable TensorFlow code
TensorFlow London 15: Find bugs in the herd with debuggable TensorFlow code
Seldon
 
Tensorflow London 13: Barbara Fusinska 'Hassle Free, Scalable, Machine Learni...
Tensorflow London 13: Barbara Fusinska 'Hassle Free, Scalable, Machine Learni...Tensorflow London 13: Barbara Fusinska 'Hassle Free, Scalable, Machine Learni...
Tensorflow London 13: Barbara Fusinska 'Hassle Free, Scalable, Machine Learni...
Seldon
 
Tensorflow London 13: Zbigniew Wojna 'Deep Learning for Big Scale 2D Imagery'
Tensorflow London 13: Zbigniew Wojna 'Deep Learning for Big Scale 2D Imagery'Tensorflow London 13: Zbigniew Wojna 'Deep Learning for Big Scale 2D Imagery'
Tensorflow London 13: Zbigniew Wojna 'Deep Learning for Big Scale 2D Imagery'
Seldon
 

Más de Seldon (20)

CD4ML and the challenges of testing and quality in ML systems
CD4ML and the challenges of testing and quality in ML systemsCD4ML and the challenges of testing and quality in ML systems
CD4ML and the challenges of testing and quality in ML systems
 
TensorFlow London: Cutting edge generative models
TensorFlow London: Cutting edge generative modelsTensorFlow London: Cutting edge generative models
TensorFlow London: Cutting edge generative models
 
Tensorflow London: Tensorflow and Graph Recommender Networks by Yaz Santissi
Tensorflow London: Tensorflow and Graph Recommender Networks by Yaz SantissiTensorflow London: Tensorflow and Graph Recommender Networks by Yaz Santissi
Tensorflow London: Tensorflow and Graph Recommender Networks by Yaz Santissi
 
TensorFlow London: Progressive Growing of GANs for increased stability, quali...
TensorFlow London: Progressive Growing of GANs for increased stability, quali...TensorFlow London: Progressive Growing of GANs for increased stability, quali...
TensorFlow London: Progressive Growing of GANs for increased stability, quali...
 
TensorFlow London 18: Dr Daniel Martinho-Corbishley, From science to startups...
TensorFlow London 18: Dr Daniel Martinho-Corbishley, From science to startups...TensorFlow London 18: Dr Daniel Martinho-Corbishley, From science to startups...
TensorFlow London 18: Dr Daniel Martinho-Corbishley, From science to startups...
 
TensorFlow London 18: Dr Alastair Moore, Towards the use of Graphical Models ...
TensorFlow London 18: Dr Alastair Moore, Towards the use of Graphical Models ...TensorFlow London 18: Dr Alastair Moore, Towards the use of Graphical Models ...
TensorFlow London 18: Dr Alastair Moore, Towards the use of Graphical Models ...
 
TensorFlow London 17: How NASA Frontier Development Lab scientists use AI to ...
TensorFlow London 17: How NASA Frontier Development Lab scientists use AI to ...TensorFlow London 17: How NASA Frontier Development Lab scientists use AI to ...
TensorFlow London 17: How NASA Frontier Development Lab scientists use AI to ...
 
TensorFlow London 17: Practical Reinforcement Learning with OpenAI
TensorFlow London 17: Practical Reinforcement Learning with OpenAITensorFlow London 17: Practical Reinforcement Learning with OpenAI
TensorFlow London 17: Practical Reinforcement Learning with OpenAI
 
TensorFlow 16: Multimodal Sentiment Analysis with TensorFlow
TensorFlow 16: Multimodal Sentiment Analysis with TensorFlow TensorFlow 16: Multimodal Sentiment Analysis with TensorFlow
TensorFlow 16: Multimodal Sentiment Analysis with TensorFlow
 
TensorFlow 16: Building a Data Science Platform
TensorFlow 16: Building a Data Science Platform TensorFlow 16: Building a Data Science Platform
TensorFlow 16: Building a Data Science Platform
 
Ai in financial services
Ai in financial servicesAi in financial services
Ai in financial services
 
TensorFlow London 15: Find bugs in the herd with debuggable TensorFlow code
TensorFlow London 15: Find bugs in the herd with debuggable TensorFlow code TensorFlow London 15: Find bugs in the herd with debuggable TensorFlow code
TensorFlow London 15: Find bugs in the herd with debuggable TensorFlow code
 
TensorFlow London 14: Ben Hall 'Machine Learning Workloads with Kubernetes an...
TensorFlow London 14: Ben Hall 'Machine Learning Workloads with Kubernetes an...TensorFlow London 14: Ben Hall 'Machine Learning Workloads with Kubernetes an...
TensorFlow London 14: Ben Hall 'Machine Learning Workloads with Kubernetes an...
 
Tensorflow London 13: Barbara Fusinska 'Hassle Free, Scalable, Machine Learni...
Tensorflow London 13: Barbara Fusinska 'Hassle Free, Scalable, Machine Learni...Tensorflow London 13: Barbara Fusinska 'Hassle Free, Scalable, Machine Learni...
Tensorflow London 13: Barbara Fusinska 'Hassle Free, Scalable, Machine Learni...
 
Tensorflow London 13: Zbigniew Wojna 'Deep Learning for Big Scale 2D Imagery'
Tensorflow London 13: Zbigniew Wojna 'Deep Learning for Big Scale 2D Imagery'Tensorflow London 13: Zbigniew Wojna 'Deep Learning for Big Scale 2D Imagery'
Tensorflow London 13: Zbigniew Wojna 'Deep Learning for Big Scale 2D Imagery'
 
TensorFlow London 11: Pierre Harvey Richemond 'Trends and Developments in Rei...
TensorFlow London 11: Pierre Harvey Richemond 'Trends and Developments in Rei...TensorFlow London 11: Pierre Harvey Richemond 'Trends and Developments in Rei...
TensorFlow London 11: Pierre Harvey Richemond 'Trends and Developments in Rei...
 
TensorFlow London 11: Gema Parreno 'Use Cases of TensorFlow'
TensorFlow London 11: Gema Parreno 'Use Cases of TensorFlow'TensorFlow London 11: Gema Parreno 'Use Cases of TensorFlow'
TensorFlow London 11: Gema Parreno 'Use Cases of TensorFlow'
 
Tensorflow London 12: Marcel Horstmann and Laurent Decamp 'Using TensorFlow t...
Tensorflow London 12: Marcel Horstmann and Laurent Decamp 'Using TensorFlow t...Tensorflow London 12: Marcel Horstmann and Laurent Decamp 'Using TensorFlow t...
Tensorflow London 12: Marcel Horstmann and Laurent Decamp 'Using TensorFlow t...
 
TensorFlow London 12: Oliver Gindele 'Recommender systems in Tensorflow'
TensorFlow London 12: Oliver Gindele 'Recommender systems in Tensorflow'TensorFlow London 12: Oliver Gindele 'Recommender systems in Tensorflow'
TensorFlow London 12: Oliver Gindele 'Recommender systems in Tensorflow'
 
TensorFlow London 13.09.17 Ilya Dmitrichenko
TensorFlow London 13.09.17 Ilya DmitrichenkoTensorFlow London 13.09.17 Ilya Dmitrichenko
TensorFlow London 13.09.17 Ilya Dmitrichenko
 

Último

%+27788225528 love spells in new york Psychic Readings, Attraction spells,Bri...
%+27788225528 love spells in new york Psychic Readings, Attraction spells,Bri...%+27788225528 love spells in new york Psychic Readings, Attraction spells,Bri...
%+27788225528 love spells in new york Psychic Readings, Attraction spells,Bri...
masabamasaba
 
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...
%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...
%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...
masabamasaba
 
The title is not connected to what is inside
The title is not connected to what is insideThe title is not connected to what is inside
The title is not connected to what is inside
shinachiaurasa2
 
%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...
%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...
%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...
masabamasaba
 

Último (20)

WSO2Con2024 - Enabling Transactional System's Exponential Growth With Simplicity
WSO2Con2024 - Enabling Transactional System's Exponential Growth With SimplicityWSO2Con2024 - Enabling Transactional System's Exponential Growth With Simplicity
WSO2Con2024 - Enabling Transactional System's Exponential Growth With Simplicity
 
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
 
VTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learnVTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learn
 
%in kempton park+277-882-255-28 abortion pills for sale in kempton park
%in kempton park+277-882-255-28 abortion pills for sale in kempton park %in kempton park+277-882-255-28 abortion pills for sale in kempton park
%in kempton park+277-882-255-28 abortion pills for sale in kempton park
 
AI & Machine Learning Presentation Template
AI & Machine Learning Presentation TemplateAI & Machine Learning Presentation Template
AI & Machine Learning Presentation Template
 
MarTech Trend 2024 Book : Marketing Technology Trends (2024 Edition) How Data...
MarTech Trend 2024 Book : Marketing Technology Trends (2024 Edition) How Data...MarTech Trend 2024 Book : Marketing Technology Trends (2024 Edition) How Data...
MarTech Trend 2024 Book : Marketing Technology Trends (2024 Edition) How Data...
 
%+27788225528 love spells in new york Psychic Readings, Attraction spells,Bri...
%+27788225528 love spells in new york Psychic Readings, Attraction spells,Bri...%+27788225528 love spells in new york Psychic Readings, Attraction spells,Bri...
%+27788225528 love spells in new york Psychic Readings, Attraction spells,Bri...
 
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
 
%in Harare+277-882-255-28 abortion pills for sale in Harare
%in Harare+277-882-255-28 abortion pills for sale in Harare%in Harare+277-882-255-28 abortion pills for sale in Harare
%in Harare+277-882-255-28 abortion pills for sale in Harare
 
%in Soweto+277-882-255-28 abortion pills for sale in soweto
%in Soweto+277-882-255-28 abortion pills for sale in soweto%in Soweto+277-882-255-28 abortion pills for sale in soweto
%in Soweto+277-882-255-28 abortion pills for sale in soweto
 
%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...
%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...
%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...
 
%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisa%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisa
 
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
 
Introducing Microsoft’s new Enterprise Work Management (EWM) Solution
Introducing Microsoft’s new Enterprise Work Management (EWM) SolutionIntroducing Microsoft’s new Enterprise Work Management (EWM) Solution
Introducing Microsoft’s new Enterprise Work Management (EWM) Solution
 
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
 
The title is not connected to what is inside
The title is not connected to what is insideThe title is not connected to what is inside
The title is not connected to what is inside
 
%in ivory park+277-882-255-28 abortion pills for sale in ivory park
%in ivory park+277-882-255-28 abortion pills for sale in ivory park %in ivory park+277-882-255-28 abortion pills for sale in ivory park
%in ivory park+277-882-255-28 abortion pills for sale in ivory park
 
WSO2CON 2024 - Cloud Native Middleware: Domain-Driven Design, Cell-Based Arch...
WSO2CON 2024 - Cloud Native Middleware: Domain-Driven Design, Cell-Based Arch...WSO2CON 2024 - Cloud Native Middleware: Domain-Driven Design, Cell-Based Arch...
WSO2CON 2024 - Cloud Native Middleware: Domain-Driven Design, Cell-Based Arch...
 
%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...
%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...
%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...
 
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...
 

Seldon: Deploying Models at Scale

  • 2. Machine Learning Deployment for Enterprise. O’Reilly AI for IBM: Deploying ML Models at Scale
  • 3. We help people shape the future by bringing machine learning deployment to life.
  • 4. Meet the Team. Alex Housley CEO & Founder Clive Cox PhD CTO Gurminder Sunner VP Engineering Lee Baker Commercial Director Giovanni Vacanti PhD Machine Learning Engineer Inga Veidmane Operations Manager Andrew Turner Sales Manager Janis Klaise PhD Data Scientist Arnaud Van Looveren Data Scientist @seldon_io hello@seldon.io bit.ly/SeldonCoreSlack
  • 5. Mapping a global network of Seldon installs Organisers of the UK’s largest applied meetup focused on their AI/ML tools - now over 2000 members. Supported by Google. Organic traction and a global community. ● Over 120,000 installs (Docker Hub pulls) since Dec ‘17. ● Community across 90 countries and across industries. ● 21% MoM growth in clusters, 138% MoM growth in nodes. ● 98% growth in nodes per cluster is an indicator that people are using it for more demanding workloads. bit.ly/SeldonCoreSlack
  • 6. Seldon serves the world’s largest companies in technology and financial services. Applied data science project followed by managed service. Enterprise Sales - Recommend products and supporting documentation to sales reps. - Increase performance of sales reps and campaigns. 1% increase = £52m revenue. Credit Risk - Reduce credit default amongst UK Card customers. - Support the customer before they miss payments. - Aiming to reduce default rate by 2%. FX Trading - Identify which way currency markets are likely to move within a short timeframe. - 5% uplift over baseline model worth estimate £3m / month. Churn Prediction - Improve customer retention by identifying customers likely to cancel. - Aiming to increase accuracy of churn prediction by 10%. NA Bank
  • 8. Source: Notes from the AI frontier: Applications and value of deep learning - McKinsey April 2018 - https://mck.co/2I5tMld A Small Number of Machine Learning Techniques work across many use cases and industries.
  • 9. Source: Notes from the AI frontier: Applications and value of deep learning - McKinsey April 2018 - https://mck.co/2I5tMld Deep learning and Reinforcement learning deliver 62% incremental value on average.
  • 10. High value ML use cases “$20.2bn machine learning budget in banking in 2018.” McKinsey 2018 Fraud Detection Compliance & Risk Capital Markets Customer Experience Customer Engagement Identify fraudulent behaviour ● First and third party ● Identify bad actors ● KYC ● Outlier detection Reduce risks and streamline reporting ● Audit trails ● Early warning and response to cyber breach ● Automate risk controls AI in the investment sector ● Fundamental and technical trading strategies ● Market predictions ● FX, equities and derivatives Identifying patterns of behaviour ● Product recommendation ● Customer retention and churn prediction ● Customer journey Customized and intelligent products & services ● Chatbots & virtual agents ● Task management ● CRM ● Personalisation
  • 11. Finance + tech niche skill sets Low latency & high data volumes Integration with legacy ecosystem Security & data governance Regulatory requirements Auditability & provenance 6 Machine Learning Trends Seldon observe
  • 12. Finance + tech niche skillsets Low latency & high data volumes Integration with legacy ecosystem Security & data governance Regulatory requirements Auditability & provenance 6 Machine Learning Trends in Financial Services Evolving Standards R Regulatory compliance a group effort. ML without a ‘human in the loop’ will require Explainable AI, or ‘XAI’ Expect to see compliance teams adopt ML Possible driver of M&A within the banking community
  • 13. Finance + tech niche skillsets Low latency & high data volumes Integration with legacy ecosystem Security & data governance Regulatory requirements Auditability & provenance 6 Machine Learning Trends in Financial Services Data management ● R Transparency of data governance Regulate the Algo - ‘Play the ball, not the man’ Cloud portability - *Euro bank example of conflict Vital nature of successful Data strategies - "We don’t have better algorithms, we just have more data." Peter Norvig, Google's director of research
  • 14. Finance + tech niche skillsets Low latency & high data volumes Integration with legacy ecosystem Security & data governance Auditability & provenance 6 Machine Learning Trends in Financial Services Security ● R As Cloud becomes standard, data & training will become increasingly separate Initiatives like the CNCF* will ally with traditional regulatory bodies Models will be a hybrid of open (Risk, KYC) and proprietary (Trading, Fraud) *Cloud Native Computing Foundation https://www.cncf.io
  • 15. Finance + tech niche skillsets Low latency & high data volumes Integration with legacy ecosystem Security & data governance Auditability & provenance 6 Machine Learning Trends in Financial Services Citizen ‘Data Scientist’ $120,000 - Data Scientist annual salary* Best tool for the job - commoditization of ML frameworks ForwardLane seeing portfolios of >200 under management Curation will be the key skillset *Glassdoor Salary Estimates FSI
  • 16. Finance + tech niche skillsets Low latency & high data volumes Integration with legacy ecosystem Security & data governance Regulatory requirements Auditability & provenance 6 Machine Learning Trends in Financial Services Speed to market Cost & speed of compute is your new competitive advantage New Revenue models - Can you extract meaning from your data? Model iteration needs to be rapid and optimal
  • 17. Finance + tech niche skillsets Low latency & high data volumes Integration with legacy ecosystem Security & data governance Regulatory requirements Auditability & provenance 6 Machine Learning Trends in Financial Services Legacy tech Key value of ‘Challenger Bank’ community Growth in outsourced banking engine New IT landscape demands ‘plug & play’ architecture Open Source adoption to escalate
  • 18. 2018 Market Analysis Machine Learning Deployment ● 25000 banks forecasted to spend $519bn on IT in 2018 (Gartner) ● 26% early adopters of ML spent 15% of their IT budget on ML ● $20.24bn ML budget in banking 2018 ● 52% initial and broad ML implementation ● 71% Kubernetes adoption in orchestration ● $7.47bn current ML budget for Kubernetes users in banking
  • 19. Seldon Core Open platform for deploying machine learning models
  • 20. Seldon Focus Seldon Core Building a Model Serving OptimizationMonitoringRoll-out Data Ingestion Data Analysis Data Transform -ation Data Validation Data Splitting Model Validation Trainer Training At Scale Logging
  • 21. Goal: Help Business succeed with Data Science Data Scientist ● Analyzes the data ● Builds the predictive model ● Optimizes the model DevOps Engineer ● Manages infrastructure ● Monitors the model in production ● First response on issues Business Manager ● Decides the project goals ● Defines business KPIs ● Evaluates ROI ● Provides Approval/Audits
  • 23. Seldon Deploy UI, Collaboration, Control, Audit MAB (Multi-Arm Bandits) Outlier Detection Explanation Seldon Core (ML Control Plane) 80% of enterprises are hybrid or multi-cloud. Over half use containers, of which 75% use Kubernetes. Seldon Technology Stack Cloud Native Tools : e.g., Ambassador, Argo, Istio Bias Detection, Concept Drift
  • 24. Seldon Core : ML Tool Agnostic Use any ML Tool Dockerise REST and gRPC Handle Seldon APIs Deploy! Deploy!
  • 25. Seldon Core : ML Tool Agnostic Any Language Current wrappers incl: ● Python ● R ● Java ● NodeJS Any ML Library Current examples incl: ● SKLearn ● TensorFlow ● PyTorch ● H2O Any ML Inference Engine Current examples incl: ● Seldon wrapped inference code ● NVIDIA TensorRT Server ● TensorFlow Serving ● Intel nGraph
  • 26. Title Type Here Type Here Type Here Type Here Seldon Core Wrappers : Source-to-Image https://github.com/openshift/source-to-image from sklearn.externals import joblib class IrisClassifier(object): def __init__(self): self.model = joblib.load('/mnt/model/IrisClassifier.sav') def predict(self,X,features_names): return self.model.predict_proba(X) User Source Code (Github/Local) Seldon Builder Images seldonio/seldon-core-s2i-python2 seldonio/seldon-core-s2i-python3 seldonio/seldon-core-s2i-r seldonio/seldon-core-s2i-java-build seldonio/seldon-core-s2i-nodejs ● ./assemble ● ./run ● ./usage Dependencies S2I User Image Ready to deploy on seldon-core #> s2i build .
  • 27. Rich Processing Components ● Routing requests ○ AB Tests ○ Multi-Armed Bandit ● Transformations ○ Feature Normalization ○ Ensembles results ● Metrics ○ Concept drift ○ Outlier detection Seldon Core : Powerful Inference Graphs Flexible ● Custom ○ Build your own ○ 3rd Party ● Dynamic ○ Change graph at inference time ● Pluggable ○ Reuse components in different inference graphs
  • 28. Title Type Here Type Here Type Here Type Here Seldon Core Inference Graphs Seldon/3rd party component Model C Model A Feature Transformation Client component API (REST, gRPC) Model B A/B Test Multi Armed Bandit Direct traffic to the most optimal model Outlier Detection Key features to identify outlier anomalies (Fraud, KYC) Explanation Why is the model doing what it’s doing?
  • 29. Title Type Here Type Here Type Here Type Here Seldon Core Example Inference Graph Seldon/3rd party component Tensorflow model served via NVIDIA TensorRT Server ONNX model served via Intel nGraph Feature Transformation in Java Client component API (REST, gRPC) R Model A/B Test Multi Armed Bandit (e-greedy,python) Outlier Detection Custom Router using business logic
  • 30. Model Explanation For example, a machine learning model flags a bank transaction as fraudulent; it becomes necessary to explain what factors contributed to the decision. Explaining complex "black box" models is a key problem. Understanding why a model output a given prediction can…. 1. Provide insight into the model behaviour. Guide decision making processes. 2. Facilitate compliance with regulation. Lime ● Locally interpretable ● Suited for images and text Representation erasure ● Suited for run time explanations ● Return features importance for any “black box” model ● Based on how much the model prediction will change when then input features are changed Lime2 ● Updated version of Lime
  • 31. Title Type Here Type Here Type Here Type Here Multi-Armed Bandits Model C Model AAPI Model B A/B Test Multi Armed Bandit Direct traffic to the most optimal model ● Deploy several models in parallel ● Optimize between models at inference time ● Generalizes A/B testing ● Exploration vs Exploitation ○ ε-greedy ○ Thompson Sampling ● State dependency ○ Contextual bandits
  • 32. ● Outlier Detection ○ Identify data anomalies ○ Measure the distance of an observation to the center of the distribution ○ Online learning, starts without knowledge of the feature distribution ● Concept Drift ○ Change in the relationship between input and output leads to lower prediction accuracy ○ Detection of drift allows to adjust the predictive models in time ● Bias Detection ○ Human bias in the data like gender bias or machine bias leads to biased predictions ○ Neutralizing bias avoids pitfalls of human decision making Monitoring Machine Learning Models
  • 33. Seldon Core : Production Deployment Options Update Inference Graphs ● Rolling ● Canary ● Blue-Green* ● Shadow* Resource Control ● GPUs, CPUs, Memory ● Data Volume Attachment ● Sidecar containers ○ DBs, Other Business logic ● Separate k8s deployments for parts of graph * roadmap
  • 34. Example Seldon Deployment Manifest (Kubernetes Custom Resource) Graph Definition Pod Specification Replicas List of predictors
  • 35. Title Type Here Type Here Type Here Type Here 1. Package Create REST or gRPC dockerized microservice 2. Describe Deployment Create/update Kubernetes resource manifest for deployment graph 3. Deploy Manage and analyze the performance of live deployments Seldon Deployment Workflow
  • 36. Title Type Here Type Here Type Here Type Here Get Started with Seldon Core 1. Install a. https://github.com/SeldonIO/seldon-core b. Helm Charts or Ksonnet Registry c. Via GCP MarketPlace d. Via Kubeflow e. Via IBM FfDL 2. Run example charts a. Helm : https://github.com/SeldonIO/seldon-core/blob/master/notebooks/helm _examples.ipynb b. Ksonnet: https://github.com/SeldonIO/seldon-core/blob/master/notebooks/kson net_examples.ipynb c. Provides example graphs - models, AB tests, multi-armed bandits, Outlier detections 3. Customize to your models a. Wrap components using S2i b. Create your own graphs
  • 37. Seldon Deploy Machine Learning Deployment for Data Science Teams. Development in progress Pilots Q4 2018, launch early 2019 >500 companies applied for beta ● Modern UX/UI for model management ● Manage multiple Seldon Core clusters ● Team workflows, approvals and audit trails ● Advanced experiments and CI/CD (GitOps) ● Explanations and compliance (GDPR)
  • 38. Thank You. Please get in touch with any further questions. @seldon_io hello@seldon.io http://bit.ly/SeldonCoreSlack
  • 39. Title Type Here Type Here Type Here Type Here Seldon Core Architecture Data scientists, engineers and managers Deployment Controller (kubectl, CI/CD, Seldon Deploy) Business Applications Pluggable Authentication REST API or gRPC Kubernetes clusters running Seldon Core Service Orchestrator Kubernetes API Operator 1. N deployment graphs Reverse Proxy (Ambassador) Public docker registry Client docker registry Seldon docker registry