About

vlad.tomsa@microsoft.com

What differentiates today’s thriving organizations?

Data

Name

$2,600.45

$2,294.58

$1,003.30

$8,488.32

Amount Fraudulent

Smith

Potter

Peters

Adams

No

Yes

Yes

No

What’s the pattern for

fraudulent

transactions?

$2,600.45

$2,294.58

$1,003.30

$8,488.32

Name Amount Fraudulent

Smith

Potter

Peters

Adams

No

Yes

Yes

No

Where

Issued

Where

Used Age

$200.12

$3,250.11

$8,156.20

$7,475.11

Pali

Jones

Hanford

Marx

USA

USA

USA

FRA

AUS

USA

USA

UK

22

29

25

64

58

43

27

32

No

No

Yes

No

USA

RUS

RUS

USA

JAP

RUS

RUS

GER

$540.00

$7,475.11

Norse

Edson

USA

USA

27

20

No

Yes

RUS

RUS

What’s the

pattern for

fraudulent

transactions?

Machine learning

algorithm

Model

Application

Data

Contains

patternsFinds

patterns

Recognizes

patterns

Provides new data to

see if it matches

known patterns

Deploy

chosen

model

Chosen

Model

Apply

learning

algorithm

to data

Candidate

ModelPrepared

Data

Apply pre-

processing

to data

Iterate to find the

best model

Data

Preprocessing

Modules

Iterate until data

is ready

Preprocessing

Modules

Machine

Learning

AlgorithmsApplications

The goal:

Smarter

applications

Raw

Data

Raw

Data

Choose data

Candidate

Model

Raw

Data

Raw

Data

Prepared

Data

Apply pre-

processing

to data

Deploy

chosen

model

Apply

learning

algorithm

to data

Chosen

Model

ML Studio

Preprocessing

Modules

Machine

Learning

Algorithms

Data

Preprocessing

Modules

Azure ML

API

Applications

Machine Learning ScenariosEXAMPLE SOLUTIONS

Cortana Intelligence Suite

Cortana Intelligence SuiteTransform data into intelligent action

DataSources

Apps

Sensors & Devices

People

Data Intelligence

Cortana Intelligence

Action

Apps

Automated systems

Cortana Intelligence

Action

People

Automated Systems

Apps

Web

Mobile

Bots

Intelligence

Dashboards &

Visualizations

Cortana

Bot

Framework

Cognitive

Services

Power BI

Business

Scenarios

Information

Management

Event Hubs

Data Catalog

Data Factory

Machine Learning

and Analytics

HDInsight

(Hadoop and

Spark)

Stream Analytics

Intelligence

Data Lake

Analytics

Machine

Learning

Big Data Stores

SQL Data

Warehouse

Data Lake Store

Data Sources

Apps

Sensors and devices

Data

{ } DocumentDB

Conversations as a PlatformIntroducing the Bot Framework

Cortana Intelligence

Action

People

Automated Systems

Apps

Web

Mobile

Bots

Intelligence

Dashboards &

Visualizations

Cortana

Bot

Framework

Cognitive

Services

Power BI

Business

Scenarios

Information

Management

Event Hubs

Data Catalog

Data Factory

Machine Learning

and Analytics

HDInsight

(Hadoop and

Spark)

Stream Analytics

Intelligence

Data Lake

Analytics

Machine

Learning

Big Data Stores

SQL Data

Warehouse

Data Lake Store

Data Sources

Apps

Sensors and devices

Data

{ } DocumentDB

Why Microsoft Cognitive Services?

Easy Flexible Tested

Simple to add: just a few lines of code required

Roll your own with REST APIs

GET AKEY

Breadth of offerings helps you find the right API for your app

Integrate into the language and platform of your choice

Quality documentation, sample code, and community support

Built by experts in their field from Microsoft Research, Bing, and Azure Machine Learning

Microsoft Cognitive ServicesGive your apps a human side

Microsoft Cognitive ServicesGive your apps a human side

Cognitive Services API Collection

Cognitive Intelligence APIshttp://gallery.cortanaintelligence.com

Try it at: https://www.microsoft.com/cognitive-services/en-us/applications

LUIS

The problem

Language understanding in human-computer interaction is:

Technically challengingIt’s exceedingly difficult to enable a

computer to understand what a

person wants and to find the pieces

of information that are relevant to

their intent.

Costly to implementBuilding and maintaining machine

learning systems requires a large

investment of time, money and

engineering resources

Often domain specificIn the past, building your own

machine learned models often

required assistance of a team of

data scientists that would customize

the models to the specific domain.

A Microsoft Cognitive Service that provides developers with an easy way to create language models to allow applications to understand user commands.

Create your

own LU model

Train by providing

examples

Deploy to an HTTP

endpoint and

activate on any

device

Maintain model

with ease

Introducing Language Understanding Intelligence Service (LUIS)

LUIS Common Usage Scenarios

LUIS offers integration with Microsoft

Bot Framework and Slack, which

enables developers to build and

connect intelligent bots to interact

with users no matter which device

they are on or which technology they

are using

Chat bots

LUIS uses pre-built models from Bing

and Cortana which enable developers

to easily add personal assistant

functionalities to their apps.

Virtual assistance

LUIS has been used to build a wide

range of IoT applications ranging

from a simple voice activated lights

control to smart kitchen appliances,

smart vending machines, facial

recognition door, and many more

IoT experiences

LUIS Benefits

Expert:Leverages MSR

technology

LUIS leverages innovative AI technology from Microsoft Research.

Easy:Use simple UX editor to

create language

understanding models

Create models for your application to better understand intents like "turn on the lights", or entities such as "start a new jog/walk/hike/bikeride". Tune your model with in-depth performance visualizations.

Flexible:Activate models on any

device

Activate your language understanding models from your application on your phone, tablet, or any other device that has access to the Internet.

Fast: Add conversational

intelligence to your apps

in minutes

LUIS has a powerful dialog engine that enables you to maintain context, author and execute any dialog in just a few steps.

LUIS is designed to enable you to

quickly deploy an HTTP endpoint that

will take the sentences you send it

and interpret them in terms of the

intention they convey and the key

entities that are present.

After your endpoint has processed a

few dozen interactions, LUIS begins

active learning. LUIS examines all the

utterances that have been sent to it,

and calls to your attention the ones

that it would like you to label.

LUIS relies on the cutting-edge

technologies developed and

incubated directly by Microsoft

Research that have been tried and

tested with hundreds of internal and

external customers all over the globe.

In addition to allowing you to build

your own applications, LUIS also

provides selected models from the

Microsoft Cortana personal assistant

as a pre-built application.

It learns and adapts

It is fast and easy It is innovativeIt uses pre-built

applications

Why LUIS?

LUIS offers a set of user-friendly tools

that completely abstract technical

complexity and get you up and

running with just a few steps.

This breakthrough feature enables

LUIS to examine all the utterances

that have been sent to it, critique its

own work, and ask for any corrections

in order to continually improve

accuracy.

LUIS is able to fulfill actions that were

triggered through a set of channels

(HTTP, news, stocks, etc.)

LUIS provides a way to add a prompt

question if user query is missing any

of the required parameters

Active learningEasy creation of

LU modelsAction fulfillment Dialog support

Key features

detect customer intent and

sentiment and drive actions

Cognitive Services

Your Bot Framework Bot

23 purpose-built ML and AI services to

add predictable, configurable intelligence

into any software

Developer Portal

Connect your bots to text/sms, Skype,

Slack, Facebook Messenger,

Office 365 mail and other channels.

• Register, connect, publish and manage your bot through your bot’s dashboard

• Automatic card normalization across channels

• Skype channel auto-configured

• Embeddable Web chat control

• Host your bot in your app via the Direct Line API

• Fast, scalable message routing

• Bot Directory for discovery and trial

Bot Builder

Tools and services to build great bots

that converse wherever your users are.

• Open source SDK on Github for Node.js, .NET and REST

• From simple built-in prompts and command dialogs to simple to use yet sophisticated ‘FormFlow’ dialogs

• Support for rich attachments (image, card, video, doc, etc.); support for calling (Skype)

• Online/offline chat Emulator

• Add bot smarts with Cognitive Services for language understanding and more

• Parse natural language (LUIS)

• Real-time transcription and translation services for voice

• Vision and face detection algorithms

• Sentence diagramming

• Web language (hashtag) parsing

• Many more

Intelligent App Demo