SlideShare uma empresa Scribd logo
1 de 59
Baixar para ler offline
Machine Learning
for Designers
Memi Beltrame - @bratwurstkomet
UX Scotland

Edinburgh, June 12. 2019
Machine Learning
for people with a
fuzzy idea of what it is
Memi Beltrame - @bratwurstkomet
Or rather
UX Scotland

Edinburgh, June 12. 2019
Design is becoming physical,
automated and connected
https://pxhere.com/en/photo/1006116
An example
https://pxhere.com/en/photo/1006116
Her pain
is your pain
otoscope
This is an
otoscope
This is an
It can be used to look at the
eardrum to see if the ear is inflamed.
Because the otoscope is connected
to an iPhone, an image can be taken
of the eardrum.
The image is sent to a service that tells me if I should go to a doctor or not.
AI:
Image recognition,
Data analysis
Industrial Design
InteractionDesign
Service Design
Machine Learning is
the main driver
What is
Machine Learning?
This service uses Machine Learning to
make a prediction of the diagnosis
machine learning:
training machines
to receive input data and
predict an output value
3 methods how machines learn
Supervised learning You train the machine with data

The machine learns to make predictions
✔ ❌
3 methods how machines learn
Supervised learning You train the machine with data

The machine learns to make predictions
#1 method used in machine learning
3 methods how machines learn
Supervised learning You train the machine with data

The machine learns to make predictions
Unsupervised learning The machine is given a lot of data and it
uses algorithms to find out interesting
patterns.
Let's get some pizza data
1 2 3 4 5 6
1
2
3
4
5
6
7
Average # of pizzas per week
Average # of toppings

per pizza
Find patterns
1 2 3 4 5 6
1
2
3
4
5
6
7
Average # of toppings

per pizza
Average # of pizzas per week
Find patterns
1 2 3 4 5 6
1
2
3
4
5
6
7
Average # of toppings

per pizza
Average # of pizzas per week
You can run this
data through an
algorithm and it
would find groups of
items that are close
together,
Take Action
1 2 3 4 5 6
1
2
3
4
5
6
7
Average # of toppings

per pizza
Average # of pizzas per week
Take Action
1 2 3 4 5 6
1
2
3
4
5
6
7
Average # of toppings

per pizza
Average # of pizzas per week
With these groups you now can direct address the different groups
The group on the top right probably are big households you can target
specifically
The group on the left are those that order less frequently so you could address
this and offer a super tuesday for those that don't order on that day
The last one is for the people that love boring pizza: give them what they want,
but larger!
The applications of this clustering by unsupervised learning are market
segmentation or fraud detection in banking
3 methods how machines learn
Supervised learning You train the machine with data

The machine learns to make predictions
Unsupervised learning The machine is given a lot of data and it
uses algorithms to find out interesting
patterns.
Reinforcement learning The machine continuously learns from the
environment in an iterative fashion. 

It starts dumb and gets smarter.
Reinforcement Learning
The machine is given a
set of rules and a goal

• Physics: Gravity etc

• Wheels turn

• Goal get farther than
previous cars

It trains itself by keeping
the features that helped
it reach the goal.
BoxCar 2D: Computation Intelligence Car Evolution (Needs Flash) http://boxcar2d.com/
Reinforcement Learning
After a few dozen
generations the
machine has succeded
in creating a vehicle
that looks like a car and
can reliably drive
#1 method: supervised learning
Bedrooms m2 Neighbourhood Floors Sale Price
4 96 Hipsterton 2 1’500’000
2 89 Snoringham 3 750’000
3 75 Hipsterton 1 1’200’000
3 79 Snoringham 2 820’000
• Give the machine
a training set with
features 

• Give it the target
values

• It figures out how
important each
feature is 

• The machine can
make predictions
of target values
Features Target
#1 method: supervised learning
Bedrooms m2 Neighbourhood Floors
4 96 Hipsterton 2
2 89 Snoringham 3
3 75 Hipsterton 1
3 79 Snoringham 2
Predictions improve with 

• more features

• larger learning sample
Features
#1 method: supervised learning
Features Target
8
#1 method: supervised learning
Features Target
owl
#1 method: supervised learning
• Train the machine
to learn what
matches and what
does not

• Train with edge
cases
Owl or Apple?
machines make predictions
using algorithms
how machines use algorithms
500g white flour,

2 tsp salt

7g fast-action yeast

3 tbsp olive oil

300ml water

475g plain flour,

1 tsp salt

10g dried yeast

1 tbsp olive oil

400ml water

The algorithm finds the valid weights of the individual
features of a data-set to make the right prediction
2 cups flour,

1 cup salt

1 tsp olive oil

1 cup water

Bread Bread Salty play dough
how machines use algorithms
1. Take a lot of training data 

2. Pass it through a generic algorithm 

(some mathematical formula)

3. Let the machine figure out its own
logic based on the data.
Emails
Generic Machine
Learning Algorithm
Spam Not Spam
generic algorithms
There are many generic
algorithms that already exist.





The same generic algorithm
can be used to solve
problems in completely
different areas.
Emails Algorithm
Spam
Not Spam
Articles Algorithm Finance
Politics
Sports
2 types of algorithms
Classification algorithms
Emails Algorithm
Spam
Not Spam
The goal is to predict discrete
values, e.g. {1,0}, {True, False},
{spam, not spam}.
Regression algorithms
House-
Details
Algorithm
Price of
House
The goal is to predict continuous
values, e.g. home prices, weather
temperatures
A big part of ML
is about classification
image recognition
Chihuahua or Muffin?
Most image recognition is
about classification
image recognition
Real time

At multiple scales

For a varying number of
recognizable elements
Realtime Multi-Person 2D Human Pose Estimation
What about language?
is language like images?
Images can be
recognized
because their data
can be encoded
Can we do the same with language?
translation versus conversation
Do you have the time?
Translation goal:
Produce an equivalent
Conversation goal:
Understand the meaning
Avez-vous l’heure? It’s 7pm.Yes
statistical translation
statistical translation
Each word of the sentence can have several meanings.
statistical translation
I try | to run | at | the prettiest | open space.
I want | to run | per | the more tidy | open space.
I mean | to forget | at | the tidiest | beach.
I try | to go | per | the more tidy | seaside.
I want | to go | to | the prettiest | beach.
The algorithm compares the possible translations against existing ones.

The algorithm picks the translation with the highest probability.
statistical translation
Input
Measurements
of input
sentence
Output I want to go to the prettiest beach.
statistical translation
AudioText
conversational interfaces
Machine learning is a
crucial part of these
interfaces.
new challenges and disciplines
• recognizing intent

• understanding context

• voice and tone

• shaping conversations in a
humane way
}Linguistics
Ethics
intent - what does it all mean?
types of meaning
understand the wordsliteral:
understand the actual meaningimplied:
Do you have the time?
metaphors & metonymiesreferenced:
Wall Street is in crisis
How long was Tony Blair Prime Minister
Elements that make 

this artificial:

• Not picking up intent 

„give me a spot on saturday“

• Literal repetition
context
context is even harder than intent
• the sequence in time

• understanding the surroundings

• semantic context 

homonymy: 🦇 is not a 🏏
voice and tone: change registers
we adapt the way we speak to the
situation we’re in
Depending on:

• how serious the situation is

• how formal it is 

• how we are connected to the person
Conversational interfaces need to take
this into account. 

This is a design task
Yes
Sporty
Neutral
Date Night
Ready for your style?
How would you describe your style?
I'd totally raid your closet... 

Sporty is my style!
Do you wear colors or nah?
Fab, I bet you look great in everything!
Where are you going in your hot new
outfit?
The designers’ role
Designers are content experts
Icons by Sarah Rudkin
Developers
Build the machine
Domain experts

Have the domain
specific knowledge
Designers
• Content oversight for training: 

What makes good training data?

• Mediator between engineering and domain
experts

• Ethical considerations
ethics matter
Machines learn from us

We choose what to teach
We need to

• challenge and stress test from a diverse
point of view

• put humans before technology

(once again)

• bring our principles of what good
design is to the AI world
This is a design task
Machine Learning is 

everywhere
Learn to see its opportunities
Get a seat at the table now
Understand the implications
of using machine learning
Bring Design principles into the
mix to make empowering and
ethical products
Thanks!
I’m @bratwurstkomet


I like kitten and ice cream
Resources
A visual introduction to machine learning 

http://www.r2d3.us

Machine Learning is Fun! 

(the perfect series of articles to get you started)

https://medium.com/@ageitgey/machine-learning-is-fun-80ea3ec3c471

30 Free Courses: Neural Networks, Machine Learning, AI

https://www.datasciencecentral.com/profiles/blogs/neural-networks-for-machine-learning 

Watson Knowledge Studio 

https://www.ibm.com/watson/developercloud/doc/wks/wks_overview_full.shtml 

2 Minutes Papers: a youtube channel dedicated to condensing the results of scientific papers on artificial intelligence.

https://www.youtube.com/channel/UCbfYPyITQ-7l4upoX8nvctg 

Realtime Multi-Person 2D Human Pose Estimation 

https://www.youtube.com/watch?v=pW6nZXeWlGM

BoxCar 2D: Computation Intelligence Car Evolution (Needs Flash)

http://boxcar2d.com/ 

Google AI Experiments

https://experiments.withgoogle.com/collection/ai 



Differences Between AI and Machine Learning, and Why it Matters

https://medium.com/datadriveninvestor/differences-between-ai-and-machine-learning-and-why-it-matters-1255b182fc6

Mais conteúdo relacionado

Mais procurados

Copy of getting into ai event slides (PDF)
Copy of getting into ai   event slides (PDF)Copy of getting into ai   event slides (PDF)
Copy of getting into ai event slides (PDF)Matthew Miller
 
An Introduction to Applied Behavioral Science, for Project Managers
An Introduction to Applied Behavioral Science, for Project ManagersAn Introduction to Applied Behavioral Science, for Project Managers
An Introduction to Applied Behavioral Science, for Project ManagersStephen Wendel
 
Expert Systems New
Expert Systems NewExpert Systems New
Expert Systems NewKate Festa
 
Behavioral Science for Data Scientists
Behavioral Science for Data ScientistsBehavioral Science for Data Scientists
Behavioral Science for Data ScientistsStephen Wendel
 
Dolapo Amusat - How to begin to build stuff @ IEEE SPAC, Ibadan
Dolapo Amusat - How to begin to build stuff @ IEEE SPAC, IbadanDolapo Amusat - How to begin to build stuff @ IEEE SPAC, Ibadan
Dolapo Amusat - How to begin to build stuff @ IEEE SPAC, IbadanDolapo Amusat
 
11 Insightful Quotes From UX London 2016 (And How They Apply to Digital Agenc...
11 Insightful Quotes From UX London 2016 (And How They Apply to Digital Agenc...11 Insightful Quotes From UX London 2016 (And How They Apply to Digital Agenc...
11 Insightful Quotes From UX London 2016 (And How They Apply to Digital Agenc...Clément Génin
 
Can your workplace design help reduce stress
Can your workplace design help reduce stressCan your workplace design help reduce stress
Can your workplace design help reduce stressCurtis Cripe
 
Mobile Design: Adding Mobile to Your Learning Ecosystem
Mobile Design: Adding Mobile to Your Learning EcosystemMobile Design: Adding Mobile to Your Learning Ecosystem
Mobile Design: Adding Mobile to Your Learning EcosystemSteven Hoober
 
Usability testing in the open
Usability testing in the openUsability testing in the open
Usability testing in the openAnne Petersen
 
Don't be too hard for agile; How to go lean with hardware
Don't be too hard for agile; How to go lean with hardwareDon't be too hard for agile; How to go lean with hardware
Don't be too hard for agile; How to go lean with hardwareMoriya Kassis
 
Engineering is Elementary: The Bridge to Engineering Partnership with SFSU an...
Engineering is Elementary: The Bridge to Engineering Partnership with SFSU an...Engineering is Elementary: The Bridge to Engineering Partnership with SFSU an...
Engineering is Elementary: The Bridge to Engineering Partnership with SFSU an...California STEM Learning Network
 
Interaction design & quantified self
Interaction design & quantified selfInteraction design & quantified self
Interaction design & quantified selfPaul Sas
 
Multitasking: How brain works on different tasks
Multitasking: How brain works on different tasksMultitasking: How brain works on different tasks
Multitasking: How brain works on different tasksMujahid Hussain
 

Mais procurados (18)

Intro to UX
Intro to UXIntro to UX
Intro to UX
 
Copy of getting into ai event slides (PDF)
Copy of getting into ai   event slides (PDF)Copy of getting into ai   event slides (PDF)
Copy of getting into ai event slides (PDF)
 
An Introduction to Applied Behavioral Science, for Project Managers
An Introduction to Applied Behavioral Science, for Project ManagersAn Introduction to Applied Behavioral Science, for Project Managers
An Introduction to Applied Behavioral Science, for Project Managers
 
Expert Systems New
Expert Systems NewExpert Systems New
Expert Systems New
 
Behavioral Science for Data Scientists
Behavioral Science for Data ScientistsBehavioral Science for Data Scientists
Behavioral Science for Data Scientists
 
Dolapo Amusat - How to begin to build stuff @ IEEE SPAC, Ibadan
Dolapo Amusat - How to begin to build stuff @ IEEE SPAC, IbadanDolapo Amusat - How to begin to build stuff @ IEEE SPAC, Ibadan
Dolapo Amusat - How to begin to build stuff @ IEEE SPAC, Ibadan
 
11 Insightful Quotes From UX London 2016 (And How They Apply to Digital Agenc...
11 Insightful Quotes From UX London 2016 (And How They Apply to Digital Agenc...11 Insightful Quotes From UX London 2016 (And How They Apply to Digital Agenc...
11 Insightful Quotes From UX London 2016 (And How They Apply to Digital Agenc...
 
Two Solitudes
Two SolitudesTwo Solitudes
Two Solitudes
 
computer Quiz
computer Quizcomputer Quiz
computer Quiz
 
Can your workplace design help reduce stress
Can your workplace design help reduce stressCan your workplace design help reduce stress
Can your workplace design help reduce stress
 
Mobile Design: Adding Mobile to Your Learning Ecosystem
Mobile Design: Adding Mobile to Your Learning EcosystemMobile Design: Adding Mobile to Your Learning Ecosystem
Mobile Design: Adding Mobile to Your Learning Ecosystem
 
Usability testing in the open
Usability testing in the openUsability testing in the open
Usability testing in the open
 
Don't be too hard for agile; How to go lean with hardware
Don't be too hard for agile; How to go lean with hardwareDon't be too hard for agile; How to go lean with hardware
Don't be too hard for agile; How to go lean with hardware
 
Engineering is Elementary: The Bridge to Engineering Partnership with SFSU an...
Engineering is Elementary: The Bridge to Engineering Partnership with SFSU an...Engineering is Elementary: The Bridge to Engineering Partnership with SFSU an...
Engineering is Elementary: The Bridge to Engineering Partnership with SFSU an...
 
Future of Work 2015 - For Beacon School, Crowborough
Future of Work 2015 - For Beacon School, CrowboroughFuture of Work 2015 - For Beacon School, Crowborough
Future of Work 2015 - For Beacon School, Crowborough
 
Interaction design & quantified self
Interaction design & quantified selfInteraction design & quantified self
Interaction design & quantified self
 
Multitasking: How brain works on different tasks
Multitasking: How brain works on different tasksMultitasking: How brain works on different tasks
Multitasking: How brain works on different tasks
 
Multitasking
MultitaskingMultitasking
Multitasking
 

Semelhante a Machine Learning for Designers - UX Scotland

Machine Learning for Designers - UX Camp Switzerland
Machine Learning for Designers - UX Camp SwitzerlandMachine Learning for Designers - UX Camp Switzerland
Machine Learning for Designers - UX Camp SwitzerlandMemi Beltrame
 
Machine Learning for Designers
Machine Learning for DesignersMachine Learning for Designers
Machine Learning for DesignersMemi Beltrame
 
Machine Learning for Designers
Machine Learning for DesignersMachine Learning for Designers
Machine Learning for DesignersMemi Beltrame
 
Machine Learning for Designers - DX Meetup Basel
Machine Learning for Designers - DX Meetup BaselMachine Learning for Designers - DX Meetup Basel
Machine Learning for Designers - DX Meetup BaselMemi Beltrame
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine LearningCloudxLab
 
Deep Learning Overview
Deep Learning OverviewDeep Learning Overview
Deep Learning OverviewCloudxLab
 
Unit 1-ML (1) (1).pptx
Unit 1-ML (1) (1).pptxUnit 1-ML (1) (1).pptx
Unit 1-ML (1) (1).pptxChitrachitrap
 
Introduction to Deep Learning | CloudxLab
Introduction to Deep Learning | CloudxLabIntroduction to Deep Learning | CloudxLab
Introduction to Deep Learning | CloudxLabCloudxLab
 
BIG DATA AND MACHINE LEARNING
BIG DATA AND MACHINE LEARNINGBIG DATA AND MACHINE LEARNING
BIG DATA AND MACHINE LEARNINGUmair Shafique
 
What Is Data Science? | Introduction to Data Science | Data Science For Begin...
What Is Data Science? | Introduction to Data Science | Data Science For Begin...What Is Data Science? | Introduction to Data Science | Data Science For Begin...
What Is Data Science? | Introduction to Data Science | Data Science For Begin...Simplilearn
 
Introduction To Data Science
Introduction To Data ScienceIntroduction To Data Science
Introduction To Data ScienceSpotle.ai
 
Deep learning introduction
Deep learning introductionDeep learning introduction
Deep learning introductionAdwait Bhave
 
HadoopSummit2015_SelfEvolvingModels
HadoopSummit2015_SelfEvolvingModelsHadoopSummit2015_SelfEvolvingModels
HadoopSummit2015_SelfEvolvingModelspeas2bees
 
Hr salary prediction using ml
Hr salary prediction using mlHr salary prediction using ml
Hr salary prediction using mlshaiksafi1
 
The elements of product success for designers and developers
The elements of product success for designers and developersThe elements of product success for designers and developers
The elements of product success for designers and developersNick Myers
 
Creating a culture that provokes failure and boosts improvement
Creating a culture that provokes failure and boosts improvementCreating a culture that provokes failure and boosts improvement
Creating a culture that provokes failure and boosts improvementBen Dressler
 
Self Evolving Model to Attain to State of Dynamic System Accuracy
Self Evolving Model to Attain to State of Dynamic System AccuracySelf Evolving Model to Attain to State of Dynamic System Accuracy
Self Evolving Model to Attain to State of Dynamic System AccuracyDataWorks Summit
 
HadoopSummit'2015:Self Evolving Models for Dynamic System Accuracy
HadoopSummit'2015:Self Evolving Models for Dynamic System AccuracyHadoopSummit'2015:Self Evolving Models for Dynamic System Accuracy
HadoopSummit'2015:Self Evolving Models for Dynamic System AccuracyRekha Joshi
 

Semelhante a Machine Learning for Designers - UX Scotland (20)

Machine Learning for Designers - UX Camp Switzerland
Machine Learning for Designers - UX Camp SwitzerlandMachine Learning for Designers - UX Camp Switzerland
Machine Learning for Designers - UX Camp Switzerland
 
Machine Learning for Designers
Machine Learning for DesignersMachine Learning for Designers
Machine Learning for Designers
 
Machine Learning for Designers
Machine Learning for DesignersMachine Learning for Designers
Machine Learning for Designers
 
Machine Learning for Designers - DX Meetup Basel
Machine Learning for Designers - DX Meetup BaselMachine Learning for Designers - DX Meetup Basel
Machine Learning for Designers - DX Meetup Basel
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
 
Deep Learning Overview
Deep Learning OverviewDeep Learning Overview
Deep Learning Overview
 
Unit 1-ML (1) (1).pptx
Unit 1-ML (1) (1).pptxUnit 1-ML (1) (1).pptx
Unit 1-ML (1) (1).pptx
 
Introduction to Deep Learning | CloudxLab
Introduction to Deep Learning | CloudxLabIntroduction to Deep Learning | CloudxLab
Introduction to Deep Learning | CloudxLab
 
Lab 7.pptx
Lab 7.pptxLab 7.pptx
Lab 7.pptx
 
BIG DATA AND MACHINE LEARNING
BIG DATA AND MACHINE LEARNINGBIG DATA AND MACHINE LEARNING
BIG DATA AND MACHINE LEARNING
 
What Is Data Science? | Introduction to Data Science | Data Science For Begin...
What Is Data Science? | Introduction to Data Science | Data Science For Begin...What Is Data Science? | Introduction to Data Science | Data Science For Begin...
What Is Data Science? | Introduction to Data Science | Data Science For Begin...
 
Introduction To Data Science
Introduction To Data ScienceIntroduction To Data Science
Introduction To Data Science
 
Deep learning introduction
Deep learning introductionDeep learning introduction
Deep learning introduction
 
HadoopSummit2015_SelfEvolvingModels
HadoopSummit2015_SelfEvolvingModelsHadoopSummit2015_SelfEvolvingModels
HadoopSummit2015_SelfEvolvingModels
 
Hr salary prediction using ml
Hr salary prediction using mlHr salary prediction using ml
Hr salary prediction using ml
 
The elements of product success for designers and developers
The elements of product success for designers and developersThe elements of product success for designers and developers
The elements of product success for designers and developers
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligence
 
Creating a culture that provokes failure and boosts improvement
Creating a culture that provokes failure and boosts improvementCreating a culture that provokes failure and boosts improvement
Creating a culture that provokes failure and boosts improvement
 
Self Evolving Model to Attain to State of Dynamic System Accuracy
Self Evolving Model to Attain to State of Dynamic System AccuracySelf Evolving Model to Attain to State of Dynamic System Accuracy
Self Evolving Model to Attain to State of Dynamic System Accuracy
 
HadoopSummit'2015:Self Evolving Models for Dynamic System Accuracy
HadoopSummit'2015:Self Evolving Models for Dynamic System AccuracyHadoopSummit'2015:Self Evolving Models for Dynamic System Accuracy
HadoopSummit'2015:Self Evolving Models for Dynamic System Accuracy
 

Mais de Memi Beltrame

Zero Adoption: Lessons Learned From Failing at Open Source
Zero Adoption: Lessons Learned From Failing at Open SourceZero Adoption: Lessons Learned From Failing at Open Source
Zero Adoption: Lessons Learned From Failing at Open SourceMemi Beltrame
 
UX in the city Coping with Complexity
UX in the city   Coping with ComplexityUX in the city   Coping with Complexity
UX in the city Coping with ComplexityMemi Beltrame
 
Dynamic A/B testing with AB/CD
Dynamic A/B testing with AB/CDDynamic A/B testing with AB/CD
Dynamic A/B testing with AB/CDMemi Beltrame
 
Product Owner ist ein Design Job
Product Owner ist ein Design JobProduct Owner ist ein Design Job
Product Owner ist ein Design JobMemi Beltrame
 
Designed for the Worst Case - Zurich's water supply
Designed for  the Worst Case - Zurich's water supplyDesigned for  the Worst Case - Zurich's water supply
Designed for the Worst Case - Zurich's water supplyMemi Beltrame
 
Data Driven Design - Frontend Conference Zurich
Data Driven Design - Frontend Conference ZurichData Driven Design - Frontend Conference Zurich
Data Driven Design - Frontend Conference ZurichMemi Beltrame
 
Clear Language and Readability
Clear Language and ReadabilityClear Language and Readability
Clear Language and ReadabilityMemi Beltrame
 
The User Experience of Near Field Communication
The User Experience of Near Field CommunicationThe User Experience of Near Field Communication
The User Experience of Near Field CommunicationMemi Beltrame
 
Prototyping and Scrum
Prototyping and ScrumPrototyping and Scrum
Prototyping and ScrumMemi Beltrame
 
Prototyping for mobile
Prototyping for mobilePrototyping for mobile
Prototyping for mobileMemi Beltrame
 
No Design without Research
No Design without ResearchNo Design without Research
No Design without ResearchMemi Beltrame
 
Just Married: User Centered Design and Agile
Just Married: User Centered Design and AgileJust Married: User Centered Design and Agile
Just Married: User Centered Design and AgileMemi Beltrame
 
Made By Many - On Collaborative Design
Made By Many - On Collaborative DesignMade By Many - On Collaborative Design
Made By Many - On Collaborative DesignMemi Beltrame
 
Elements of UX Design
Elements of UX DesignElements of UX Design
Elements of UX DesignMemi Beltrame
 

Mais de Memi Beltrame (20)

Protostrap
ProtostrapProtostrap
Protostrap
 
Zero Adoption: Lessons Learned From Failing at Open Source
Zero Adoption: Lessons Learned From Failing at Open SourceZero Adoption: Lessons Learned From Failing at Open Source
Zero Adoption: Lessons Learned From Failing at Open Source
 
UX in the city Coping with Complexity
UX in the city   Coping with ComplexityUX in the city   Coping with Complexity
UX in the city Coping with Complexity
 
Dynamic A/B testing with AB/CD
Dynamic A/B testing with AB/CDDynamic A/B testing with AB/CD
Dynamic A/B testing with AB/CD
 
Product Owner ist ein Design Job
Product Owner ist ein Design JobProduct Owner ist ein Design Job
Product Owner ist ein Design Job
 
Designed for the Worst Case - Zurich's water supply
Designed for  the Worst Case - Zurich's water supplyDesigned for  the Worst Case - Zurich's water supply
Designed for the Worst Case - Zurich's water supply
 
Data Driven Design - Frontend Conference Zurich
Data Driven Design - Frontend Conference ZurichData Driven Design - Frontend Conference Zurich
Data Driven Design - Frontend Conference Zurich
 
Clear Language and Readability
Clear Language and ReadabilityClear Language and Readability
Clear Language and Readability
 
The User Experience of Near Field Communication
The User Experience of Near Field CommunicationThe User Experience of Near Field Communication
The User Experience of Near Field Communication
 
Prototyping and Scrum
Prototyping and ScrumPrototyping and Scrum
Prototyping and Scrum
 
Prototyping for mobile
Prototyping for mobilePrototyping for mobile
Prototyping for mobile
 
Protostrap
ProtostrapProtostrap
Protostrap
 
Content Audits
Content AuditsContent Audits
Content Audits
 
No Design without Research
No Design without ResearchNo Design without Research
No Design without Research
 
Swiss mobile stats
Swiss mobile statsSwiss mobile stats
Swiss mobile stats
 
Content Strategy
Content StrategyContent Strategy
Content Strategy
 
Just Married: User Centered Design and Agile
Just Married: User Centered Design and AgileJust Married: User Centered Design and Agile
Just Married: User Centered Design and Agile
 
Made By Many - On Collaborative Design
Made By Many - On Collaborative DesignMade By Many - On Collaborative Design
Made By Many - On Collaborative Design
 
Elements of UX Design
Elements of UX DesignElements of UX Design
Elements of UX Design
 
Scope & co
Scope & coScope & co
Scope & co
 

Último

Create Web Pages by programming of your chice.pdf
Create Web Pages by programming of your chice.pdfCreate Web Pages by programming of your chice.pdf
Create Web Pages by programming of your chice.pdfworkingdev2003
 
MT. Marseille an Archipelago. Strategies for Integrating Residential Communit...
MT. Marseille an Archipelago. Strategies for Integrating Residential Communit...MT. Marseille an Archipelago. Strategies for Integrating Residential Communit...
MT. Marseille an Archipelago. Strategies for Integrating Residential Communit...katerynaivanenko1
 
办理(麻省罗威尔毕业证书)美国麻省大学罗威尔校区毕业证成绩单原版一比一
办理(麻省罗威尔毕业证书)美国麻省大学罗威尔校区毕业证成绩单原版一比一办理(麻省罗威尔毕业证书)美国麻省大学罗威尔校区毕业证成绩单原版一比一
办理(麻省罗威尔毕业证书)美国麻省大学罗威尔校区毕业证成绩单原版一比一diploma 1
 
专业一比一美国亚利桑那大学毕业证成绩单pdf电子版制作修改#真实工艺展示#真实防伪#diploma#degree
专业一比一美国亚利桑那大学毕业证成绩单pdf电子版制作修改#真实工艺展示#真实防伪#diploma#degree专业一比一美国亚利桑那大学毕业证成绩单pdf电子版制作修改#真实工艺展示#真实防伪#diploma#degree
专业一比一美国亚利桑那大学毕业证成绩单pdf电子版制作修改#真实工艺展示#真实防伪#diploma#degreeyuu sss
 
(办理学位证)约克圣约翰大学毕业证,KCL成绩单原版一比一
(办理学位证)约克圣约翰大学毕业证,KCL成绩单原版一比一(办理学位证)约克圣约翰大学毕业证,KCL成绩单原版一比一
(办理学位证)约克圣约翰大学毕业证,KCL成绩单原版一比一D SSS
 
西北大学毕业证学位证成绩单-怎么样办伪造
西北大学毕业证学位证成绩单-怎么样办伪造西北大学毕业证学位证成绩单-怎么样办伪造
西北大学毕业证学位证成绩单-怎么样办伪造kbdhl05e
 
昆士兰大学毕业证(UQ毕业证)#文凭成绩单#真实留信学历认证永久存档
昆士兰大学毕业证(UQ毕业证)#文凭成绩单#真实留信学历认证永久存档昆士兰大学毕业证(UQ毕业证)#文凭成绩单#真实留信学历认证永久存档
昆士兰大学毕业证(UQ毕业证)#文凭成绩单#真实留信学历认证永久存档208367051
 
毕业文凭制作#回国入职#diploma#degree美国威斯康星大学欧克莱尔分校毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#...
毕业文凭制作#回国入职#diploma#degree美国威斯康星大学欧克莱尔分校毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#...毕业文凭制作#回国入职#diploma#degree美国威斯康星大学欧克莱尔分校毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#...
毕业文凭制作#回国入职#diploma#degree美国威斯康星大学欧克莱尔分校毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#...ttt fff
 
How to Empower the future of UX Design with Gen AI
How to Empower the future of UX Design with Gen AIHow to Empower the future of UX Design with Gen AI
How to Empower the future of UX Design with Gen AIyuj
 
Iconic Global Solution - web design, Digital Marketing services
Iconic Global Solution - web design, Digital Marketing servicesIconic Global Solution - web design, Digital Marketing services
Iconic Global Solution - web design, Digital Marketing servicesIconic global solution
 
在线办理ohio毕业证俄亥俄大学毕业证成绩单留信学历认证
在线办理ohio毕业证俄亥俄大学毕业证成绩单留信学历认证在线办理ohio毕业证俄亥俄大学毕业证成绩单留信学历认证
在线办理ohio毕业证俄亥俄大学毕业证成绩单留信学历认证nhjeo1gg
 
Call Girls Aslali 7397865700 Ridhima Hire Me Full Night
Call Girls Aslali 7397865700 Ridhima Hire Me Full NightCall Girls Aslali 7397865700 Ridhima Hire Me Full Night
Call Girls Aslali 7397865700 Ridhima Hire Me Full Nightssuser7cb4ff
 
澳洲UQ学位证,昆士兰大学毕业证书1:1制作
澳洲UQ学位证,昆士兰大学毕业证书1:1制作澳洲UQ学位证,昆士兰大学毕业证书1:1制作
澳洲UQ学位证,昆士兰大学毕业证书1:1制作aecnsnzk
 
FiveHypotheses_UIDMasterclass_18April2024.pdf
FiveHypotheses_UIDMasterclass_18April2024.pdfFiveHypotheses_UIDMasterclass_18April2024.pdf
FiveHypotheses_UIDMasterclass_18April2024.pdfShivakumar Viswanathan
 
'CASE STUDY OF INDIRA PARYAVARAN BHAVAN DELHI ,
'CASE STUDY OF INDIRA PARYAVARAN BHAVAN DELHI ,'CASE STUDY OF INDIRA PARYAVARAN BHAVAN DELHI ,
'CASE STUDY OF INDIRA PARYAVARAN BHAVAN DELHI ,Aginakm1
 
Design and Managing Service in the field of tourism and hospitality industry
Design and Managing Service in the field of tourism and hospitality industryDesign and Managing Service in the field of tourism and hospitality industry
Design and Managing Service in the field of tourism and hospitality industryrioverosanniejoy
 
group_15_empirya_p1projectIndustrial.pdf
group_15_empirya_p1projectIndustrial.pdfgroup_15_empirya_p1projectIndustrial.pdf
group_15_empirya_p1projectIndustrial.pdfneelspinoy
 
办理学位证(UCSD证书)美国加利福尼亚大学圣迭戈分校毕业证成绩单原版一比一
办理学位证(UCSD证书)美国加利福尼亚大学圣迭戈分校毕业证成绩单原版一比一办理学位证(UCSD证书)美国加利福尼亚大学圣迭戈分校毕业证成绩单原版一比一
办理学位证(UCSD证书)美国加利福尼亚大学圣迭戈分校毕业证成绩单原版一比一A SSS
 
1比1办理美国北卡罗莱纳州立大学毕业证成绩单pdf电子版制作修改
1比1办理美国北卡罗莱纳州立大学毕业证成绩单pdf电子版制作修改1比1办理美国北卡罗莱纳州立大学毕业证成绩单pdf电子版制作修改
1比1办理美国北卡罗莱纳州立大学毕业证成绩单pdf电子版制作修改yuu sss
 

Último (20)

Call Girls in Pratap Nagar, 9953056974 Escort Service
Call Girls in Pratap Nagar,  9953056974 Escort ServiceCall Girls in Pratap Nagar,  9953056974 Escort Service
Call Girls in Pratap Nagar, 9953056974 Escort Service
 
Create Web Pages by programming of your chice.pdf
Create Web Pages by programming of your chice.pdfCreate Web Pages by programming of your chice.pdf
Create Web Pages by programming of your chice.pdf
 
MT. Marseille an Archipelago. Strategies for Integrating Residential Communit...
MT. Marseille an Archipelago. Strategies for Integrating Residential Communit...MT. Marseille an Archipelago. Strategies for Integrating Residential Communit...
MT. Marseille an Archipelago. Strategies for Integrating Residential Communit...
 
办理(麻省罗威尔毕业证书)美国麻省大学罗威尔校区毕业证成绩单原版一比一
办理(麻省罗威尔毕业证书)美国麻省大学罗威尔校区毕业证成绩单原版一比一办理(麻省罗威尔毕业证书)美国麻省大学罗威尔校区毕业证成绩单原版一比一
办理(麻省罗威尔毕业证书)美国麻省大学罗威尔校区毕业证成绩单原版一比一
 
专业一比一美国亚利桑那大学毕业证成绩单pdf电子版制作修改#真实工艺展示#真实防伪#diploma#degree
专业一比一美国亚利桑那大学毕业证成绩单pdf电子版制作修改#真实工艺展示#真实防伪#diploma#degree专业一比一美国亚利桑那大学毕业证成绩单pdf电子版制作修改#真实工艺展示#真实防伪#diploma#degree
专业一比一美国亚利桑那大学毕业证成绩单pdf电子版制作修改#真实工艺展示#真实防伪#diploma#degree
 
(办理学位证)约克圣约翰大学毕业证,KCL成绩单原版一比一
(办理学位证)约克圣约翰大学毕业证,KCL成绩单原版一比一(办理学位证)约克圣约翰大学毕业证,KCL成绩单原版一比一
(办理学位证)约克圣约翰大学毕业证,KCL成绩单原版一比一
 
西北大学毕业证学位证成绩单-怎么样办伪造
西北大学毕业证学位证成绩单-怎么样办伪造西北大学毕业证学位证成绩单-怎么样办伪造
西北大学毕业证学位证成绩单-怎么样办伪造
 
昆士兰大学毕业证(UQ毕业证)#文凭成绩单#真实留信学历认证永久存档
昆士兰大学毕业证(UQ毕业证)#文凭成绩单#真实留信学历认证永久存档昆士兰大学毕业证(UQ毕业证)#文凭成绩单#真实留信学历认证永久存档
昆士兰大学毕业证(UQ毕业证)#文凭成绩单#真实留信学历认证永久存档
 
毕业文凭制作#回国入职#diploma#degree美国威斯康星大学欧克莱尔分校毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#...
毕业文凭制作#回国入职#diploma#degree美国威斯康星大学欧克莱尔分校毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#...毕业文凭制作#回国入职#diploma#degree美国威斯康星大学欧克莱尔分校毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#...
毕业文凭制作#回国入职#diploma#degree美国威斯康星大学欧克莱尔分校毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#...
 
How to Empower the future of UX Design with Gen AI
How to Empower the future of UX Design with Gen AIHow to Empower the future of UX Design with Gen AI
How to Empower the future of UX Design with Gen AI
 
Iconic Global Solution - web design, Digital Marketing services
Iconic Global Solution - web design, Digital Marketing servicesIconic Global Solution - web design, Digital Marketing services
Iconic Global Solution - web design, Digital Marketing services
 
在线办理ohio毕业证俄亥俄大学毕业证成绩单留信学历认证
在线办理ohio毕业证俄亥俄大学毕业证成绩单留信学历认证在线办理ohio毕业证俄亥俄大学毕业证成绩单留信学历认证
在线办理ohio毕业证俄亥俄大学毕业证成绩单留信学历认证
 
Call Girls Aslali 7397865700 Ridhima Hire Me Full Night
Call Girls Aslali 7397865700 Ridhima Hire Me Full NightCall Girls Aslali 7397865700 Ridhima Hire Me Full Night
Call Girls Aslali 7397865700 Ridhima Hire Me Full Night
 
澳洲UQ学位证,昆士兰大学毕业证书1:1制作
澳洲UQ学位证,昆士兰大学毕业证书1:1制作澳洲UQ学位证,昆士兰大学毕业证书1:1制作
澳洲UQ学位证,昆士兰大学毕业证书1:1制作
 
FiveHypotheses_UIDMasterclass_18April2024.pdf
FiveHypotheses_UIDMasterclass_18April2024.pdfFiveHypotheses_UIDMasterclass_18April2024.pdf
FiveHypotheses_UIDMasterclass_18April2024.pdf
 
'CASE STUDY OF INDIRA PARYAVARAN BHAVAN DELHI ,
'CASE STUDY OF INDIRA PARYAVARAN BHAVAN DELHI ,'CASE STUDY OF INDIRA PARYAVARAN BHAVAN DELHI ,
'CASE STUDY OF INDIRA PARYAVARAN BHAVAN DELHI ,
 
Design and Managing Service in the field of tourism and hospitality industry
Design and Managing Service in the field of tourism and hospitality industryDesign and Managing Service in the field of tourism and hospitality industry
Design and Managing Service in the field of tourism and hospitality industry
 
group_15_empirya_p1projectIndustrial.pdf
group_15_empirya_p1projectIndustrial.pdfgroup_15_empirya_p1projectIndustrial.pdf
group_15_empirya_p1projectIndustrial.pdf
 
办理学位证(UCSD证书)美国加利福尼亚大学圣迭戈分校毕业证成绩单原版一比一
办理学位证(UCSD证书)美国加利福尼亚大学圣迭戈分校毕业证成绩单原版一比一办理学位证(UCSD证书)美国加利福尼亚大学圣迭戈分校毕业证成绩单原版一比一
办理学位证(UCSD证书)美国加利福尼亚大学圣迭戈分校毕业证成绩单原版一比一
 
1比1办理美国北卡罗莱纳州立大学毕业证成绩单pdf电子版制作修改
1比1办理美国北卡罗莱纳州立大学毕业证成绩单pdf电子版制作修改1比1办理美国北卡罗莱纳州立大学毕业证成绩单pdf电子版制作修改
1比1办理美国北卡罗莱纳州立大学毕业证成绩单pdf电子版制作修改
 

Machine Learning for Designers - UX Scotland

  • 1. Machine Learning for Designers Memi Beltrame - @bratwurstkomet UX Scotland Edinburgh, June 12. 2019
  • 2. Machine Learning for people with a fuzzy idea of what it is Memi Beltrame - @bratwurstkomet Or rather UX Scotland Edinburgh, June 12. 2019
  • 3.
  • 4. Design is becoming physical, automated and connected
  • 8. otoscope This is an It can be used to look at the eardrum to see if the ear is inflamed. Because the otoscope is connected to an iPhone, an image can be taken of the eardrum.
  • 9.
  • 10. The image is sent to a service that tells me if I should go to a doctor or not.
  • 11. AI: Image recognition, Data analysis Industrial Design InteractionDesign Service Design
  • 12. Machine Learning is the main driver
  • 14. This service uses Machine Learning to make a prediction of the diagnosis
  • 15. machine learning: training machines to receive input data and predict an output value
  • 16. 3 methods how machines learn Supervised learning You train the machine with data The machine learns to make predictions ✔ ❌
  • 17. 3 methods how machines learn Supervised learning You train the machine with data The machine learns to make predictions #1 method used in machine learning
  • 18. 3 methods how machines learn Supervised learning You train the machine with data The machine learns to make predictions Unsupervised learning The machine is given a lot of data and it uses algorithms to find out interesting patterns.
  • 19. Let's get some pizza data 1 2 3 4 5 6 1 2 3 4 5 6 7 Average # of pizzas per week Average # of toppings per pizza
  • 20. Find patterns 1 2 3 4 5 6 1 2 3 4 5 6 7 Average # of toppings per pizza Average # of pizzas per week
  • 21. Find patterns 1 2 3 4 5 6 1 2 3 4 5 6 7 Average # of toppings per pizza Average # of pizzas per week You can run this data through an algorithm and it would find groups of items that are close together,
  • 22. Take Action 1 2 3 4 5 6 1 2 3 4 5 6 7 Average # of toppings per pizza Average # of pizzas per week
  • 23. Take Action 1 2 3 4 5 6 1 2 3 4 5 6 7 Average # of toppings per pizza Average # of pizzas per week With these groups you now can direct address the different groups The group on the top right probably are big households you can target specifically The group on the left are those that order less frequently so you could address this and offer a super tuesday for those that don't order on that day The last one is for the people that love boring pizza: give them what they want, but larger! The applications of this clustering by unsupervised learning are market segmentation or fraud detection in banking
  • 24. 3 methods how machines learn Supervised learning You train the machine with data The machine learns to make predictions Unsupervised learning The machine is given a lot of data and it uses algorithms to find out interesting patterns. Reinforcement learning The machine continuously learns from the environment in an iterative fashion. 
 It starts dumb and gets smarter.
  • 25. Reinforcement Learning The machine is given a set of rules and a goal
 • Physics: Gravity etc • Wheels turn • Goal get farther than previous cars
 It trains itself by keeping the features that helped it reach the goal. BoxCar 2D: Computation Intelligence Car Evolution (Needs Flash) http://boxcar2d.com/
  • 26. Reinforcement Learning After a few dozen generations the machine has succeded in creating a vehicle that looks like a car and can reliably drive
  • 27. #1 method: supervised learning Bedrooms m2 Neighbourhood Floors Sale Price 4 96 Hipsterton 2 1’500’000 2 89 Snoringham 3 750’000 3 75 Hipsterton 1 1’200’000 3 79 Snoringham 2 820’000 • Give the machine a training set with features • Give it the target values • It figures out how important each feature is • The machine can make predictions of target values Features Target
  • 28. #1 method: supervised learning Bedrooms m2 Neighbourhood Floors 4 96 Hipsterton 2 2 89 Snoringham 3 3 75 Hipsterton 1 3 79 Snoringham 2 Predictions improve with • more features • larger learning sample Features
  • 29. #1 method: supervised learning Features Target 8
  • 30. #1 method: supervised learning Features Target owl
  • 31. #1 method: supervised learning • Train the machine to learn what matches and what does not • Train with edge cases Owl or Apple?
  • 33. how machines use algorithms 500g white flour, 2 tsp salt 7g fast-action yeast
 3 tbsp olive oil 300ml water 475g plain flour, 1 tsp salt 10g dried yeast
 1 tbsp olive oil 400ml water The algorithm finds the valid weights of the individual features of a data-set to make the right prediction 2 cups flour, 1 cup salt 1 tsp olive oil 1 cup water Bread Bread Salty play dough
  • 34. how machines use algorithms 1. Take a lot of training data 
 2. Pass it through a generic algorithm 
 (some mathematical formula)
 3. Let the machine figure out its own logic based on the data. Emails Generic Machine Learning Algorithm Spam Not Spam
  • 35. generic algorithms There are many generic algorithms that already exist.
 
 
 The same generic algorithm can be used to solve problems in completely different areas. Emails Algorithm Spam Not Spam Articles Algorithm Finance Politics Sports
  • 36. 2 types of algorithms Classification algorithms Emails Algorithm Spam Not Spam The goal is to predict discrete values, e.g. {1,0}, {True, False}, {spam, not spam}. Regression algorithms House- Details Algorithm Price of House The goal is to predict continuous values, e.g. home prices, weather temperatures A big part of ML is about classification
  • 37. image recognition Chihuahua or Muffin? Most image recognition is about classification
  • 38. image recognition Real time At multiple scales For a varying number of recognizable elements Realtime Multi-Person 2D Human Pose Estimation
  • 40. is language like images? Images can be recognized because their data can be encoded Can we do the same with language?
  • 41. translation versus conversation Do you have the time? Translation goal: Produce an equivalent Conversation goal: Understand the meaning Avez-vous l’heure? It’s 7pm.Yes
  • 43. statistical translation Each word of the sentence can have several meanings.
  • 44. statistical translation I try | to run | at | the prettiest | open space. I want | to run | per | the more tidy | open space. I mean | to forget | at | the tidiest | beach. I try | to go | per | the more tidy | seaside. I want | to go | to | the prettiest | beach. The algorithm compares the possible translations against existing ones. The algorithm picks the translation with the highest probability.
  • 47. AudioText conversational interfaces Machine learning is a crucial part of these interfaces.
  • 48. new challenges and disciplines • recognizing intent • understanding context • voice and tone • shaping conversations in a humane way }Linguistics Ethics
  • 49. intent - what does it all mean? types of meaning understand the wordsliteral: understand the actual meaningimplied: Do you have the time? metaphors & metonymiesreferenced: Wall Street is in crisis How long was Tony Blair Prime Minister
  • 50.
  • 51. Elements that make 
 this artificial: • Not picking up intent 
 „give me a spot on saturday“ • Literal repetition
  • 52. context context is even harder than intent • the sequence in time • understanding the surroundings • semantic context 
 homonymy: 🦇 is not a 🏏
  • 53. voice and tone: change registers we adapt the way we speak to the situation we’re in Depending on: • how serious the situation is • how formal it is • how we are connected to the person Conversational interfaces need to take this into account. 
 This is a design task Yes Sporty Neutral Date Night Ready for your style? How would you describe your style? I'd totally raid your closet... 
 Sporty is my style! Do you wear colors or nah? Fab, I bet you look great in everything! Where are you going in your hot new outfit?
  • 55. Designers are content experts Icons by Sarah Rudkin Developers Build the machine Domain experts
 Have the domain specific knowledge Designers • Content oversight for training: 
 What makes good training data? • Mediator between engineering and domain experts • Ethical considerations
  • 56. ethics matter Machines learn from us
 We choose what to teach We need to • challenge and stress test from a diverse point of view • put humans before technology
 (once again) • bring our principles of what good design is to the AI world This is a design task
  • 57. Machine Learning is 
 everywhere Learn to see its opportunities Get a seat at the table now Understand the implications of using machine learning Bring Design principles into the mix to make empowering and ethical products
  • 59. Resources A visual introduction to machine learning 
 http://www.r2d3.us Machine Learning is Fun! 
 (the perfect series of articles to get you started)
 https://medium.com/@ageitgey/machine-learning-is-fun-80ea3ec3c471 30 Free Courses: Neural Networks, Machine Learning, AI
 https://www.datasciencecentral.com/profiles/blogs/neural-networks-for-machine-learning Watson Knowledge Studio 
 https://www.ibm.com/watson/developercloud/doc/wks/wks_overview_full.shtml 2 Minutes Papers: a youtube channel dedicated to condensing the results of scientific papers on artificial intelligence.
 https://www.youtube.com/channel/UCbfYPyITQ-7l4upoX8nvctg Realtime Multi-Person 2D Human Pose Estimation 
 https://www.youtube.com/watch?v=pW6nZXeWlGM BoxCar 2D: Computation Intelligence Car Evolution (Needs Flash)
 http://boxcar2d.com/ 
 Google AI Experiments
 https://experiments.withgoogle.com/collection/ai 
 Differences Between AI and Machine Learning, and Why it Matters
 https://medium.com/datadriveninvestor/differences-between-ai-and-machine-learning-and-why-it-matters-1255b182fc6