Machine Learning
for Designers
Memi Beltrame - @bratwurstkomet
UXCamp Switzerland

Zurich, May 10. 2019
Machine Learning
for people with a
fuzzy idea of what it is
Memi Beltrame - @bratwurstkomet
Or rather
UXCamp Switzerland

Zurich, May 10. 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?
Netflix uses
machine learning
to predict the
match probability
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
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 use algorithms
to make predictions
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
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
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
Audio Text
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 and ethical 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
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:
Assisted Intelligence
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

Machine Learning for Designers - UX Camp Switzerland

  • 1.
    Machine Learning for Designers MemiBeltrame - @bratwurstkomet UXCamp Switzerland Zurich, May 10. 2019
  • 2.
    Machine Learning for peoplewith a fuzzy idea of what it is Memi Beltrame - @bratwurstkomet Or rather UXCamp Switzerland Zurich, May 10. 2019
  • 3.
    Design is becomingphysical, automated and connected
  • 4.
  • 5.
  • 6.
  • 7.
    otoscope This is an Itcan 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.
    The image issent to a service that tells me if I should go to a doctor or not.
  • 10.
    AI: Image recognition, Data analysis IndustrialDesign InteractionDesign Service Design
  • 11.
  • 12.
    What is MachineLearning?
  • 14.
    Netflix uses machine learning topredict the match probability
  • 15.
    machine learning: training machines toreceive input data and predict an output value
  • 16.
    3 methods howmachines learn Supervised learning You train the machine with data The machine learns to make predictions ✔ ❌
  • 17.
    3 methods howmachines learn Supervised learning You train the machine with data The machine learns to make predictions #1 method used in machine learning
  • 18.
    3 methods howmachines 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 somepizza 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 23 4 5 6 1 2 3 4 5 6 7 Average # of toppings per pizza Average # of pizzas per week
  • 21.
    Find patterns 1 23 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 23 4 5 6 1 2 3 4 5 6 7 Average # of toppings per pizza Average # of pizzas per week
  • 23.
    Take Action 1 23 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 howmachines 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 machineis 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.
  • 27.
    Reinforcement Learning After afew dozen generations the machine has succeded in creating a vehicle that looks like a car and can reliably drive
  • 28.
    #1 method: supervisedlearning 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
  • 29.
    #1 method: supervisedlearning 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
  • 30.
    #1 method: supervisedlearning Features Target 8
  • 31.
    #1 method: supervisedlearning Features Target owl
  • 32.
    #1 method: supervisedlearning • Train the machine to learn what matches and what does not • Train with edge cases Owl or Apple?
  • 33.
  • 34.
    how machines usealgorithms 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.
    how machines usealgorithms 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
  • 36.
    generic algorithms There aremany 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
  • 37.
    2 types ofalgorithms 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
  • 38.
    image recognition Chihuahua orMuffin? Most image recognition is about classification
  • 39.
    image recognition Real time Atmultiple scales For a varying number of recognizable elements Realtime Multi-Person 2D Human Pose Estimation
  • 40.
  • 41.
    is language likeimages? Images can be recognized because their data can be encoded Can we do the same with language?
  • 42.
    translation versus conversation Doyou have the time? Translation goal: Produce an equivalent Conversation goal: Understand the meaning Avez-vous l’heure? It’s 7pm.Yes
  • 43.
  • 44.
    statistical translation Each wordof the sentence can have several meanings.
  • 45.
    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.
  • 46.
  • 47.
  • 48.
    Audio Text conversational interfaces Machinelearning is a crucial part of these interfaces
  • 49.
    new challenges anddisciplines • recognizing intent • understanding context • voice and tone • shaping conversations in a humane and ethical way }Linguistics Ethics
  • 50.
    intent - whatdoes 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
  • 52.
    Elements that make
 this artificial: • Not picking up intent 
 „give me a spot on saturday“ • Literal repetition
  • 53.
    context context is evenharder than intent • the sequence in time • understanding the surroundings • semantic context 
 homonymy: " is not a #
  • 54.
    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.
  • 56.
    Designers are contentexperts 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
  • 57.
    ethics matter Machines learnfrom 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
  • 58.
    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.
  • 60.
    Resources A visual introductionto 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