testing machine learning, learning machine testing. eurostar 2016 rik marselis

43
Testing Machine Learning, Learning Machine Testing Rik Marselis, Sogeti Nederland [email protected]

Upload: rik-marselis

Post on 11-Apr-2017

83 views

Category:

Technology


6 download

TRANSCRIPT

Page 1: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Testing Machine Learning,

Learning Machine Testing

Rik Marselis, Sogeti Nederland

[email protected]

Page 2: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

1980

2007 2012 20122008

Workgroup-member

20142009

Rik Marselis@rikmarselis

Page 3: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Who uses a robot today?

Page 4: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

You will use multiple within just a few years!!

Page 5: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

And please realise: these are robots too!

Chatbot Self-driving mini-bus

Page 6: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

WePod: self-driving bus

This minibus is allowed on the road now in Wageningen (the Netherlands) andwas tested by mySogeti-colleaguesDragan, Hugo andRemco.

Page 7: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Robots, ok, but in less than 10 years????

Well;

Did you understand this

trafficsign 10 years ago?

That’s how fast technology

progresses!!

Page 8: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

What is Robotics?

• Internet of Things (IoT)

• Big data analytics

• Cloud technology

• Machine learning

• Artificial Intelligence

Robotics

Definition: A robot is a machine that gathers information about its environment by input of sensors and based on this input changes its behavior. Combined with machine learning and artificial intelligence the robot’s reactions over time get more and more adequate. The use of Internet of Things, Bid Data Analytics and Cloud technology make a robot versatile. Robots may appear in a physical shape (e.g. a tin man) or non-physical (e.g. chatbot).

Page 9: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Traditional: Robots for dull & dangerous work

Page 10: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

New possibilities, just 2 examples

Exo-skeleton

Healthcare disabled peopleTransport drone delivery

Page 11: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

New risks

The bull doesn’t likethe manure robot andconstantly pushes it off its track. (to much frustration of the farmer who needs to cometo rescue the robot ;-)

Page 12: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

New angles of quality, aimed at roboticsMechanical

Electrical

Information Processing

Machine Intelligence

Business Impact

Social Impact

e.g. Ethics

e.g. Embodiment

e.g. Empathy

Page 13: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Part 1:

Testing machine learning

Page 14: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Machine Learning in the 80’s

Page 15: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Machine learning today: demonstrating

Page 16: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Machine learning today: demonstrating

Page 17: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Learning by creating rules

How can we find the rules that self-drivingcars must use?

Ask you!

moralmachine.mit.edu

Page 18: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Some

results

Page 19: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Machine learning or machine training?

• A learning machine consists of a complex network

of algorithms

• The learning machine has very many “dials and

switches”

• Making sure the machine learns the right things is

just like ordinary training (well, in a different way…)

Page 20: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Testing Machine Intelligence

• Human: “Dear robot please get me a softdrink”

• Robot: “Dear human here is your cola”

• Is this the correct output?

• No!

In Sweden I want:

Page 21: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Testing Machine Intelligence

• Human: “Dear robot please get me a softdrink”

• Robot: “Dear human it’s Saturday

evening now, so here is your beer”

• Is this the correct output?

• After studying your behavior,

the robot knows your patterns

Page 22: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Testing traditional IT vs. machine intelligence

Traditional (example):

• 1 + 1 = ?

• There’s only one correct output

With Machine Intelligence (example):

• Prepare a meal

• When is the meal “good enough”?

• Is it always the same meal?

2

Page 23: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Two sides of testing machine intelligence

• Testing the output

This we know from traditional testing,

but it’s hard to predict outputs, the

result may be different every time.

• Testing the input

If the machine gets the right input

it will learn and do the right things.

Page 24: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

To control the results of AI:

control the inputs…

Page 25: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Helpful chatbots?

• There’s a very thin line between a robot that is not helpful,

a robot that is helpful and a robot that’s too helpful

Page 26: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Helpful chatbots?

The uncanny valley:

Page 27: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

What is the role of the tester?

• The tester must see whether the intelligent

machine will maintain the intended behavior in live

operation

• In a way the tester is the psychologist of the

intelligent machine

• A tester must ask even more questions than

before !!

Note: I picked up the idea of the tester being the psychologist of robots from James Bach.

Page 28: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

It’s no longer about right or wrong

• Testing intelligent machines is not an easy check

whether the result is right or wrong

• It becomes an appraisal of a specific response in a

certain situation with a certain amount of

knowledge for a certain audience

• If these parameters change the right behavior will

also change

Page 29: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

After finishing the test…

• The machine continues to learn and adapt…

• What about confidence?

• The test must result in the confidence that the

machine will learn and adapt in the right way…

Page 30: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Part 2:

Learning machine testing

Page 31: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Using a robot for dull or dangerous testing

• Mechanical tests use robot-arm

Page 32: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Using a robot for intelligent testing

• Functional tests use machine intelligence to

– create test cases and

– execute test cases

– and (important!!) to judge the results

Page 33: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Using a robot for testing physical objects

Page 34: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Using a robot for intelligent testing

• Non-functional tests use machine intelligence

For example intelligent performance testing

(not just simple transactions but a normal variety)

Page 35: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

People and Robots testing together

• Teamwork of person & robot

• Each does what it is best at

– Robot repetitive work

– Human creative work

Page 36: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Machine learning: unsupervised & supervised

Deep learning:

Robot learns at various

layers. Lower layers

are unsupervised.

Highest layer(s) is (are)

supervised.

Page 37: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Machine Intelligence generates test data

• Based on Big Data Analytics of live data

• This is so-called “weak intelligence”

The machine is only intelligent in a limited field

Page 38: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Machine Intelligence generates test cases

• Evolutionary algorithms

• Brute force testing

The machine is able to generate and execute

many many more test cases than a human tester

Page 39: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Conclusion

Page 40: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Testing machine learning

• Testing inputs is very important because the output

is not predictable

• The objective of testing is to gain confidence that

the machine will learn and develop itself in a right

way

Page 41: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Learning machine testing

• Test automation will go to the next level

• Use machine intelligence (e.g. big data analytics)

to create your optimal test data

• Use machine intelligence to create many more test

cases, execute them and analyze results

Page 42: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Conclusion…

As a tester better prepare yourself for:

• Testing of Robots

and

• Testing with Robots

Page 43: Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis

Thanks for attending my talk.

Any questions ???????????

Rik Marselis, Sogeti Nederland

[email protected]