s e e d / / s e a r c h f o r e x t r a o r d i n a r y e ... · s e e d / / s e a r c h f o r e x...
TRANSCRIPT
S E E D / / S E A R C H F O R E X T R A O R D I N A R Y E X P E R I E N C E S D I V I S I O N
Deep Learning in Games
Martin Singh-Blom@singhblom
What is Machine Learning?
S E E D // Introduction
S E E D // Introduction
What is Artificial Intelligence?
or ...
S E E D // Introduction
Guess the function!
S E E D // Introduction
f (2) = 4
S E E D // Introduction
f (8) = 16
S E E D // Introduction
f (x) = 2x
S E E D // Introduction
How does the machine guess?
S E E D // Middle
It learns from the data.
S E E D // Middle
S E E D // Middle
(That’s why we call it machine learning!)
It learns from the data.
S E E D // How do the machines learn?
x
y
Guess a straight line!
S E E D // How do the machines learn?
x
y
Guess a straight line!
f (x) = 9.5 – 0.3x
S E E D // How do the machines learn?
x
y
Guess a straight line!
f (x) = 9.5 – 0.3x
S E E D // How do the machines learn?
x
y
Guess a straight line!
f (x) = 0.3 + 0.6x
S E E D // How do the machines learn?
x
y
Guess a straight line!
f (x) = 0.3 + 0.6x
S E E D // How do the machines learn?
Guess a straight line!
f (x) = 0.3 + 0.6x
f (x) = 9.5 – 0.3x
S E E D // How do the machines learn?
1. Data – f ( x ) = y pairs.2. A way to tell the machine how bad a guess is.3. Some idea of what kind of function the machine is allowed to guess –
straight line? Curve? Something stranger?
That is all there is to it!
S E E D // How do the machines learn?
x
y
Guess a straight line!
S E E D // How do the machines learn?
Guess a straight line!
What is Deep Learning?
S E E D // Deep Learning
What are Artificial Neural Networks?
S E E D // Deep Learning
f
S E E D // Deep learning
S E E D // Deep Learning
S E E D // Deep learning
f ( ) = 8
S E E D // Deep learning
f ( ) = 8
S E E D // Deep learning
f ( ) = 5
S E E D // Deep learning
f ( ) = 0
S E E D // Deep learning
f ( ) = 6
S E E D // Deep learning
S E E D // Deep learning
S E E D // Deep learning
f ( )
S E E D // Deep learning
f ( ) = cat
S E E D // Deep learning
”I saw it in a theater once and
it was great.
It was very… I don’t know,
a little dark.
I like the psychological
effects and the way it
portrays the characters.”
f ( ) =”Have you seen
Suicide Squad?”
S E E D // Deep learning
f ( ) = ”A person flying a kite
on a beach”
S E E D // Deep learning
f ( ) =”A coffee, please.”
S E E D // Deep learning
f ( ) =”A coffee, please.”
S E E D // Deep learning
f ( ) =
S E E D // Deep learning
Agents in Games
S E E D // Agents in Games
S E E D // Agents in Games
S E E D // Agents in Games
S E E D // Agents in Games
f ( ) =
S E E D // TOPIC
S E E D // Deep learning
AlphaGo
Animation
S E E D // Animation
S E E D // Animation
S E E D // Animation
f ( ) =
Audio-Driven Facial Animation by Joint End-to-End Learning of Pose and Emotion, Karras et al., 2017, NVIDIA
Learn all the things!
S E E D // All the things!
S E E D // All the things!
f ( ) =
Physics
Physics Forests: Real-time Fluid Simulation using Machine Learning, Ladicky et al., 2015, www.physicsforests.com
S E E D // All the things!
S E E D // All the things!
f ( ) =
Realtime Multi-Person 2D Human Pose Estimation using Part Affinity Fields, Cao et al., 2017
S E E D // All the things!
f ( ) =
Phase-Functioned Neural Networks for Character Control, Holden, 2017
S E E D // All the things!
f ( ) =
f ( ) = 8
f ( ) =
f ( ) =f ( ) =
f ( ) = cat
f ( ) =
”I saw it in a theater once and
it was great.
It was very… I don’t know,
a little dark.
I like the psychological
effects and the way it
portrays the characters.”
”Have you seen
Suicide Squad?”
f ( ) = ”A coffee, please.”
f ( ) =”A coffee, please.”
S E E D // Final remark
Instead of programming – showing
Same method for every problem
Greatest paradigm change in computing since transistors
It’s all just function guessing – or – A new paradigm for computing
FIN
S E E D // Thank you
StockholmHector Anadon Leon
Jorge del Val Santos
Mattias Teye
Anastasia Opara
Camilo Gordillo
Joakim Bergdahl
Jack Harmer
Linus Gisslén
Henrik Johansson
Paul Greveson
Niklas Nummelin
Ken Brown
Mark Kyobe
Effeli Holst
Jenna Frisk
Ida Winterhaven
Tomasz Stachowiak
Colin Barré-Brisebois
Graham Wihlidal
Lars Sjöström
Daniel Lundin
MontrealMathieu Lamarre
Etienne Danvoye
Los AngelesCarlos Ochoa
JP Lewis
Binh Le
Henrik Halen
John Courte
Special thank you toMagnus Nordin
Johan Andersson