SlideShare une entreprise Scribd logo
1  sur  52
Télécharger pour lire hors ligne
SOME EXPERIMENTS I HAVE DONE
WITH ART + DEEP LEARNING
Jason Toy
THE PRESENTATION
show some of my experiments, both testing the limits of other
people’s models and training my own models
overview of how the models work
for artists and machine learners in the audience, i tried to make it
so you will all learn a little
hopefully inspire some of you to go out and build something
awesome
MY BACKGROUND - JASONTOY
my main passion is general artificial intelligence
studied math and computer science
generalists, program a little of everything, master of nothing
founded a couple of companies: rubynow, socmetrics - using ML for
mining social media
CEO of filepicker,sold in beginning of 2016
exploring the intersection of machine learning,art, entrepreneurship
DEEP LEARNINGVSTRADITIONAL
MACHINE LEARNING
mostly automated feature extraction
DEEP LEARNINGVSTRADITIONAL
MACHINE LEARNING
much better at learning nonlinear relationships
WHAT IS GENERATIVE
MODELING
generative vs discriminative
architect of models
GM around for a long time - used in architect, design,games,etc
miniature systems that mimic something in real life,“artist in a
box”
more fun; I'm not as interested to increase ad clickthrough rates
DISCRIMINATIVEVS GENERATIVE
generative:
naive bayes
LDA
deep learning
discriminative:
SVM
random forest
linear/logistic
regression
GENERATIVE DEEP MODELS
tweak-able output w/ vectors
EXPERIMENTS
CHAR-RNN
“I'm not going anywhere. I will bring the poorly educated back
bigger and better. It's an incredible movement. ”
“We're losing companies, the economy.We are going to save it.
We're going to bring the party. Let's Make America Great Again”
“I want to thank the volunteers.They've been unbelievable, they
work like endlessly, you know, they don't want to die. My
leadership is good”
CHAR-RNN
1vanilla (image classification) 2 sequence output (image -> text)
3 sequence input ( sentiment analysis)
4 seq2seq (machine translation) 5 synced seq2seq (video
classification)
CHAR-RNN
RNN - recurrent because they perform the same task for every
element of a sequence; typically 2-3 layers
LSTM - long short term memory
similar, state is calculated differently
MY CHAR-RNN EXPERIMENTS
what does Hellen Keller think?
seeing is like or inspirents of a kiss licks, in child, for the last decting
of accomplish with me for the mistakes in silence is to keep the
moments filled whiter, the chaps of the house language was sends a
humanise.
i wish i could presepred its repepenting and the days like the poor
discuss of language of the poem in the letters, dotiment in the endless
good and eager and over the charicality of the hall of rubbings that I
hapmende the comprehend, the birds like your mind to perhaps the
not wind I should do?
MY CHAR-RNN EXPERIMENTS
“i love you. Now her before it just numberse idevening with the
press over. I was probably ever need to ever admit? Right” -
Trump
“life is an economy. I was in the LGBT communities can to the
worst of the gun not only the fight are of us safe and I start up
these are not grow…” - Hillary
FUTURE CHAR-RNN
EXPERIMENTS
train a model to talk like a person with little data? transfer
learning?
could we train a model off of a standard “human” model ?
could we train a model to talk in different emotions/styles?
DEEP DREAMING / INCEPTION
A MACHINE LEARNING IMAGE
CLASSIFIER
LAYERS LEARNED FEATURES
architects:
imagenet
googlenet
alexnet
GOOGLENET
LAYER AMPLIFICATION
objective function: activate as many neurons in a layer
key trick: push back to image
feedback loop
choose different layers for different effects:
conv2/3x3,inception_3a,etc
TEST IMAGE
–Johnny Appleseed
“Type a quote here.”
TRAINING MY OWN DREAMS
INCEPTION FUTURE
EXPERIMENTS
train with different image sets - sea life, reptiles?
different objective function - activate only 1 group of neurons?
selective regions of hallucinating?
testing different network architects
NEURALSTYLE
Paint images in the style of any painting
A NEURAL ALGORITHM OF
ARTISTIC STYLE
paper: http://arxiv.org/abs/1508.06576
The key finding of this paper is that the representations of
content and style in the CNNs are separable.
CNNs - convolutional Neural Network
high layers in the network act as the content of the image
style computed from multiple layers’ filter responses
]
?{;.
/ΠK
;
NEURALSTYLE FUTURE
EXPERIMENTS
can we automatically find the “good” images from a combination?
can we know beforehand if a combo style/content will look
good?
currently trained on vggnet data, what happens if we train it on a
different data set, will the art look different?
will a different architect make better art?
MULTIMODAL! STORYTELLING
I ACCIDENTALLY GAVETHE ANIMAL
BACK OF MY HEAD , BREATHING
DEEPLY .THERE WAS NO DOUBT IN
HER EYES ,AND I COULDTELL BY
THE LOOK ON HIS FACETHAT HE
DID N'T APPROVE OF WHAT WAS
HAPPENINGTO ME . IN FACT , IT
MUST HAVE BEEN ONE OFTHOSE
RARE OCCASIONS ,AS WELL AS A
PET ANIMAL . HER SCENT FILLED
THE AIR .THAT 'S WHAT SHE WAS
LOOKING FOR ,AND NOW SHE
HADTO STAY AWAKE LONG
ENOUGHTO DIG UPTHE LEASH
SKIP-THOUGHTVECTORS
sentence -> vectors
TRUMP STORYTELLER
FUTURE NEURAL STORY
EXPERIMENTS
train with different text
a “seeing” Hellen Keller version
train on different visual features
AND MANY OTHER EXPERIMENTS…….
HOPEFULLY INSPIRING
DATA IS ESSENTIAL
many of these models are built on public datasets
always has been a problem; bigger problem for DL and general
models
very hard to get data; how can this be solved?
constantly on my mind ; lets connect me if interested
DL IS NOT ALL FUN AND
UNICORNS
data issue
specialized software/hardware pipelines; GPUs
be prepared to wait; think weeks, not hours
model tuning
architect tuning
techniques and architects changing everyday
WHY?
I dream of building larger models
AGI and multi modal models
larger experiments
want to collaborate with cool artists and coders
fun? lets talk!
LINK APPENDIX
STUDY LINKS
what is deep learning: http://www.jtoy.net/2016/02/14/opening-
up-deep-learning-for-everyone.html
generative models: https://en.wikipedia.org/wiki/
Generative_model
discriminative models: https://en.wikipedia.org/wiki/
Discriminative_model
TEST LIVE MODEL LINKS
trump char-rnn model: http://somatic.io/models/WZmmBjZ9
neural style model: http://www.somatic.io/models/5BkaqkMR
neural talk model: http://somatic.io/models/qoEGanRe
romance story telling: http://somatic.io/models/2n6g7RZQ
LINKS
VGG net data used: http://www.robots.ox.ac.uk/~vgg/research/
very_deep/
tensorflow version: https://github.com/anishathalye/neural-style
neural style paper: http://arxiv.org/abs/1508.06576
char-rnn code: https://github.com/somaticio/char-rnn-tensorflow
mscoco: http://mscoco.org
imagenet: http://image-net.org/
LINKS
char-rnn: https://github.com/somaticio/char-rnn-tensorflow
tensorflow char-rnn tutorial: https://www.tensorflow.org/
versions/r0.9/tutorials/seq2seq/index.html#recurrent-neural-
networks
neuralstyle: https://github.com/anishathalye/neural-style
–John Dewey
“Every great advance in science has issued from a new
audacity of imagination.”
Jason Toy
jason@somatic.io
I write here:
http://jtoy.net http://somatic.io/bog
my models here: http://somatic.io
@jtoy
QUESTIONS?

Contenu connexe

Similaire à Experiments with Art and Deep Learning

Deep Learning from Scratch - Building with Python from First Principles.pdf
Deep Learning from Scratch - Building with Python from First Principles.pdfDeep Learning from Scratch - Building with Python from First Principles.pdf
Deep Learning from Scratch - Building with Python from First Principles.pdfYungSang1
 
Applied And Persuasive Applications For Museums
Applied And Persuasive Applications For MuseumsApplied And Persuasive Applications For Museums
Applied And Persuasive Applications For MuseumsPietro Polsinelli
 
Refactoring (the brain) for developers
Refactoring (the brain) for developers Refactoring (the brain) for developers
Refactoring (the brain) for developers Ionel Condor
 
LASTconf 2018 - System Mapping: Discover, Communicate and Explore the Real Co...
LASTconf 2018 - System Mapping: Discover, Communicate and Explore the Real Co...LASTconf 2018 - System Mapping: Discover, Communicate and Explore the Real Co...
LASTconf 2018 - System Mapping: Discover, Communicate and Explore the Real Co...Colin Panisset
 
Culture And Aesthetic Revisited
Culture And Aesthetic RevisitedCulture And Aesthetic Revisited
Culture And Aesthetic RevisitedAdam Keys
 
Designing An Applied Game For Your Museum - Workshop
Designing An Applied Game For Your Museum - WorkshopDesigning An Applied Game For Your Museum - Workshop
Designing An Applied Game For Your Museum - WorkshopPietro Polsinelli
 
Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016Grigory Sapunov
 
Bestseller Analysis: Visualization Fiction (for PyData Boston 2013)
Bestseller Analysis: Visualization Fiction (for PyData Boston 2013)Bestseller Analysis: Visualization Fiction (for PyData Boston 2013)
Bestseller Analysis: Visualization Fiction (for PyData Boston 2013)Lynn Cherny
 
What Developers Need To Know About Visual Design
What Developers Need To Know About Visual DesignWhat Developers Need To Know About Visual Design
What Developers Need To Know About Visual DesignBen Hall
 
Emotion detection using cnn.pptx
Emotion detection using cnn.pptxEmotion detection using cnn.pptx
Emotion detection using cnn.pptxRADO7900
 
Hpai class 12 - potpourri & perception - 032620
Hpai   class 12 - potpourri & perception - 032620Hpai   class 12 - potpourri & perception - 032620
Hpai class 12 - potpourri & perception - 032620melendez321
 
Thinking Like a Storyteller
Thinking Like a StorytellerThinking Like a Storyteller
Thinking Like a StorytellerCindy Chastain
 
Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial IntelligenceNiket Singh
 
Pin On Reluctant Homeschool Writers
Pin On Reluctant Homeschool WritersPin On Reluctant Homeschool Writers
Pin On Reluctant Homeschool WritersTonia Wallace
 

Similaire à Experiments with Art and Deep Learning (20)

Presentation unit 2 programming
Presentation  unit 2 programmingPresentation  unit 2 programming
Presentation unit 2 programming
 
Deep Learning from Scratch - Building with Python from First Principles.pdf
Deep Learning from Scratch - Building with Python from First Principles.pdfDeep Learning from Scratch - Building with Python from First Principles.pdf
Deep Learning from Scratch - Building with Python from First Principles.pdf
 
Applied And Persuasive Applications For Museums
Applied And Persuasive Applications For MuseumsApplied And Persuasive Applications For Museums
Applied And Persuasive Applications For Museums
 
Refactoring (the brain) for developers
Refactoring (the brain) for developers Refactoring (the brain) for developers
Refactoring (the brain) for developers
 
Applied and persuasive: playful learning
Applied and persuasive: playful learningApplied and persuasive: playful learning
Applied and persuasive: playful learning
 
Data, The Android
Data, The AndroidData, The Android
Data, The Android
 
ELO Sonnet
ELO SonnetELO Sonnet
ELO Sonnet
 
LASTconf 2018 - System Mapping: Discover, Communicate and Explore the Real Co...
LASTconf 2018 - System Mapping: Discover, Communicate and Explore the Real Co...LASTconf 2018 - System Mapping: Discover, Communicate and Explore the Real Co...
LASTconf 2018 - System Mapping: Discover, Communicate and Explore the Real Co...
 
Culture And Aesthetic Revisited
Culture And Aesthetic RevisitedCulture And Aesthetic Revisited
Culture And Aesthetic Revisited
 
Midterm Pecha Kucha
Midterm Pecha KuchaMidterm Pecha Kucha
Midterm Pecha Kucha
 
Designing An Applied Game For Your Museum - Workshop
Designing An Applied Game For Your Museum - WorkshopDesigning An Applied Game For Your Museum - Workshop
Designing An Applied Game For Your Museum - Workshop
 
Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016
 
Flow based-1994
Flow based-1994Flow based-1994
Flow based-1994
 
Bestseller Analysis: Visualization Fiction (for PyData Boston 2013)
Bestseller Analysis: Visualization Fiction (for PyData Boston 2013)Bestseller Analysis: Visualization Fiction (for PyData Boston 2013)
Bestseller Analysis: Visualization Fiction (for PyData Boston 2013)
 
What Developers Need To Know About Visual Design
What Developers Need To Know About Visual DesignWhat Developers Need To Know About Visual Design
What Developers Need To Know About Visual Design
 
Emotion detection using cnn.pptx
Emotion detection using cnn.pptxEmotion detection using cnn.pptx
Emotion detection using cnn.pptx
 
Hpai class 12 - potpourri & perception - 032620
Hpai   class 12 - potpourri & perception - 032620Hpai   class 12 - potpourri & perception - 032620
Hpai class 12 - potpourri & perception - 032620
 
Thinking Like a Storyteller
Thinking Like a StorytellerThinking Like a Storyteller
Thinking Like a Storyteller
 
Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
 
Pin On Reluctant Homeschool Writers
Pin On Reluctant Homeschool WritersPin On Reluctant Homeschool Writers
Pin On Reluctant Homeschool Writers
 

Dernier

Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Paola De la Torre
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesSinan KOZAK
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024The Digital Insurer
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Servicegiselly40
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘RTylerCroy
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking MenDelhi Call girls
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure servicePooja Nehwal
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonetsnaman860154
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEarley Information Science
 
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsTop 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsRoshan Dwivedi
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilV3cube
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationRadu Cotescu
 

Dernier (20)

Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen Frames
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
 
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsTop 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of Brazil
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 

Experiments with Art and Deep Learning

  • 1. SOME EXPERIMENTS I HAVE DONE WITH ART + DEEP LEARNING Jason Toy
  • 2. THE PRESENTATION show some of my experiments, both testing the limits of other people’s models and training my own models overview of how the models work for artists and machine learners in the audience, i tried to make it so you will all learn a little hopefully inspire some of you to go out and build something awesome
  • 3. MY BACKGROUND - JASONTOY my main passion is general artificial intelligence studied math and computer science generalists, program a little of everything, master of nothing founded a couple of companies: rubynow, socmetrics - using ML for mining social media CEO of filepicker,sold in beginning of 2016 exploring the intersection of machine learning,art, entrepreneurship
  • 5. DEEP LEARNINGVSTRADITIONAL MACHINE LEARNING much better at learning nonlinear relationships
  • 6. WHAT IS GENERATIVE MODELING generative vs discriminative architect of models GM around for a long time - used in architect, design,games,etc miniature systems that mimic something in real life,“artist in a box” more fun; I'm not as interested to increase ad clickthrough rates
  • 7. DISCRIMINATIVEVS GENERATIVE generative: naive bayes LDA deep learning discriminative: SVM random forest linear/logistic regression
  • 10. CHAR-RNN “I'm not going anywhere. I will bring the poorly educated back bigger and better. It's an incredible movement. ” “We're losing companies, the economy.We are going to save it. We're going to bring the party. Let's Make America Great Again” “I want to thank the volunteers.They've been unbelievable, they work like endlessly, you know, they don't want to die. My leadership is good”
  • 11. CHAR-RNN 1vanilla (image classification) 2 sequence output (image -> text) 3 sequence input ( sentiment analysis) 4 seq2seq (machine translation) 5 synced seq2seq (video classification)
  • 12. CHAR-RNN RNN - recurrent because they perform the same task for every element of a sequence; typically 2-3 layers LSTM - long short term memory similar, state is calculated differently
  • 13. MY CHAR-RNN EXPERIMENTS what does Hellen Keller think? seeing is like or inspirents of a kiss licks, in child, for the last decting of accomplish with me for the mistakes in silence is to keep the moments filled whiter, the chaps of the house language was sends a humanise. i wish i could presepred its repepenting and the days like the poor discuss of language of the poem in the letters, dotiment in the endless good and eager and over the charicality of the hall of rubbings that I hapmende the comprehend, the birds like your mind to perhaps the not wind I should do?
  • 14. MY CHAR-RNN EXPERIMENTS “i love you. Now her before it just numberse idevening with the press over. I was probably ever need to ever admit? Right” - Trump “life is an economy. I was in the LGBT communities can to the worst of the gun not only the fight are of us safe and I start up these are not grow…” - Hillary
  • 15. FUTURE CHAR-RNN EXPERIMENTS train a model to talk like a person with little data? transfer learning? could we train a model off of a standard “human” model ? could we train a model to talk in different emotions/styles?
  • 16. DEEP DREAMING / INCEPTION
  • 17. A MACHINE LEARNING IMAGE CLASSIFIER
  • 19.
  • 21. LAYER AMPLIFICATION objective function: activate as many neurons in a layer key trick: push back to image feedback loop choose different layers for different effects: conv2/3x3,inception_3a,etc
  • 23.
  • 25.
  • 26. TRAINING MY OWN DREAMS
  • 27.
  • 28.
  • 29.
  • 30. INCEPTION FUTURE EXPERIMENTS train with different image sets - sea life, reptiles? different objective function - activate only 1 group of neurons? selective regions of hallucinating? testing different network architects
  • 31. NEURALSTYLE Paint images in the style of any painting
  • 32. A NEURAL ALGORITHM OF ARTISTIC STYLE paper: http://arxiv.org/abs/1508.06576 The key finding of this paper is that the representations of content and style in the CNNs are separable. CNNs - convolutional Neural Network
  • 33. high layers in the network act as the content of the image style computed from multiple layers’ filter responses
  • 34.
  • 36. NEURALSTYLE FUTURE EXPERIMENTS can we automatically find the “good” images from a combination? can we know beforehand if a combo style/content will look good? currently trained on vggnet data, what happens if we train it on a different data set, will the art look different? will a different architect make better art?
  • 38. I ACCIDENTALLY GAVETHE ANIMAL BACK OF MY HEAD , BREATHING DEEPLY .THERE WAS NO DOUBT IN HER EYES ,AND I COULDTELL BY THE LOOK ON HIS FACETHAT HE DID N'T APPROVE OF WHAT WAS HAPPENINGTO ME . IN FACT , IT MUST HAVE BEEN ONE OFTHOSE RARE OCCASIONS ,AS WELL AS A PET ANIMAL . HER SCENT FILLED THE AIR .THAT 'S WHAT SHE WAS LOOKING FOR ,AND NOW SHE HADTO STAY AWAKE LONG ENOUGHTO DIG UPTHE LEASH
  • 40.
  • 42. FUTURE NEURAL STORY EXPERIMENTS train with different text a “seeing” Hellen Keller version train on different visual features
  • 43. AND MANY OTHER EXPERIMENTS……. HOPEFULLY INSPIRING
  • 44. DATA IS ESSENTIAL many of these models are built on public datasets always has been a problem; bigger problem for DL and general models very hard to get data; how can this be solved? constantly on my mind ; lets connect me if interested
  • 45. DL IS NOT ALL FUN AND UNICORNS data issue specialized software/hardware pipelines; GPUs be prepared to wait; think weeks, not hours model tuning architect tuning techniques and architects changing everyday
  • 46. WHY? I dream of building larger models AGI and multi modal models larger experiments want to collaborate with cool artists and coders fun? lets talk!
  • 48. STUDY LINKS what is deep learning: http://www.jtoy.net/2016/02/14/opening- up-deep-learning-for-everyone.html generative models: https://en.wikipedia.org/wiki/ Generative_model discriminative models: https://en.wikipedia.org/wiki/ Discriminative_model
  • 49. TEST LIVE MODEL LINKS trump char-rnn model: http://somatic.io/models/WZmmBjZ9 neural style model: http://www.somatic.io/models/5BkaqkMR neural talk model: http://somatic.io/models/qoEGanRe romance story telling: http://somatic.io/models/2n6g7RZQ
  • 50. LINKS VGG net data used: http://www.robots.ox.ac.uk/~vgg/research/ very_deep/ tensorflow version: https://github.com/anishathalye/neural-style neural style paper: http://arxiv.org/abs/1508.06576 char-rnn code: https://github.com/somaticio/char-rnn-tensorflow mscoco: http://mscoco.org imagenet: http://image-net.org/
  • 51. LINKS char-rnn: https://github.com/somaticio/char-rnn-tensorflow tensorflow char-rnn tutorial: https://www.tensorflow.org/ versions/r0.9/tutorials/seq2seq/index.html#recurrent-neural- networks neuralstyle: https://github.com/anishathalye/neural-style
  • 52. –John Dewey “Every great advance in science has issued from a new audacity of imagination.” Jason Toy jason@somatic.io I write here: http://jtoy.net http://somatic.io/bog my models here: http://somatic.io @jtoy QUESTIONS?