SlideShare une entreprise Scribd logo
1  sur  13
Télécharger pour lire hors ligne
Digits that are not
Generating new types through deep neural nets
Mehdi Cherti, Balázs Kégl
LAL/LRI, CNRS
Université Paris-Saclay
Akın Kazakçı
MINES ParisTech,
PSL Research University
The Short Story
Why are we doing this?
How to determine the value of novelty?
The value of novelty is the blindspot of creativity research
(Kazakçı, 2014).
Computational creativity
Deep learning to the rescue?
• has enabled great progress in machine
learning
• Also, several promising work renewed
interest in computational creativity.
• Google created Magenta (nobody needs us
anymore)
Gatys et al. 2015
Deep learning
Yet
• main emphasis in DL research remains
learning to predict
• models are based on likelihood whereas
creativity is unlikely
• the initial breakthrough came from a
generative model
But the generative potential of
deep nets is largely unexplored
Fitness function barrier
• For most computational creativity systems, the value
function is fixed and predetermined
• This is a paradox. - And an obstacle for progress.
• Evolutionary approaches to computational creativity
bears these inherent limitations:
• Explicit fitness functions reflects system designer’s
preference for novelty - not the machine’s.
• We call this the fitness function barrier.
A program to go beyond the barrier
Ultimate objective:Try & get rid of hard-coded
value functions; let the system develop its own
A genuinely creative system needs to be able to develop its
own notion of value
Current work: Build a system
1. that can study & learn a referential set of objects (RS)
2. that can generate new objects that keep essential
features of RS but generate unseen types
3. that provides an experimental bench for developing
& testing various ways an agent can develop a value
function
Auto-associative neural nets
a.k.a auto-encoders
Learning to
disassemble
Learning to
build
- Auto-encoders have existed
for long time (Kramer 1991)
- Deep variants are more recent
(Hinton, Salakhutdinov, 2006;
Bengio 2009)
- A deep auto-encoder learns
successive transformations
that decompose and then
recompose a set of training
objects
- The depth allows learning a
hierarchy of transformations
The experimental setup
- Training data : MNIST, 70000 images of
handwritten digits of size 28x28
- We use a sparse convolutional auto-
encoder (3c1d) trained to:
- Encode : take an image and
transform it to a sparse code
- Decode : take the sparse code and
reconstruct the image
- Training objective is to minimize the
reconstruction error
Generating new symbols
- We use an iterative method to build symbols the has never seen:
- Start with a random image x0 = r,
- and force the network to construct (i.e. interpret)
- xk = f(xk-1), until convergence
- Our method is inspired by Bengio et al. (2013)
- By contrast to them, we do not constrain the net to generate only
known types (we do not consider unknown symbols as spurious)
Visualising the structure of generated images
Coloured clusters are original
MNIST digits (classes from 0
to 9)
The gray dots are newly
generated objects
New objects form new clusters
Using a clustering algorithm, we
recover coherent sets of new
symbols
A distance preserving projection of
digits to a two-dimensional space
(van der Maaten and Hinton 2008)
Creativity by fixations
LearnForceFixate
Summary
A genuinely creative system needs to be able to develop its
own notion of value.
Our system is a first step:
• It can effectively create new types of objects preserving abstract
and semantic properties of a domain.
• It provides an experimental setup that enables testing various
hypothesis.
• It provides a bridge between current research on machine
learning and creativity research.
Thank you
Mehdi Cherti, Balázs Kégl
{mehdi.cherti, balazskegl}@gmail.com
Akın Kazakçı
akin.kazakci@mines-paristech.fr

Contenu connexe

Tendances

An overview of machine learning
An overview of machine learningAn overview of machine learning
An overview of machine learningdrcfetr
 
Machine Learning ICS 273A
Machine Learning ICS 273AMachine Learning ICS 273A
Machine Learning ICS 273Abutest
 
Introduction to machine learning
Introduction to machine learningIntroduction to machine learning
Introduction to machine learningSangath babu
 
林守德/Practical Issues in Machine Learning
林守德/Practical Issues in Machine Learning林守德/Practical Issues in Machine Learning
林守德/Practical Issues in Machine Learning台灣資料科學年會
 
Python for data science
Python for data sciencePython for data science
Python for data sciencebotsplash.com
 
Learning to Compose Domain-Specific Transformations for Data Augmentation
Learning to Compose Domain-Specific Transformations for Data AugmentationLearning to Compose Domain-Specific Transformations for Data Augmentation
Learning to Compose Domain-Specific Transformations for Data AugmentationTatsuya Shirakawa
 
Recommendation system using collaborative deep learning
Recommendation system using collaborative deep learningRecommendation system using collaborative deep learning
Recommendation system using collaborative deep learningRitesh Sawant
 
Pybcn machine learning for dummies with python
Pybcn machine learning for dummies with pythonPybcn machine learning for dummies with python
Pybcn machine learning for dummies with pythonJavier Arias Losada
 
Data Science and Machine Learning with Tensorflow
 Data Science and Machine Learning with Tensorflow Data Science and Machine Learning with Tensorflow
Data Science and Machine Learning with TensorflowShubham Sharma
 
Europython - Machine Learning for dummies with Python
Europython - Machine Learning for dummies with PythonEuropython - Machine Learning for dummies with Python
Europython - Machine Learning for dummies with PythonJavier Arias Losada
 
A Hidden Markov Model Approach to Predict Students' Actions in an Adaptive an...
A Hidden Markov Model Approach to Predict Students' Actions in an Adaptive an...A Hidden Markov Model Approach to Predict Students' Actions in an Adaptive an...
A Hidden Markov Model Approach to Predict Students' Actions in an Adaptive an...Simon Bolivar University
 
PREDICTING STOCK PRICE MOVEMENTS BASED ON NEWSPAPER ARTICLES USING A NOVEL DE...
PREDICTING STOCK PRICE MOVEMENTS BASED ON NEWSPAPER ARTICLES USING A NOVEL DE...PREDICTING STOCK PRICE MOVEMENTS BASED ON NEWSPAPER ARTICLES USING A NOVEL DE...
PREDICTING STOCK PRICE MOVEMENTS BASED ON NEWSPAPER ARTICLES USING A NOVEL DE...webwinkelvakdag
 

Tendances (13)

An overview of machine learning
An overview of machine learningAn overview of machine learning
An overview of machine learning
 
Machine Learning ICS 273A
Machine Learning ICS 273AMachine Learning ICS 273A
Machine Learning ICS 273A
 
Introduction to machine learning
Introduction to machine learningIntroduction to machine learning
Introduction to machine learning
 
4.80 sy it
4.80 sy it4.80 sy it
4.80 sy it
 
林守德/Practical Issues in Machine Learning
林守德/Practical Issues in Machine Learning林守德/Practical Issues in Machine Learning
林守德/Practical Issues in Machine Learning
 
Python for data science
Python for data sciencePython for data science
Python for data science
 
Learning to Compose Domain-Specific Transformations for Data Augmentation
Learning to Compose Domain-Specific Transformations for Data AugmentationLearning to Compose Domain-Specific Transformations for Data Augmentation
Learning to Compose Domain-Specific Transformations for Data Augmentation
 
Recommendation system using collaborative deep learning
Recommendation system using collaborative deep learningRecommendation system using collaborative deep learning
Recommendation system using collaborative deep learning
 
Pybcn machine learning for dummies with python
Pybcn machine learning for dummies with pythonPybcn machine learning for dummies with python
Pybcn machine learning for dummies with python
 
Data Science and Machine Learning with Tensorflow
 Data Science and Machine Learning with Tensorflow Data Science and Machine Learning with Tensorflow
Data Science and Machine Learning with Tensorflow
 
Europython - Machine Learning for dummies with Python
Europython - Machine Learning for dummies with PythonEuropython - Machine Learning for dummies with Python
Europython - Machine Learning for dummies with Python
 
A Hidden Markov Model Approach to Predict Students' Actions in an Adaptive an...
A Hidden Markov Model Approach to Predict Students' Actions in an Adaptive an...A Hidden Markov Model Approach to Predict Students' Actions in an Adaptive an...
A Hidden Markov Model Approach to Predict Students' Actions in an Adaptive an...
 
PREDICTING STOCK PRICE MOVEMENTS BASED ON NEWSPAPER ARTICLES USING A NOVEL DE...
PREDICTING STOCK PRICE MOVEMENTS BASED ON NEWSPAPER ARTICLES USING A NOVEL DE...PREDICTING STOCK PRICE MOVEMENTS BASED ON NEWSPAPER ARTICLES USING A NOVEL DE...
PREDICTING STOCK PRICE MOVEMENTS BASED ON NEWSPAPER ARTICLES USING A NOVEL DE...
 

En vedette

Deep learning to the rescue - solving long standing problems of recommender ...
Deep learning to the rescue - solving long standing problems of recommender ...Deep learning to the rescue - solving long standing problems of recommender ...
Deep learning to the rescue - solving long standing problems of recommender ...Balázs Hidasi
 
2017 How Deep Learning Changes the Design Process (1)
2017 How Deep Learning Changes the Design Process (1)2017 How Deep Learning Changes the Design Process (1)
2017 How Deep Learning Changes the Design Process (1)Alexander Meinhardt
 
쉬운 예제 중심의 HTML5 / CSS / MediaQuery / JQuery 강의
쉬운 예제 중심의 HTML5 / CSS / MediaQuery / JQuery 강의쉬운 예제 중심의 HTML5 / CSS / MediaQuery / JQuery 강의
쉬운 예제 중심의 HTML5 / CSS / MediaQuery / JQuery 강의Minha Yang
 
2017 How Deep Learning Changes the Design Process (2)
2017 How Deep Learning Changes the Design Process (2)2017 How Deep Learning Changes the Design Process (2)
2017 How Deep Learning Changes the Design Process (2)Alexander Meinhardt
 
Artificial Intelligence - Past, Present and Future
Artificial Intelligence - Past, Present and FutureArtificial Intelligence - Past, Present and Future
Artificial Intelligence - Past, Present and FutureGrigory Sapunov
 
How Deep Learning Changes the Design Process #NEXT17
How Deep Learning Changes the Design Process #NEXT17How Deep Learning Changes the Design Process #NEXT17
How Deep Learning Changes the Design Process #NEXT17Alexander Meinhardt
 

En vedette (6)

Deep learning to the rescue - solving long standing problems of recommender ...
Deep learning to the rescue - solving long standing problems of recommender ...Deep learning to the rescue - solving long standing problems of recommender ...
Deep learning to the rescue - solving long standing problems of recommender ...
 
2017 How Deep Learning Changes the Design Process (1)
2017 How Deep Learning Changes the Design Process (1)2017 How Deep Learning Changes the Design Process (1)
2017 How Deep Learning Changes the Design Process (1)
 
쉬운 예제 중심의 HTML5 / CSS / MediaQuery / JQuery 강의
쉬운 예제 중심의 HTML5 / CSS / MediaQuery / JQuery 강의쉬운 예제 중심의 HTML5 / CSS / MediaQuery / JQuery 강의
쉬운 예제 중심의 HTML5 / CSS / MediaQuery / JQuery 강의
 
2017 How Deep Learning Changes the Design Process (2)
2017 How Deep Learning Changes the Design Process (2)2017 How Deep Learning Changes the Design Process (2)
2017 How Deep Learning Changes the Design Process (2)
 
Artificial Intelligence - Past, Present and Future
Artificial Intelligence - Past, Present and FutureArtificial Intelligence - Past, Present and Future
Artificial Intelligence - Past, Present and Future
 
How Deep Learning Changes the Design Process #NEXT17
How Deep Learning Changes the Design Process #NEXT17How Deep Learning Changes the Design Process #NEXT17
How Deep Learning Changes the Design Process #NEXT17
 

Similaire à Creativity through deep learning

MachinaFiesta: A Vision into Machine Learning 🚀
MachinaFiesta: A Vision into Machine Learning 🚀MachinaFiesta: A Vision into Machine Learning 🚀
MachinaFiesta: A Vision into Machine Learning 🚀GDSCNiT
 
How machines can take decisions
How machines can take decisionsHow machines can take decisions
How machines can take decisionsDeepu S Nath
 
How machines can take decisions
How machines can take decisionsHow machines can take decisions
How machines can take decisionsDeepu S Nath
 
Deep Learning Jump Start
Deep Learning Jump StartDeep Learning Jump Start
Deep Learning Jump StartMichele Toni
 
Build a simple image recognition system with tensor flow
Build a simple image recognition system with tensor flowBuild a simple image recognition system with tensor flow
Build a simple image recognition system with tensor flowDebasisMohanty37
 
DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101Felipe Prado
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learningAmr Rashed
 
How data science works and how can customers help
How data science works and how can customers helpHow data science works and how can customers help
How data science works and how can customers helpDanko Nikolic
 
7-200404101602.pdf
7-200404101602.pdf7-200404101602.pdf
7-200404101602.pdfssuser07e9f2
 
Predictive Coding and E-Discovery in 2015 and Beyond - LegalTechNYC 2013 ( Da...
Predictive Coding and E-Discovery in 2015 and Beyond - LegalTechNYC 2013 ( Da...Predictive Coding and E-Discovery in 2015 and Beyond - LegalTechNYC 2013 ( Da...
Predictive Coding and E-Discovery in 2015 and Beyond - LegalTechNYC 2013 ( Da...Daniel Katz
 
Pres Tesi LM-2016+transcript_eng
Pres Tesi LM-2016+transcript_engPres Tesi LM-2016+transcript_eng
Pres Tesi LM-2016+transcript_engDaniele Ciriello
 
A Friendly Introduction to Machine Learning
A Friendly Introduction to Machine LearningA Friendly Introduction to Machine Learning
A Friendly Introduction to Machine LearningHaptik
 
Interactive Machine Learning Appendix
Interactive  Machine Learning AppendixInteractive  Machine Learning Appendix
Interactive Machine Learning AppendixZitao Liu
 
AI In Actuarial Science
AI In Actuarial ScienceAI In Actuarial Science
AI In Actuarial ScienceAudrey Britton
 
WELCOME TO AI PROJECT shidhant mittaal.pptx
WELCOME TO AI PROJECT shidhant mittaal.pptxWELCOME TO AI PROJECT shidhant mittaal.pptx
WELCOME TO AI PROJECT shidhant mittaal.pptx9D38SHIDHANTMITTAL
 
Weave-D - 2nd Progress Evaluation Presentation
Weave-D - 2nd Progress Evaluation PresentationWeave-D - 2nd Progress Evaluation Presentation
Weave-D - 2nd Progress Evaluation Presentationlasinducharith
 
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...ijscai
 
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...ijscai
 

Similaire à Creativity through deep learning (20)

Null
NullNull
Null
 
MachinaFiesta: A Vision into Machine Learning 🚀
MachinaFiesta: A Vision into Machine Learning 🚀MachinaFiesta: A Vision into Machine Learning 🚀
MachinaFiesta: A Vision into Machine Learning 🚀
 
How machines can take decisions
How machines can take decisionsHow machines can take decisions
How machines can take decisions
 
How machines can take decisions
How machines can take decisionsHow machines can take decisions
How machines can take decisions
 
Deep Learning Jump Start
Deep Learning Jump StartDeep Learning Jump Start
Deep Learning Jump Start
 
Build a simple image recognition system with tensor flow
Build a simple image recognition system with tensor flowBuild a simple image recognition system with tensor flow
Build a simple image recognition system with tensor flow
 
DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
How data science works and how can customers help
How data science works and how can customers helpHow data science works and how can customers help
How data science works and how can customers help
 
Generative models
Generative modelsGenerative models
Generative models
 
7-200404101602.pdf
7-200404101602.pdf7-200404101602.pdf
7-200404101602.pdf
 
Predictive Coding and E-Discovery in 2015 and Beyond - LegalTechNYC 2013 ( Da...
Predictive Coding and E-Discovery in 2015 and Beyond - LegalTechNYC 2013 ( Da...Predictive Coding and E-Discovery in 2015 and Beyond - LegalTechNYC 2013 ( Da...
Predictive Coding and E-Discovery in 2015 and Beyond - LegalTechNYC 2013 ( Da...
 
Pres Tesi LM-2016+transcript_eng
Pres Tesi LM-2016+transcript_engPres Tesi LM-2016+transcript_eng
Pres Tesi LM-2016+transcript_eng
 
A Friendly Introduction to Machine Learning
A Friendly Introduction to Machine LearningA Friendly Introduction to Machine Learning
A Friendly Introduction to Machine Learning
 
Interactive Machine Learning Appendix
Interactive  Machine Learning AppendixInteractive  Machine Learning Appendix
Interactive Machine Learning Appendix
 
AI In Actuarial Science
AI In Actuarial ScienceAI In Actuarial Science
AI In Actuarial Science
 
WELCOME TO AI PROJECT shidhant mittaal.pptx
WELCOME TO AI PROJECT shidhant mittaal.pptxWELCOME TO AI PROJECT shidhant mittaal.pptx
WELCOME TO AI PROJECT shidhant mittaal.pptx
 
Weave-D - 2nd Progress Evaluation Presentation
Weave-D - 2nd Progress Evaluation PresentationWeave-D - 2nd Progress Evaluation Presentation
Weave-D - 2nd Progress Evaluation Presentation
 
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...
 
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...
 

Plus de Akin Osman Kazakci

Transformation digitale par l'IA et la valorisation des données
Transformation digitale par l'IA et la valorisation des données Transformation digitale par l'IA et la valorisation des données
Transformation digitale par l'IA et la valorisation des données Akin Osman Kazakci
 
Learning, Representations, Generative modelling
Learning, Representations, Generative modellingLearning, Representations, Generative modelling
Learning, Representations, Generative modellingAkin Osman Kazakci
 
Data Science for Business Managers - The bare minimum a manager should know
Data Science for Business Managers - The bare minimum a manager should knowData Science for Business Managers - The bare minimum a manager should know
Data Science for Business Managers - The bare minimum a manager should knowAkin Osman Kazakci
 
Data Science for Business Managers - Trends and Evolutions
Data Science for Business Managers - Trends and EvolutionsData Science for Business Managers - Trends and Evolutions
Data Science for Business Managers - Trends and EvolutionsAkin Osman Kazakci
 
Introduction to search and optimisation for the design theorist
Introduction to search and optimisation for the design theoristIntroduction to search and optimisation for the design theorist
Introduction to search and optimisation for the design theoristAkin Osman Kazakci
 
Innovative Design Workshop - HiggsML and beyond (Machine Learning in Particle...
Innovative Design Workshop - HiggsML and beyond (Machine Learning in Particle...Innovative Design Workshop - HiggsML and beyond (Machine Learning in Particle...
Innovative Design Workshop - HiggsML and beyond (Machine Learning in Particle...Akin Osman Kazakci
 

Plus de Akin Osman Kazakci (7)

Transformation digitale par l'IA et la valorisation des données
Transformation digitale par l'IA et la valorisation des données Transformation digitale par l'IA et la valorisation des données
Transformation digitale par l'IA et la valorisation des données
 
Learning, Representations, Generative modelling
Learning, Representations, Generative modellingLearning, Representations, Generative modelling
Learning, Representations, Generative modelling
 
Value of Data Science
Value of Data ScienceValue of Data Science
Value of Data Science
 
Data Science for Business Managers - The bare minimum a manager should know
Data Science for Business Managers - The bare minimum a manager should knowData Science for Business Managers - The bare minimum a manager should know
Data Science for Business Managers - The bare minimum a manager should know
 
Data Science for Business Managers - Trends and Evolutions
Data Science for Business Managers - Trends and EvolutionsData Science for Business Managers - Trends and Evolutions
Data Science for Business Managers - Trends and Evolutions
 
Introduction to search and optimisation for the design theorist
Introduction to search and optimisation for the design theoristIntroduction to search and optimisation for the design theorist
Introduction to search and optimisation for the design theorist
 
Innovative Design Workshop - HiggsML and beyond (Machine Learning in Particle...
Innovative Design Workshop - HiggsML and beyond (Machine Learning in Particle...Innovative Design Workshop - HiggsML and beyond (Machine Learning in Particle...
Innovative Design Workshop - HiggsML and beyond (Machine Learning in Particle...
 

Dernier

FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhisoniya singh
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Patryk Bandurski
 
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
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
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
 
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
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitecturePixlogix Infotech
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...shyamraj55
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxKatpro Technologies
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphNeo4j
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
 
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
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxOnBoard
 
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
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersThousandEyes
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 

Dernier (20)

FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
 
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
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
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
 
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
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC Architecture
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptx
 
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
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 

Creativity through deep learning

  • 1. Digits that are not Generating new types through deep neural nets Mehdi Cherti, Balázs Kégl LAL/LRI, CNRS Université Paris-Saclay Akın Kazakçı MINES ParisTech, PSL Research University
  • 2. The Short Story Why are we doing this?
  • 3. How to determine the value of novelty? The value of novelty is the blindspot of creativity research (Kazakçı, 2014).
  • 4. Computational creativity Deep learning to the rescue? • has enabled great progress in machine learning • Also, several promising work renewed interest in computational creativity. • Google created Magenta (nobody needs us anymore) Gatys et al. 2015 Deep learning Yet • main emphasis in DL research remains learning to predict • models are based on likelihood whereas creativity is unlikely • the initial breakthrough came from a generative model But the generative potential of deep nets is largely unexplored
  • 5. Fitness function barrier • For most computational creativity systems, the value function is fixed and predetermined • This is a paradox. - And an obstacle for progress. • Evolutionary approaches to computational creativity bears these inherent limitations: • Explicit fitness functions reflects system designer’s preference for novelty - not the machine’s. • We call this the fitness function barrier.
  • 6. A program to go beyond the barrier Ultimate objective:Try & get rid of hard-coded value functions; let the system develop its own A genuinely creative system needs to be able to develop its own notion of value Current work: Build a system 1. that can study & learn a referential set of objects (RS) 2. that can generate new objects that keep essential features of RS but generate unseen types 3. that provides an experimental bench for developing & testing various ways an agent can develop a value function
  • 7. Auto-associative neural nets a.k.a auto-encoders Learning to disassemble Learning to build - Auto-encoders have existed for long time (Kramer 1991) - Deep variants are more recent (Hinton, Salakhutdinov, 2006; Bengio 2009) - A deep auto-encoder learns successive transformations that decompose and then recompose a set of training objects - The depth allows learning a hierarchy of transformations
  • 8. The experimental setup - Training data : MNIST, 70000 images of handwritten digits of size 28x28 - We use a sparse convolutional auto- encoder (3c1d) trained to: - Encode : take an image and transform it to a sparse code - Decode : take the sparse code and reconstruct the image - Training objective is to minimize the reconstruction error
  • 9. Generating new symbols - We use an iterative method to build symbols the has never seen: - Start with a random image x0 = r, - and force the network to construct (i.e. interpret) - xk = f(xk-1), until convergence - Our method is inspired by Bengio et al. (2013) - By contrast to them, we do not constrain the net to generate only known types (we do not consider unknown symbols as spurious)
  • 10. Visualising the structure of generated images Coloured clusters are original MNIST digits (classes from 0 to 9) The gray dots are newly generated objects New objects form new clusters Using a clustering algorithm, we recover coherent sets of new symbols A distance preserving projection of digits to a two-dimensional space (van der Maaten and Hinton 2008)
  • 12. Summary A genuinely creative system needs to be able to develop its own notion of value. Our system is a first step: • It can effectively create new types of objects preserving abstract and semantic properties of a domain. • It provides an experimental setup that enables testing various hypothesis. • It provides a bridge between current research on machine learning and creativity research.
  • 13. Thank you Mehdi Cherti, Balázs Kégl {mehdi.cherti, balazskegl}@gmail.com Akın Kazakçı akin.kazakci@mines-paristech.fr