SlideShare a Scribd company logo
Computational Systems
FOSTERING CREATIVITY in
Dr. Sarah Shuchi, Postdoctoral Fellow
1
2
Human
Creativity
Computational
Creativity
Models of
Creativity
Human and machine
collaboration
Future of creative
computing
Outline
-What does it mean?
-Thinking process
-Creativity as process
-Goal
-CC in various domain
-Creative tool
-Data mining
-Machine learning
- Some essential conditions
- Human vs. machine
challenges
- Framework
Human Creativity
‘To solve day to day problem’
‘Novel, surprising and valuable’
3
Thought process of ordinary people’
‘Out of box thinking’
‘Social process’
‘Creativity is a process of thinking (both conscious and unconscious), arise to solve a problem in a specific
context (cultural and social), where the outcome of the process is novel, surprising and valuable.’
‘Effective surprise for its uniqueness’
http://flowpro.io/blog/creativity
Weisberg, R.W., Problem solving and creativity. The nature of creativity, 1988: p. 148-176.
Boden, M.A., What is creativity, in Dimensions of Creativity. 1994, The MIT Press: USA. p. 75-117.
Robinson, K., Unlocking creativity: A strategy for development. Belfast: Department of Culture Arts and Leisure, 2001.
Logical
Sequential
Analytical
Rational
Objective
Random
Intuitive
Holistic
Synthesizi
ng
Picture: https://www.linkedin.com/pulse/left-brain-vs-
right-hr-logical-creative-anya-chupryna
4
Explore
possibilitie
s
Divergent
thinking
Convergent
thinking
Decide
what to
doThinking process
5
CREATIVITY
Valuable
Novel
Surprising
Creativity as novelty, surprise and value
Historical Creative (H-creativity)
Physiologically Creative (P-creativity)
Combination - unfamiliar combinations of
familiar ideas
Exploration of
Conceptual space - Exploratory creativity rests
on some culturally accepted style
of thinking
Transformation - Transformation of space
Aesthetic
Moment of perceive
Judgement
Types of
creativity
6
Modelling Creativity
The Walla’s model
-Cognitive process of creativity
4 P model of Creativity
Amabile’s -Componential model
People
Product
Process Press
System view of Creativity
7
Input Processing Output
Enablersofcreativity
Mechanismofcreativity
Evaluationofcreativity
Knowledge
Motivation
Intuition
Curiosity
Autonomy
Divergent thinking
Conscious/unconscious
Novel
Valuable
Surprise (unusual,
unexpected, impossible)
People and interaction
Assessment
/evaluation
Creative processReason Artefacts
Environment / context
Really?
Are Computers Creative,
8
Computational Creativity
"What does it mean for a computer to be creative?
Design a program that can enhance human creativity without necessarily being
creative themselves.
Construct a program or computer capable of human-level creativity.
Formulate algorithmic perspective on human creative behaviour.
Goal
9
Maher, M., Merrick, K., & Macindoe, O. (2005). Can designs themselves be creative. Computational and Cognitive Models of Creative Design VI, 111-126.
Computer generated - Music, Jokes, mathematics, storey telling, painting
http://newatlas.com/creative-ai-algorithmic-art-painting-fool-aaron/36106/
10
What do you get when you cross a frog with road?
+
Q: What do you call a strange market?
A: A bizarre bazaar.
Q: What is the difference between leaves and a car?
A: One you brush and rake, the other you rush and
brake.
Q : What kind of murderer has fibre?
A : A cereal killer.
11
Computer as Creative tool
Photos: http://www.thepaintingfool.com/galleries/city_series/index.html
Colton, S. Automatic invention of fitness functions with application to scene generation. in Workshops on
Applications of Evolutionary Computation. 2008. Springer.
Colton, S. Creativity Versus the Perception of Creativity in Computational Systems. in AAAI spring symposium:
creative intelligent systems. 2008
Appreciative behaviours revolve around human emotions.
Number of painting styles that I can use to hopefully
enhance the emotional content of portraits
The imaginative behaviours achieved by
involving generative techniques from Artificial
Intelligence and Computer Graphics.
Skillful behaviours are based on simulating the
physical painting process.
12
Convolutional neural network
Gatys, L. A., Ecker, A. S., & Bethge, M. (2015). A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576.
Style
Reconstruction
Input Image
Content
reconstruction
Style
reconstructio
n
Machine learning and Creativity
Neural network on image data
Artistic Style Imitation
- By applying the style of
different artists to an arbitrary image
of their choice.
-Applying a simple neural network on
image data directly creates large
number of parameters .
- Convolutional Neural Networks
(CNNs) were introduced
13
Gatys, L. A., Ecker, A. S., & Bethge, M. (2015). A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576
https://deepdreamgenerator.com/gallery.
Machine learning and Creativity (continues)
Neural network on image data
Similar text - with training data, the models can generate similar
texts, for example, like Shakespeare plays
Chat bots - make use of the vast amount of data
Often conversations with bots can lack flow
At a glance, they do look
authentic
Usually, the images are generated in
iterations and in each iteration it is
zoomed into the image.
Google deep dream- published by
Google engineers
Text data
Little feeling or personality
associated with it
14
Neurocognitive model and Creativity
Creativity is a product of ordinary neurocognitive process
To create novel words – a neurocognitive model
inspired by the putative processes of brain
Results are surprisingly similar to those created by humans.
Associative
memory
Imagination
Filtering
Duch, W., & Pilichowski, M. (2007). Experiments with computational creativity. Neural Information Processing–Letters and Reviews, 11(4-6), 123-133
Murray, L.L., The effects of varying attentional demands on the word retrieval skills of adults with aphasia, right hemisphere brain damage, or no brain damage.
Brain and language, 2000. 72(1): p. 40-72.
Stores background
knowledge
Challenges
Most interesting
one
 Some words are already
developed
 Some words needs to be manually
removed
15
Big data and Creativity
By using big data computationally creative program can automatically
design and discover culinary recipes that are flavourful, healthy, and
novel!
The system understands food at the molecular level, learns the
essence of culinary traditions.
Thousands of ingredients, and a great deal of psychological data on
human perception
Maher, M., Merrick, K., & Macindoe, O. (2005). Can designs themselves be creative. Computational and Cognitive Models of Creative Design VI, 111-126.
- Learning evaluation function
- Generating complex artefacts
- Differentiate useful and useless data
16
Swarm intelligence, art creativity and freedom
Experiment with Swarmic freedom or controlled freedom
a b c d e
Pushing the swarms towards exploration, freedom is enhanced and by
encouraging exploitation, constraint is more emphasised.
- Finding a balance between exploration
and exploitation is an important
theoretical challenge
- Doesn’t really go beyond the expecting
simulation of human intelligence
al-Rifaie, M.M. and M. Bishop, Weak and strong computational creativity, in Computational creativity research: Towards creative machines. 2015, Springer. p. 37-49.
Machine creativity
and
17
18
Human
Creativity
Computational
Creativity
Human vs. Machine Creativity
Evaluation via assessment of
artefacts
Perspectives and criteria to evaluate
ideas and modify them
It is easy to generate random
combinations, but not many of
them may be valuable.
A rich store of world knowledge
(including cultural knowledge).
Lack of an associative memory
and search process
Lack of evaluation criteria
Intuition, judgement, common
sense
Lack of common sense
Human are unable to retain large
amount of data in memory
Fast response and ability
to comprehend large
amount of data quickly
19
Human
Creativity
Social
acceptancesAutonomy Computational
Creativity
Challenges
Evaluating
creativity
-Evaluation via assessment
of artefacts
- Process of the artefacts
-Human and machine co-ordination
-Requires a level of autonomy
-Autonomy and trust
Human and machine co-
ordination
20
Creativity Support Framework
Cognitive
capabilities
Skill
Artefact Evaluation
Imagination
Appreciation
Progression and development
Process
Product
Environment Society
Computational
creative processDomain
knowledge
Autonomy
Motivation
Data filteringComplexity
Domain specific
Decision making
Interaction
Communication
Learning
Level of
Acceptance
21
Thanks For Listening!

More Related Content

Similar to Fostering creativity in autonomous systems

Application Of Artificial Intelligence In Electrical Engineering
Application Of Artificial Intelligence In Electrical EngineeringApplication Of Artificial Intelligence In Electrical Engineering
Application Of Artificial Intelligence In Electrical Engineering
Amy Roman
 
The IOT Academy Training for Artificial Intelligence ( AI)
The IOT Academy Training for Artificial Intelligence ( AI)The IOT Academy Training for Artificial Intelligence ( AI)
The IOT Academy Training for Artificial Intelligence ( AI)
The IOT Academy
 
BCII 2016 - Visualizing Complexity
BCII 2016 - Visualizing ComplexityBCII 2016 - Visualizing Complexity
BCII 2016 - Visualizing Complexity
Simon Buckingham Shum
 
Crowdsourcing Approaches for Smart City Open Data Management
Crowdsourcing Approaches for Smart City Open Data ManagementCrowdsourcing Approaches for Smart City Open Data Management
Crowdsourcing Approaches for Smart City Open Data Management
Edward Curry
 
Artifical inrelligence
Artifical inrelligenceArtifical inrelligence
Artifical inrelligence
Raghav Garg
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligence
AnkanSinha5
 
Human-machine Inter-agencies
Human-machine Inter-agenciesHuman-machine Inter-agencies
Human-machine Inter-agencies
mo-seph
 
許永真/Crowd Computing for Big and Deep AI
許永真/Crowd Computing for Big and Deep AI許永真/Crowd Computing for Big and Deep AI
許永真/Crowd Computing for Big and Deep AI
台灣資料科學年會
 
Introducing Computational Creativity
Introducing Computational CreativityIntroducing Computational Creativity
Introducing Computational Creativity
Tony Veale
 
Algorithmic Pioneers_ Unraveling the Secrets of Machine Learning.pdf
Algorithmic Pioneers_ Unraveling the Secrets of Machine Learning.pdfAlgorithmic Pioneers_ Unraveling the Secrets of Machine Learning.pdf
Algorithmic Pioneers_ Unraveling the Secrets of Machine Learning.pdf
suryaedcater
 
DWX 2018 Session about Artificial Intelligence, Machine and Deep Learning
DWX 2018 Session about Artificial Intelligence, Machine and Deep LearningDWX 2018 Session about Artificial Intelligence, Machine and Deep Learning
DWX 2018 Session about Artificial Intelligence, Machine and Deep Learning
Mykola Dobrochynskyy
 
Intelligence Augmentation Reading List - Spohrer 20231008.docx
Intelligence Augmentation Reading List - Spohrer 20231008.docxIntelligence Augmentation Reading List - Spohrer 20231008.docx
Intelligence Augmentation Reading List - Spohrer 20231008.docx
International Society of Service Innovation Professionals
 
PPT on Artificial Intelligence(A.I.)
PPT on Artificial Intelligence(A.I.) PPT on Artificial Intelligence(A.I.)
PPT on Artificial Intelligence(A.I.)
Aakanksh Nath
 
MY 1st Nobel Prize by 2037 (Work-in-Progress)
MY 1st Nobel Prize by 2037 (Work-in-Progress)MY 1st Nobel Prize by 2037 (Work-in-Progress)
MY 1st Nobel Prize by 2037 (Work-in-Progress)my1nobel2037
 
e-Research and the Demise of the Scholarly Article
e-Research and the Demise of the Scholarly Articlee-Research and the Demise of the Scholarly Article
e-Research and the Demise of the Scholarly Article
David De Roure
 
ARI5902
ARI5902ARI5902
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligence
Santanu Mukhopadhyay
 
Artificial intelligence, watson and the final checkmate
Artificial intelligence, watson and the final checkmateArtificial intelligence, watson and the final checkmate
Artificial intelligence, watson and the final checkmate
Ricardo Murer
 
AI 3.0
AI 3.0AI 3.0
AI 3.0
InnoTech
 

Similar to Fostering creativity in autonomous systems (20)

Application Of Artificial Intelligence In Electrical Engineering
Application Of Artificial Intelligence In Electrical EngineeringApplication Of Artificial Intelligence In Electrical Engineering
Application Of Artificial Intelligence In Electrical Engineering
 
The IOT Academy Training for Artificial Intelligence ( AI)
The IOT Academy Training for Artificial Intelligence ( AI)The IOT Academy Training for Artificial Intelligence ( AI)
The IOT Academy Training for Artificial Intelligence ( AI)
 
BCII 2016 - Visualizing Complexity
BCII 2016 - Visualizing ComplexityBCII 2016 - Visualizing Complexity
BCII 2016 - Visualizing Complexity
 
Crowdsourcing Approaches for Smart City Open Data Management
Crowdsourcing Approaches for Smart City Open Data ManagementCrowdsourcing Approaches for Smart City Open Data Management
Crowdsourcing Approaches for Smart City Open Data Management
 
Artifical inrelligence
Artifical inrelligenceArtifical inrelligence
Artifical inrelligence
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligence
 
Human-machine Inter-agencies
Human-machine Inter-agenciesHuman-machine Inter-agencies
Human-machine Inter-agencies
 
許永真/Crowd Computing for Big and Deep AI
許永真/Crowd Computing for Big and Deep AI許永真/Crowd Computing for Big and Deep AI
許永真/Crowd Computing for Big and Deep AI
 
Introducing Computational Creativity
Introducing Computational CreativityIntroducing Computational Creativity
Introducing Computational Creativity
 
Algorithmic Pioneers_ Unraveling the Secrets of Machine Learning.pdf
Algorithmic Pioneers_ Unraveling the Secrets of Machine Learning.pdfAlgorithmic Pioneers_ Unraveling the Secrets of Machine Learning.pdf
Algorithmic Pioneers_ Unraveling the Secrets of Machine Learning.pdf
 
DWX 2018 Session about Artificial Intelligence, Machine and Deep Learning
DWX 2018 Session about Artificial Intelligence, Machine and Deep LearningDWX 2018 Session about Artificial Intelligence, Machine and Deep Learning
DWX 2018 Session about Artificial Intelligence, Machine and Deep Learning
 
Intelligence Augmentation Reading List - Spohrer 20231008.docx
Intelligence Augmentation Reading List - Spohrer 20231008.docxIntelligence Augmentation Reading List - Spohrer 20231008.docx
Intelligence Augmentation Reading List - Spohrer 20231008.docx
 
PPT on Artificial Intelligence(A.I.)
PPT on Artificial Intelligence(A.I.) PPT on Artificial Intelligence(A.I.)
PPT on Artificial Intelligence(A.I.)
 
MY 1st Nobel Prize by 2037 (Work-in-Progress)
MY 1st Nobel Prize by 2037 (Work-in-Progress)MY 1st Nobel Prize by 2037 (Work-in-Progress)
MY 1st Nobel Prize by 2037 (Work-in-Progress)
 
e-Research and the Demise of the Scholarly Article
e-Research and the Demise of the Scholarly Articlee-Research and the Demise of the Scholarly Article
e-Research and the Demise of the Scholarly Article
 
ARI5902
ARI5902ARI5902
ARI5902
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligence
 
Artificial intelligence, watson and the final checkmate
Artificial intelligence, watson and the final checkmateArtificial intelligence, watson and the final checkmate
Artificial intelligence, watson and the final checkmate
 
AI 3.0
AI 3.0AI 3.0
AI 3.0
 
Artificial intel
Artificial intelArtificial intel
Artificial intel
 

Recently uploaded

一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理
zwunae
 
6th International Conference on Machine Learning & Applications (CMLA 2024)
6th International Conference on Machine Learning & Applications (CMLA 2024)6th International Conference on Machine Learning & Applications (CMLA 2024)
6th International Conference on Machine Learning & Applications (CMLA 2024)
ClaraZara1
 
在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样
在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样
在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样
obonagu
 
road safety engineering r s e unit 3.pdf
road safety engineering  r s e unit 3.pdfroad safety engineering  r s e unit 3.pdf
road safety engineering r s e unit 3.pdf
VENKATESHvenky89705
 
ML for identifying fraud using open blockchain data.pptx
ML for identifying fraud using open blockchain data.pptxML for identifying fraud using open blockchain data.pptx
ML for identifying fraud using open blockchain data.pptx
Vijay Dialani, PhD
 
AKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdf
AKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdfAKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdf
AKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdf
SamSarthak3
 
Cosmetic shop management system project report.pdf
Cosmetic shop management system project report.pdfCosmetic shop management system project report.pdf
Cosmetic shop management system project report.pdf
Kamal Acharya
 
CME397 Surface Engineering- Professional Elective
CME397 Surface Engineering- Professional ElectiveCME397 Surface Engineering- Professional Elective
CME397 Surface Engineering- Professional Elective
karthi keyan
 
RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Hori...
RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Hori...RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Hori...
RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Hori...
thanhdowork
 
Recycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part IIIRecycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part III
Aditya Rajan Patra
 
Investor-Presentation-Q1FY2024 investor presentation document.pptx
Investor-Presentation-Q1FY2024 investor presentation document.pptxInvestor-Presentation-Q1FY2024 investor presentation document.pptx
Investor-Presentation-Q1FY2024 investor presentation document.pptx
AmarGB2
 
Water Industry Process Automation and Control Monthly - May 2024.pdf
Water Industry Process Automation and Control Monthly - May 2024.pdfWater Industry Process Automation and Control Monthly - May 2024.pdf
Water Industry Process Automation and Control Monthly - May 2024.pdf
Water Industry Process Automation & Control
 
DfMAy 2024 - key insights and contributions
DfMAy 2024 - key insights and contributionsDfMAy 2024 - key insights and contributions
DfMAy 2024 - key insights and contributions
gestioneergodomus
 
space technology lecture notes on satellite
space technology lecture notes on satellitespace technology lecture notes on satellite
space technology lecture notes on satellite
ongomchris
 
Railway Signalling Principles Edition 3.pdf
Railway Signalling Principles Edition 3.pdfRailway Signalling Principles Edition 3.pdf
Railway Signalling Principles Edition 3.pdf
TeeVichai
 
HYDROPOWER - Hydroelectric power generation
HYDROPOWER - Hydroelectric power generationHYDROPOWER - Hydroelectric power generation
HYDROPOWER - Hydroelectric power generation
Robbie Edward Sayers
 
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)
MdTanvirMahtab2
 
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
bakpo1
 
Sachpazis:Terzaghi Bearing Capacity Estimation in simple terms with Calculati...
Sachpazis:Terzaghi Bearing Capacity Estimation in simple terms with Calculati...Sachpazis:Terzaghi Bearing Capacity Estimation in simple terms with Calculati...
Sachpazis:Terzaghi Bearing Capacity Estimation in simple terms with Calculati...
Dr.Costas Sachpazis
 
MCQ Soil mechanics questions (Soil shear strength).pdf
MCQ Soil mechanics questions (Soil shear strength).pdfMCQ Soil mechanics questions (Soil shear strength).pdf
MCQ Soil mechanics questions (Soil shear strength).pdf
Osamah Alsalih
 

Recently uploaded (20)

一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理
 
6th International Conference on Machine Learning & Applications (CMLA 2024)
6th International Conference on Machine Learning & Applications (CMLA 2024)6th International Conference on Machine Learning & Applications (CMLA 2024)
6th International Conference on Machine Learning & Applications (CMLA 2024)
 
在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样
在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样
在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样
 
road safety engineering r s e unit 3.pdf
road safety engineering  r s e unit 3.pdfroad safety engineering  r s e unit 3.pdf
road safety engineering r s e unit 3.pdf
 
ML for identifying fraud using open blockchain data.pptx
ML for identifying fraud using open blockchain data.pptxML for identifying fraud using open blockchain data.pptx
ML for identifying fraud using open blockchain data.pptx
 
AKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdf
AKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdfAKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdf
AKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdf
 
Cosmetic shop management system project report.pdf
Cosmetic shop management system project report.pdfCosmetic shop management system project report.pdf
Cosmetic shop management system project report.pdf
 
CME397 Surface Engineering- Professional Elective
CME397 Surface Engineering- Professional ElectiveCME397 Surface Engineering- Professional Elective
CME397 Surface Engineering- Professional Elective
 
RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Hori...
RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Hori...RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Hori...
RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Hori...
 
Recycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part IIIRecycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part III
 
Investor-Presentation-Q1FY2024 investor presentation document.pptx
Investor-Presentation-Q1FY2024 investor presentation document.pptxInvestor-Presentation-Q1FY2024 investor presentation document.pptx
Investor-Presentation-Q1FY2024 investor presentation document.pptx
 
Water Industry Process Automation and Control Monthly - May 2024.pdf
Water Industry Process Automation and Control Monthly - May 2024.pdfWater Industry Process Automation and Control Monthly - May 2024.pdf
Water Industry Process Automation and Control Monthly - May 2024.pdf
 
DfMAy 2024 - key insights and contributions
DfMAy 2024 - key insights and contributionsDfMAy 2024 - key insights and contributions
DfMAy 2024 - key insights and contributions
 
space technology lecture notes on satellite
space technology lecture notes on satellitespace technology lecture notes on satellite
space technology lecture notes on satellite
 
Railway Signalling Principles Edition 3.pdf
Railway Signalling Principles Edition 3.pdfRailway Signalling Principles Edition 3.pdf
Railway Signalling Principles Edition 3.pdf
 
HYDROPOWER - Hydroelectric power generation
HYDROPOWER - Hydroelectric power generationHYDROPOWER - Hydroelectric power generation
HYDROPOWER - Hydroelectric power generation
 
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)
 
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
 
Sachpazis:Terzaghi Bearing Capacity Estimation in simple terms with Calculati...
Sachpazis:Terzaghi Bearing Capacity Estimation in simple terms with Calculati...Sachpazis:Terzaghi Bearing Capacity Estimation in simple terms with Calculati...
Sachpazis:Terzaghi Bearing Capacity Estimation in simple terms with Calculati...
 
MCQ Soil mechanics questions (Soil shear strength).pdf
MCQ Soil mechanics questions (Soil shear strength).pdfMCQ Soil mechanics questions (Soil shear strength).pdf
MCQ Soil mechanics questions (Soil shear strength).pdf
 

Fostering creativity in autonomous systems

  • 1. Computational Systems FOSTERING CREATIVITY in Dr. Sarah Shuchi, Postdoctoral Fellow 1
  • 2. 2 Human Creativity Computational Creativity Models of Creativity Human and machine collaboration Future of creative computing Outline -What does it mean? -Thinking process -Creativity as process -Goal -CC in various domain -Creative tool -Data mining -Machine learning - Some essential conditions - Human vs. machine challenges - Framework
  • 3. Human Creativity ‘To solve day to day problem’ ‘Novel, surprising and valuable’ 3 Thought process of ordinary people’ ‘Out of box thinking’ ‘Social process’ ‘Creativity is a process of thinking (both conscious and unconscious), arise to solve a problem in a specific context (cultural and social), where the outcome of the process is novel, surprising and valuable.’ ‘Effective surprise for its uniqueness’ http://flowpro.io/blog/creativity Weisberg, R.W., Problem solving and creativity. The nature of creativity, 1988: p. 148-176. Boden, M.A., What is creativity, in Dimensions of Creativity. 1994, The MIT Press: USA. p. 75-117. Robinson, K., Unlocking creativity: A strategy for development. Belfast: Department of Culture Arts and Leisure, 2001.
  • 5. 5 CREATIVITY Valuable Novel Surprising Creativity as novelty, surprise and value Historical Creative (H-creativity) Physiologically Creative (P-creativity) Combination - unfamiliar combinations of familiar ideas Exploration of Conceptual space - Exploratory creativity rests on some culturally accepted style of thinking Transformation - Transformation of space Aesthetic Moment of perceive Judgement Types of creativity
  • 6. 6 Modelling Creativity The Walla’s model -Cognitive process of creativity 4 P model of Creativity Amabile’s -Componential model People Product Process Press System view of Creativity
  • 7. 7 Input Processing Output Enablersofcreativity Mechanismofcreativity Evaluationofcreativity Knowledge Motivation Intuition Curiosity Autonomy Divergent thinking Conscious/unconscious Novel Valuable Surprise (unusual, unexpected, impossible) People and interaction Assessment /evaluation Creative processReason Artefacts Environment / context
  • 9. Computational Creativity "What does it mean for a computer to be creative? Design a program that can enhance human creativity without necessarily being creative themselves. Construct a program or computer capable of human-level creativity. Formulate algorithmic perspective on human creative behaviour. Goal 9 Maher, M., Merrick, K., & Macindoe, O. (2005). Can designs themselves be creative. Computational and Cognitive Models of Creative Design VI, 111-126. Computer generated - Music, Jokes, mathematics, storey telling, painting http://newatlas.com/creative-ai-algorithmic-art-painting-fool-aaron/36106/
  • 10. 10 What do you get when you cross a frog with road? + Q: What do you call a strange market? A: A bizarre bazaar. Q: What is the difference between leaves and a car? A: One you brush and rake, the other you rush and brake. Q : What kind of murderer has fibre? A : A cereal killer.
  • 11. 11 Computer as Creative tool Photos: http://www.thepaintingfool.com/galleries/city_series/index.html Colton, S. Automatic invention of fitness functions with application to scene generation. in Workshops on Applications of Evolutionary Computation. 2008. Springer. Colton, S. Creativity Versus the Perception of Creativity in Computational Systems. in AAAI spring symposium: creative intelligent systems. 2008 Appreciative behaviours revolve around human emotions. Number of painting styles that I can use to hopefully enhance the emotional content of portraits The imaginative behaviours achieved by involving generative techniques from Artificial Intelligence and Computer Graphics. Skillful behaviours are based on simulating the physical painting process.
  • 12. 12 Convolutional neural network Gatys, L. A., Ecker, A. S., & Bethge, M. (2015). A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576. Style Reconstruction Input Image Content reconstruction Style reconstructio n Machine learning and Creativity Neural network on image data Artistic Style Imitation - By applying the style of different artists to an arbitrary image of their choice. -Applying a simple neural network on image data directly creates large number of parameters . - Convolutional Neural Networks (CNNs) were introduced
  • 13. 13 Gatys, L. A., Ecker, A. S., & Bethge, M. (2015). A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576 https://deepdreamgenerator.com/gallery. Machine learning and Creativity (continues) Neural network on image data Similar text - with training data, the models can generate similar texts, for example, like Shakespeare plays Chat bots - make use of the vast amount of data Often conversations with bots can lack flow At a glance, they do look authentic Usually, the images are generated in iterations and in each iteration it is zoomed into the image. Google deep dream- published by Google engineers Text data Little feeling or personality associated with it
  • 14. 14 Neurocognitive model and Creativity Creativity is a product of ordinary neurocognitive process To create novel words – a neurocognitive model inspired by the putative processes of brain Results are surprisingly similar to those created by humans. Associative memory Imagination Filtering Duch, W., & Pilichowski, M. (2007). Experiments with computational creativity. Neural Information Processing–Letters and Reviews, 11(4-6), 123-133 Murray, L.L., The effects of varying attentional demands on the word retrieval skills of adults with aphasia, right hemisphere brain damage, or no brain damage. Brain and language, 2000. 72(1): p. 40-72. Stores background knowledge Challenges Most interesting one  Some words are already developed  Some words needs to be manually removed
  • 15. 15 Big data and Creativity By using big data computationally creative program can automatically design and discover culinary recipes that are flavourful, healthy, and novel! The system understands food at the molecular level, learns the essence of culinary traditions. Thousands of ingredients, and a great deal of psychological data on human perception Maher, M., Merrick, K., & Macindoe, O. (2005). Can designs themselves be creative. Computational and Cognitive Models of Creative Design VI, 111-126. - Learning evaluation function - Generating complex artefacts - Differentiate useful and useless data
  • 16. 16 Swarm intelligence, art creativity and freedom Experiment with Swarmic freedom or controlled freedom a b c d e Pushing the swarms towards exploration, freedom is enhanced and by encouraging exploitation, constraint is more emphasised. - Finding a balance between exploration and exploitation is an important theoretical challenge - Doesn’t really go beyond the expecting simulation of human intelligence al-Rifaie, M.M. and M. Bishop, Weak and strong computational creativity, in Computational creativity research: Towards creative machines. 2015, Springer. p. 37-49.
  • 18. 18 Human Creativity Computational Creativity Human vs. Machine Creativity Evaluation via assessment of artefacts Perspectives and criteria to evaluate ideas and modify them It is easy to generate random combinations, but not many of them may be valuable. A rich store of world knowledge (including cultural knowledge). Lack of an associative memory and search process Lack of evaluation criteria Intuition, judgement, common sense Lack of common sense Human are unable to retain large amount of data in memory Fast response and ability to comprehend large amount of data quickly
  • 19. 19 Human Creativity Social acceptancesAutonomy Computational Creativity Challenges Evaluating creativity -Evaluation via assessment of artefacts - Process of the artefacts -Human and machine co-ordination -Requires a level of autonomy -Autonomy and trust Human and machine co- ordination
  • 20. 20 Creativity Support Framework Cognitive capabilities Skill Artefact Evaluation Imagination Appreciation Progression and development Process Product Environment Society Computational creative processDomain knowledge Autonomy Motivation Data filteringComplexity Domain specific Decision making Interaction Communication Learning Level of Acceptance

Editor's Notes

  1. Our ability to think creatively is one of the factors that generates excitement in our lives  introduces novelty and opens up new possibilities 
  2. Creativity has been traditionally focused on human creativity, and even more specifically, on the psychology of individual creative people. Computational creativity is a multidisciplinary field that studies creativity, using techniques from artificial intelligence, and concepts drawing from psychology, cognitive science and the arts
  3. Creativity is not just for artist, musician, writers and designers
  4. By connecting ideas together creative leaps can be made, producing some of history’s biggest breakthroughs. Poetic Imagery and Figurative Language are examples of Combinational Creativity
  5. added emphasis on finding the ways of being creative rather than asking whether computers can be considered as creative or not
  6. The exhibition was called Growth and was a retrospective of 10 years of automated art generation. I can look at digital photographs and determine regions of colour; then abstract these regions and change their colour according to palettes; then simulate natural media such as paints, pastels and pencils, and their usage in outlining and filling paint regions.  Working with machine vision software, I can also detect the emotion of people and use this to paint portraits accordingly, as described in the Emotionally Aware Painting project.
  7. Artificial neural networks inspired by biological neurons is considered as an important group of machine learning algorithms. The neural network technique to amplify the output on image data really works but the drawbacks is the number of parameters, which gets extraordinary large. To overcome this problem, Convolutional Neural Networks (CNNs) were introduced. This process has been named inceptionism
  8. Machine learning is a well-established research area, and has a greatest impact on all AI subfields. It is inherently a multidisciplinary field, which accumulate results from artificial intelligence, probability and statistics, Artificial neural networks inspired by biological neurons is considered as an important group of machine learning algorithms. The neural network technique to amplify the output on image data really works but the drawbacks is the number of parameters, which gets extraordinary large. To overcome this problem, Convolutional Neural Networks (CNNs) were introduced. This process has been named inceptionism
  9. The mystery of the mind and its relations to the brain is slowly being unraveled. Many low-level cognitive functions involving perception and motor control have reasonable neural models. They were rather in doubt that whether artificial intelligence, which was previously focused only on symbol manipulation for problem solving, can lead to creative behaviour. To understand the higher cognitive processes one should start from understanding how symbols are stored and used in the brain. The details of the phonological processing is available in literature The algorithms used for the creation of novel words are quite efficient and might be used in practice to generate interesting names for products, companies, web sites or names of various entities.
  10. In swarm intelligence systems pushing the swarms towards exploration, freedom is enhanced and by encouraging exploitation, constraint is more emphasised. experiment with Swarmic freedom or controlled freedom shows that when more ‘freedom’ is granted to the randomised algorithm the algorithm soon begins to deviate excessively from the original line drawing The authors drew an analogy that in weak computationally creative which is achieved through swarm intelligence technique, which doesn’t really go beyond the expecting simulation of human intelligence
  11. Though computational creativity boroughs human creativity concept, however human creativity and computational creativity is not the same. Computers don’t have the cognitive ability to think like human, which makes it more doubtful for the researchers to develop computer programs that will be ever to be considered as creative as human.
  12. We’re undoubtedly seeing the first steps towards AI’s move into independent creativity The primary resource we have for examining creative actions is that of ourselves; how humans demonstrate creativity. The closer artificial creative systems can match our perception of human creativity, the more successful they are generally deemed to be for demonstrating creativity.  However, it’s because of human involvement – that computers are able to learn from human creativity and computer programs are able to produce artefacts which are considered as creative to some extent. People have to get used to the idea of software creating things," Machines “learn” by using algorithms to analyze data and find patterns or predict outcomes.
  13. We’re undoubtedly seeing the first steps towards AI’s move into independent creativity However, it’s because of human involvement – that computers are able to learn from human creativity and computer programs are able to produce artefacts which are considered as creative to some extent. People have to get used to the idea of software creating things," Machines “learn” by using algorithms to analyze data and find patterns or predict outcomes.