SlideShare une entreprise Scribd logo
1  sur  14
Algorithms - A technical perspective
Are they really a black box?
Ansgar Koene
Algorithms Workshop
15 February 2017
http://unbias.wp.horizon.ac.uk/
Algorithms in the news
2
• Technical issues
– Fundamental
– Practical
• Business/management interests, e.g. trade secrets
 How a decision was reached is in principle possible to be
revealed, if sufficient data about the state of the system at
time of operation is available (and we have access to the
code)
 Why a particular chain of operations was done is much more
difficult (especially with ML)
Origins of the ‘black box’
3
• Machine Learning (ML) • Hand coded
Fundamental properties
O1=f(w1,H1,w2,H2,w3,H3)
Machine Learning
• If parameters & data are
known, we can trace how
the output is computed.
• If history of data is known,
we can in principle trace
how parameters were set.
• Explaining why certain
parameters are optimal can
be very difficult.
=> Explaining why output is
produced is difficult.
Hand Coded
• If parameters & data are
known, we can trace how
the output is computed.
• We known the parameters
were set by engineers.
• We can ask the engineers
why certain parameters
were chosen.
=> Explaining why output is
produced depends on the
engineers.
Fundamental transparency: how vs. why
• High dimensionality of Big Data algorithms can make
interpretation of the ‘explanation’ problematic
– e.g. Google page ranking algorithms is estimated to
involve 200+ parameters
• Approximated transparency through dimensionality
reduction, e.g. Principle Component Analysis (PCA)
– requires case-by-case analysis depending on input data
– ‘general’ solution only valid for the ‘majority case’
conditions
High dimensionality, a.k.a. when an
explanation is not transparent
6
Machine Learning
• If Machine Learning
algorithms use ‘in situ’
continuous or intermitted
learning, the parameter
setting change over time.
• To re-create a system
behaviour requires
knowledge of the past
parameter states.
Hand Coded
• Hand coded systems are
also frequently updates,
especially if there is an
‘arms race’ between the
service provider and users
trying to ‘game’ the system
(e.g. Google search vs.
Search Engine Optimization)
Practical issues: non-static algorithms
In some cases, randomness might be built into an
algorithm’s design meaning its outcomes can never be
perfectly predicted.
• Defining precisely what a task/problem is (logic)
• Break that down into a precise set of instructions, factoring
in any contingencies, such as how the algorithm should
perform under different conditions (control).
• “Explain it to something as stonily stupid as a computer”
(Fuller 2008).
• Many tasks and problems are extremely difficult or
impossible to translate into algorithms and end up being
hugely oversimplified.
• Mistranslating the problem and/or solution will lead to
erroneous outcomes and random uncertainties.
The challenge of translating a
task/problem into an algorithm
8
System design in the real world
9
https://effectivesoftwaredesign.com/2012/04/23/communication-problems-in-software-projects/
• Algorithm are created through: trial and error, play,
collaboration, discussion, and negotiation.
• They are teased into being: edited, revised, deleted and
restarted, shared with others, passing through multiple
iterations stretched out over time and space.
• They are always somewhat uncertain, provisional and messy
fragile accomplishments.
• Algorithmic systems are not standalone little boxes, but
massive, networked ones with hundreds of hands reaching
into them, tweaking and tuning, swapping out parts and
experimenting with new arrangements.
Algorithm creation
10
Gillespie, T. (2014a) The relevance of algorithms, in Media Technologies: Essays on Communication, Materiality, and Society, ed. by
Gillespie, T., Boczkowski, P.J. and Foot, K.A. Cambridge, MA: MIT Press, pp.167-93.; Neyland, D. (2014) On organizing algorithms. Theory,
Culture and Society, online first. cited in: Kitchin, Rob, and Martin Dodge. 2017. “The (in)security of Smart Cities: Vulnerabilities, Risks,
Mitigation and Prevention.” SocArXiv. February 13. osf.io/preprints/socarxiv/f6z63.
• Deconstructing and tracing how an algorithm is constructed
in code and mutates over time is not straightforward.
• Code often takes the form of a “Big Ball of Mud”: “[a]
haphazardly structured, sprawling, sloppy, duct-tape and
bailing wire, spaghetti code jungle”.
Examining pseudo-code/source code
11
Foote, B. and Yoder, J. (1997) Big Ball of Mud. Pattern Languages of Program Design 4: 654-92; cited in
Kitchin, Rob, and Martin Dodge. 2017. “The (in)security of Smart Cities: Vulnerabilities, Risks, Mitigation and Prevention.” SocArXiv. February 13.
osf.io/preprints/socarxiv/f6z63.
• Reverse engineering is the process of articulating the
specifications of a system through a rigorous examination
drawing on domain knowledge, observation, and deduction
to unearth a model of how that system works.
• By examining what data is fed into an algorithm and what
output is produced it is possible to start to reverse engineer
how the recipe of the algorithm is composed (how it weights
and preferences some criteria) and what it does.
Reverse engineering
12
• HOW
– With access to the code, data and parameter settings,
HOW the output was produced can be ‘explained’.
– High dimensionality can make the ‘explanation’ difficult
to understand.
– Dimensionality reduction can help to generate an
approximate explanation that is understandable.
• WHY
– Can be (very) difficult to determine, especially if Machine
Learning methods are used.
– Approximate explanation based on the manually set
optimization targets can help.
Conclusion
13
UnBias project
14
http://unbias.wp.horizon.ac.uk/

Contenu connexe

Tendances

Tendances (20)

iConference 2018 BIAS workshop keynote
iConference 2018 BIAS workshop keynoteiConference 2018 BIAS workshop keynote
iConference 2018 BIAS workshop keynote
 
Bsa cpd a_koene2016
Bsa cpd a_koene2016Bsa cpd a_koene2016
Bsa cpd a_koene2016
 
A koene intersectionality_algorithmic_discrimination_dec2017
A koene intersectionality_algorithmic_discrimination_dec2017A koene intersectionality_algorithmic_discrimination_dec2017
A koene intersectionality_algorithmic_discrimination_dec2017
 
AI and us communicating for algorithmic bias awareness
AI and us communicating for algorithmic bias awarenessAI and us communicating for algorithmic bias awareness
AI and us communicating for algorithmic bias awareness
 
Algorithmically Mediated Online Inforamtion Access workshop at WebSci17
Algorithmically Mediated Online Inforamtion Access workshop at WebSci17Algorithmically Mediated Online Inforamtion Access workshop at WebSci17
Algorithmically Mediated Online Inforamtion Access workshop at WebSci17
 
Editorial responsibilities arising from personalisation algorithms
Editorial responsibilities arising from personalisation algorithmsEditorial responsibilities arising from personalisation algorithms
Editorial responsibilities arising from personalisation algorithms
 
AI Governance and Ethics - Industry Standards
AI Governance and Ethics - Industry StandardsAI Governance and Ethics - Industry Standards
AI Governance and Ethics - Industry Standards
 
Algorithms of Online Platforms and Networks
Algorithms of Online Platforms and NetworksAlgorithms of Online Platforms and Networks
Algorithms of Online Platforms and Networks
 
Ethics of Analytics and Machine Learning
Ethics of Analytics and Machine LearningEthics of Analytics and Machine Learning
Ethics of Analytics and Machine Learning
 
Introduction to AI Governance
Introduction to AI GovernanceIntroduction to AI Governance
Introduction to AI Governance
 
Implementing Ethics in AI
Implementing Ethics in AIImplementing Ethics in AI
Implementing Ethics in AI
 
20190423 PRiSE model to tackle data protection impact assessments and data pr...
20190423 PRiSE model to tackle data protection impact assessments and data pr...20190423 PRiSE model to tackle data protection impact assessments and data pr...
20190423 PRiSE model to tackle data protection impact assessments and data pr...
 
Responsible AI: An Example AI Development Process with Focus on Risks and Con...
Responsible AI: An Example AI Development Process with Focus on Risks and Con...Responsible AI: An Example AI Development Process with Focus on Risks and Con...
Responsible AI: An Example AI Development Process with Focus on Risks and Con...
 
EU Ethics guidelines for trustworthy AI
EU Ethics guidelines for trustworthy AI EU Ethics guidelines for trustworthy AI
EU Ethics guidelines for trustworthy AI
 
Aspa ai webinar
Aspa   ai webinarAspa   ai webinar
Aspa ai webinar
 
Towards Fairer Datasets: Filtering and Balancing the Distribution of the Peop...
Towards Fairer Datasets: Filtering and Balancing the Distribution of the Peop...Towards Fairer Datasets: Filtering and Balancing the Distribution of the Peop...
Towards Fairer Datasets: Filtering and Balancing the Distribution of the Peop...
 
From principles to action: A method for ethically aligned AI design and imple...
From principles to action: A method for ethically aligned AI design and imple...From principles to action: A method for ethically aligned AI design and imple...
From principles to action: A method for ethically aligned AI design and imple...
 
Questions of Ethics in Software Development
Questions of Ethics in Software DevelopmentQuestions of Ethics in Software Development
Questions of Ethics in Software Development
 
AAMAS-2017 8-12 May, 2017, Sao Paulo, Brazil
AAMAS-2017 8-12 May, 2017, Sao Paulo, BrazilAAMAS-2017 8-12 May, 2017, Sao Paulo, Brazil
AAMAS-2017 8-12 May, 2017, Sao Paulo, Brazil
 
Deep Neural Networks for Machine Learning
Deep Neural Networks for Machine LearningDeep Neural Networks for Machine Learning
Deep Neural Networks for Machine Learning
 

Similaire à are algorithms really a black box

BsidesLVPresso2016_JZeditsv6
BsidesLVPresso2016_JZeditsv6BsidesLVPresso2016_JZeditsv6
BsidesLVPresso2016_JZeditsv6
Rod Soto
 
Borders of Decidability in Verification of Data-Centric Dynamic Systems
Borders of Decidability in Verification of Data-Centric Dynamic SystemsBorders of Decidability in Verification of Data-Centric Dynamic Systems
Borders of Decidability in Verification of Data-Centric Dynamic Systems
net2-project
 

Similaire à are algorithms really a black box (20)

AI & ML in Cyber Security - Why Algorithms Are Dangerous
AI & ML in Cyber Security - Why Algorithms Are DangerousAI & ML in Cyber Security - Why Algorithms Are Dangerous
AI & ML in Cyber Security - Why Algorithms Are Dangerous
 
Rise of the machines -- Owasp israel -- June 2014 meetup
Rise of the machines -- Owasp israel -- June 2014 meetupRise of the machines -- Owasp israel -- June 2014 meetup
Rise of the machines -- Owasp israel -- June 2014 meetup
 
Keynote at-icpc-2020
Keynote at-icpc-2020Keynote at-icpc-2020
Keynote at-icpc-2020
 
Insemtives swat4ls 2012
Insemtives swat4ls 2012Insemtives swat4ls 2012
Insemtives swat4ls 2012
 
BsidesLVPresso2016_JZeditsv6
BsidesLVPresso2016_JZeditsv6BsidesLVPresso2016_JZeditsv6
BsidesLVPresso2016_JZeditsv6
 
EVAIN Artificial intelligence and semantic annotation: are you serious about it?
EVAIN Artificial intelligence and semantic annotation: are you serious about it?EVAIN Artificial intelligence and semantic annotation: are you serious about it?
EVAIN Artificial intelligence and semantic annotation: are you serious about it?
 
Doing Analytics Right - Building the Analytics Environment
Doing Analytics Right - Building the Analytics EnvironmentDoing Analytics Right - Building the Analytics Environment
Doing Analytics Right - Building the Analytics Environment
 
Ch01lect1 et
Ch01lect1 etCh01lect1 et
Ch01lect1 et
 
MODEL-DRIVEN ENGINEERING (MDE) in Practice
MODEL-DRIVEN ENGINEERING (MDE) in PracticeMODEL-DRIVEN ENGINEERING (MDE) in Practice
MODEL-DRIVEN ENGINEERING (MDE) in Practice
 
Unit no_1.pptx
Unit no_1.pptxUnit no_1.pptx
Unit no_1.pptx
 
Era ofdataeconomyv4short
Era ofdataeconomyv4shortEra ofdataeconomyv4short
Era ofdataeconomyv4short
 
Data Summer Conf 2018, “Architecting IoT system with Machine Learning (ENG)” ...
Data Summer Conf 2018, “Architecting IoT system with Machine Learning (ENG)” ...Data Summer Conf 2018, “Architecting IoT system with Machine Learning (ENG)” ...
Data Summer Conf 2018, “Architecting IoT system with Machine Learning (ENG)” ...
 
Architecting IoT with Machine Learning
Architecting IoT with Machine LearningArchitecting IoT with Machine Learning
Architecting IoT with Machine Learning
 
Pydata Chicago - work hard once
Pydata Chicago - work hard oncePydata Chicago - work hard once
Pydata Chicago - work hard once
 
Borders of Decidability in Verification of Data-Centric Dynamic Systems
Borders of Decidability in Verification of Data-Centric Dynamic SystemsBorders of Decidability in Verification of Data-Centric Dynamic Systems
Borders of Decidability in Verification of Data-Centric Dynamic Systems
 
GenerativeAI and Automation - IEEE ACSOS 2023.pptx
GenerativeAI and Automation - IEEE ACSOS 2023.pptxGenerativeAI and Automation - IEEE ACSOS 2023.pptx
GenerativeAI and Automation - IEEE ACSOS 2023.pptx
 
AI for Software Engineering
AI for Software EngineeringAI for Software Engineering
AI for Software Engineering
 
Data Science at Scale - The DevOps Approach
Data Science at Scale - The DevOps ApproachData Science at Scale - The DevOps Approach
Data Science at Scale - The DevOps Approach
 
Data collection and enhancement
Data collection and enhancementData collection and enhancement
Data collection and enhancement
 
Data Science in the Real World: Making a Difference
Data Science in the Real World: Making a Difference Data Science in the Real World: Making a Difference
Data Science in the Real World: Making a Difference
 

Plus de Ansgar Koene

Plus de Ansgar Koene (14)

Industry Standards as vehicle to address socio-technical AI challenges
Industry Standards as vehicle to address socio-technical AI challengesIndustry Standards as vehicle to address socio-technical AI challenges
Industry Standards as vehicle to address socio-technical AI challenges
 
What is AI?
What is AI?What is AI?
What is AI?
 
A koene governance_framework_algorithmicaccountabilitytransparency_october2018
A koene governance_framework_algorithmicaccountabilitytransparency_october2018A koene governance_framework_algorithmicaccountabilitytransparency_october2018
A koene governance_framework_algorithmicaccountabilitytransparency_october2018
 
IEEE P7003 Algorithmic Bias Considerations
IEEE P7003 Algorithmic Bias ConsiderationsIEEE P7003 Algorithmic Bias Considerations
IEEE P7003 Algorithmic Bias Considerations
 
A koene ai_in_command_control
A koene ai_in_command_controlA koene ai_in_command_control
A koene ai_in_command_control
 
Human Agency on Algorithmic Systems
Human Agency on Algorithmic SystemsHuman Agency on Algorithmic Systems
Human Agency on Algorithmic Systems
 
TRILcon'17 confernece workshop presentation on UnBias stakeholder engagement
TRILcon'17 confernece workshop presentation on UnBias stakeholder engagementTRILcon'17 confernece workshop presentation on UnBias stakeholder engagement
TRILcon'17 confernece workshop presentation on UnBias stakeholder engagement
 
Young people's policy recommendations on algorithm fairness web sci17
Young people's policy recommendations on algorithm fairness web sci17Young people's policy recommendations on algorithm fairness web sci17
Young people's policy recommendations on algorithm fairness web sci17
 
A koene Rebooting The Expert Petcha Kutcha 2017
A koene Rebooting The Expert Petcha Kutcha 2017A koene Rebooting The Expert Petcha Kutcha 2017
A koene Rebooting The Expert Petcha Kutcha 2017
 
Internet Society (ISOC Uk England) Webinar on User Trust
Internet Society (ISOC Uk England) Webinar on User TrustInternet Society (ISOC Uk England) Webinar on User Trust
Internet Society (ISOC Uk England) Webinar on User Trust
 
Explorers fair talk who_isincontrol_you_thealgorithm
Explorers fair talk who_isincontrol_you_thealgorithmExplorers fair talk who_isincontrol_you_thealgorithm
Explorers fair talk who_isincontrol_you_thealgorithm
 
Gada CaSMa oxford connected life oxcl16
Gada CaSMa oxford connected life oxcl16Gada CaSMa oxford connected life oxcl16
Gada CaSMa oxford connected life oxcl16
 
Dasts16 a koene_un_bias
Dasts16 a koene_un_biasDasts16 a koene_un_bias
Dasts16 a koene_un_bias
 
Ass a koene_ca_sma
Ass a koene_ca_smaAss a koene_ca_sma
Ass a koene_ca_sma
 

Dernier

Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...
Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...
Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...
Sheetaleventcompany
 

Dernier (20)

Call Now ☎ 8264348440 !! Call Girls in Rani Bagh Escort Service Delhi N.C.R.
Call Now ☎ 8264348440 !! Call Girls in Rani Bagh Escort Service Delhi N.C.R.Call Now ☎ 8264348440 !! Call Girls in Rani Bagh Escort Service Delhi N.C.R.
Call Now ☎ 8264348440 !! Call Girls in Rani Bagh Escort Service Delhi N.C.R.
 
WhatsApp 📞 8448380779 ✅Call Girls In Mamura Sector 66 ( Noida)
WhatsApp 📞 8448380779 ✅Call Girls In Mamura Sector 66 ( Noida)WhatsApp 📞 8448380779 ✅Call Girls In Mamura Sector 66 ( Noida)
WhatsApp 📞 8448380779 ✅Call Girls In Mamura Sector 66 ( Noida)
 
Real Men Wear Diapers T Shirts sweatshirt
Real Men Wear Diapers T Shirts sweatshirtReal Men Wear Diapers T Shirts sweatshirt
Real Men Wear Diapers T Shirts sweatshirt
 
VVIP Pune Call Girls Sinhagad WhatSapp Number 8005736733 With Elite Staff And...
VVIP Pune Call Girls Sinhagad WhatSapp Number 8005736733 With Elite Staff And...VVIP Pune Call Girls Sinhagad WhatSapp Number 8005736733 With Elite Staff And...
VVIP Pune Call Girls Sinhagad WhatSapp Number 8005736733 With Elite Staff And...
 
Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...
Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...
Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...
 
All Time Service Available Call Girls Mg Road 👌 ⏭️ 6378878445
All Time Service Available Call Girls Mg Road 👌 ⏭️ 6378878445All Time Service Available Call Girls Mg Road 👌 ⏭️ 6378878445
All Time Service Available Call Girls Mg Road 👌 ⏭️ 6378878445
 
VIP Model Call Girls NIBM ( Pune ) Call ON 8005736733 Starting From 5K to 25K...
VIP Model Call Girls NIBM ( Pune ) Call ON 8005736733 Starting From 5K to 25K...VIP Model Call Girls NIBM ( Pune ) Call ON 8005736733 Starting From 5K to 25K...
VIP Model Call Girls NIBM ( Pune ) Call ON 8005736733 Starting From 5K to 25K...
 
Trump Diapers Over Dems t shirts Sweatshirt
Trump Diapers Over Dems t shirts SweatshirtTrump Diapers Over Dems t shirts Sweatshirt
Trump Diapers Over Dems t shirts Sweatshirt
 
Russian Call Girls Pune (Adult Only) 8005736733 Escort Service 24x7 Cash Pay...
Russian Call Girls Pune  (Adult Only) 8005736733 Escort Service 24x7 Cash Pay...Russian Call Girls Pune  (Adult Only) 8005736733 Escort Service 24x7 Cash Pay...
Russian Call Girls Pune (Adult Only) 8005736733 Escort Service 24x7 Cash Pay...
 
'Future Evolution of the Internet' delivered by Geoff Huston at Everything Op...
'Future Evolution of the Internet' delivered by Geoff Huston at Everything Op...'Future Evolution of the Internet' delivered by Geoff Huston at Everything Op...
'Future Evolution of the Internet' delivered by Geoff Huston at Everything Op...
 
Moving Beyond Twitter/X and Facebook - Social Media for local news providers
Moving Beyond Twitter/X and Facebook - Social Media for local news providersMoving Beyond Twitter/X and Facebook - Social Media for local news providers
Moving Beyond Twitter/X and Facebook - Social Media for local news providers
 
Hot Call Girls |Delhi |Hauz Khas ☎ 9711199171 Book Your One night Stand
Hot Call Girls |Delhi |Hauz Khas ☎ 9711199171 Book Your One night StandHot Call Girls |Delhi |Hauz Khas ☎ 9711199171 Book Your One night Stand
Hot Call Girls |Delhi |Hauz Khas ☎ 9711199171 Book Your One night Stand
 
Call Now ☎ 8264348440 !! Call Girls in Sarai Rohilla Escort Service Delhi N.C.R.
Call Now ☎ 8264348440 !! Call Girls in Sarai Rohilla Escort Service Delhi N.C.R.Call Now ☎ 8264348440 !! Call Girls in Sarai Rohilla Escort Service Delhi N.C.R.
Call Now ☎ 8264348440 !! Call Girls in Sarai Rohilla Escort Service Delhi N.C.R.
 
Top Rated Pune Call Girls Daund ⟟ 6297143586 ⟟ Call Me For Genuine Sex Servi...
Top Rated  Pune Call Girls Daund ⟟ 6297143586 ⟟ Call Me For Genuine Sex Servi...Top Rated  Pune Call Girls Daund ⟟ 6297143586 ⟟ Call Me For Genuine Sex Servi...
Top Rated Pune Call Girls Daund ⟟ 6297143586 ⟟ Call Me For Genuine Sex Servi...
 
Call Now ☎ 8264348440 !! Call Girls in Green Park Escort Service Delhi N.C.R.
Call Now ☎ 8264348440 !! Call Girls in Green Park Escort Service Delhi N.C.R.Call Now ☎ 8264348440 !! Call Girls in Green Park Escort Service Delhi N.C.R.
Call Now ☎ 8264348440 !! Call Girls in Green Park Escort Service Delhi N.C.R.
 
Enjoy Night⚡Call Girls Dlf City Phase 3 Gurgaon >༒8448380779 Escort Service
Enjoy Night⚡Call Girls Dlf City Phase 3 Gurgaon >༒8448380779 Escort ServiceEnjoy Night⚡Call Girls Dlf City Phase 3 Gurgaon >༒8448380779 Escort Service
Enjoy Night⚡Call Girls Dlf City Phase 3 Gurgaon >༒8448380779 Escort Service
 
Russian Call Girls in %(+971524965298 )# Call Girls in Dubai
Russian Call Girls in %(+971524965298  )#  Call Girls in DubaiRussian Call Girls in %(+971524965298  )#  Call Girls in Dubai
Russian Call Girls in %(+971524965298 )# Call Girls in Dubai
 
(INDIRA) Call Girl Pune Call Now 8250077686 Pune Escorts 24x7
(INDIRA) Call Girl Pune Call Now 8250077686 Pune Escorts 24x7(INDIRA) Call Girl Pune Call Now 8250077686 Pune Escorts 24x7
(INDIRA) Call Girl Pune Call Now 8250077686 Pune Escorts 24x7
 
Shikrapur - Call Girls in Pune Neha 8005736733 | 100% Gennuine High Class Ind...
Shikrapur - Call Girls in Pune Neha 8005736733 | 100% Gennuine High Class Ind...Shikrapur - Call Girls in Pune Neha 8005736733 | 100% Gennuine High Class Ind...
Shikrapur - Call Girls in Pune Neha 8005736733 | 100% Gennuine High Class Ind...
 
Busty Desi⚡Call Girls in Vasundhara Ghaziabad >༒8448380779 Escort Service
Busty Desi⚡Call Girls in Vasundhara Ghaziabad >༒8448380779 Escort ServiceBusty Desi⚡Call Girls in Vasundhara Ghaziabad >༒8448380779 Escort Service
Busty Desi⚡Call Girls in Vasundhara Ghaziabad >༒8448380779 Escort Service
 

are algorithms really a black box

  • 1. Algorithms - A technical perspective Are they really a black box? Ansgar Koene Algorithms Workshop 15 February 2017 http://unbias.wp.horizon.ac.uk/
  • 3. • Technical issues – Fundamental – Practical • Business/management interests, e.g. trade secrets  How a decision was reached is in principle possible to be revealed, if sufficient data about the state of the system at time of operation is available (and we have access to the code)  Why a particular chain of operations was done is much more difficult (especially with ML) Origins of the ‘black box’ 3
  • 4. • Machine Learning (ML) • Hand coded Fundamental properties O1=f(w1,H1,w2,H2,w3,H3)
  • 5. Machine Learning • If parameters & data are known, we can trace how the output is computed. • If history of data is known, we can in principle trace how parameters were set. • Explaining why certain parameters are optimal can be very difficult. => Explaining why output is produced is difficult. Hand Coded • If parameters & data are known, we can trace how the output is computed. • We known the parameters were set by engineers. • We can ask the engineers why certain parameters were chosen. => Explaining why output is produced depends on the engineers. Fundamental transparency: how vs. why
  • 6. • High dimensionality of Big Data algorithms can make interpretation of the ‘explanation’ problematic – e.g. Google page ranking algorithms is estimated to involve 200+ parameters • Approximated transparency through dimensionality reduction, e.g. Principle Component Analysis (PCA) – requires case-by-case analysis depending on input data – ‘general’ solution only valid for the ‘majority case’ conditions High dimensionality, a.k.a. when an explanation is not transparent 6
  • 7. Machine Learning • If Machine Learning algorithms use ‘in situ’ continuous or intermitted learning, the parameter setting change over time. • To re-create a system behaviour requires knowledge of the past parameter states. Hand Coded • Hand coded systems are also frequently updates, especially if there is an ‘arms race’ between the service provider and users trying to ‘game’ the system (e.g. Google search vs. Search Engine Optimization) Practical issues: non-static algorithms In some cases, randomness might be built into an algorithm’s design meaning its outcomes can never be perfectly predicted.
  • 8. • Defining precisely what a task/problem is (logic) • Break that down into a precise set of instructions, factoring in any contingencies, such as how the algorithm should perform under different conditions (control). • “Explain it to something as stonily stupid as a computer” (Fuller 2008). • Many tasks and problems are extremely difficult or impossible to translate into algorithms and end up being hugely oversimplified. • Mistranslating the problem and/or solution will lead to erroneous outcomes and random uncertainties. The challenge of translating a task/problem into an algorithm 8
  • 9. System design in the real world 9 https://effectivesoftwaredesign.com/2012/04/23/communication-problems-in-software-projects/
  • 10. • Algorithm are created through: trial and error, play, collaboration, discussion, and negotiation. • They are teased into being: edited, revised, deleted and restarted, shared with others, passing through multiple iterations stretched out over time and space. • They are always somewhat uncertain, provisional and messy fragile accomplishments. • Algorithmic systems are not standalone little boxes, but massive, networked ones with hundreds of hands reaching into them, tweaking and tuning, swapping out parts and experimenting with new arrangements. Algorithm creation 10 Gillespie, T. (2014a) The relevance of algorithms, in Media Technologies: Essays on Communication, Materiality, and Society, ed. by Gillespie, T., Boczkowski, P.J. and Foot, K.A. Cambridge, MA: MIT Press, pp.167-93.; Neyland, D. (2014) On organizing algorithms. Theory, Culture and Society, online first. cited in: Kitchin, Rob, and Martin Dodge. 2017. “The (in)security of Smart Cities: Vulnerabilities, Risks, Mitigation and Prevention.” SocArXiv. February 13. osf.io/preprints/socarxiv/f6z63.
  • 11. • Deconstructing and tracing how an algorithm is constructed in code and mutates over time is not straightforward. • Code often takes the form of a “Big Ball of Mud”: “[a] haphazardly structured, sprawling, sloppy, duct-tape and bailing wire, spaghetti code jungle”. Examining pseudo-code/source code 11 Foote, B. and Yoder, J. (1997) Big Ball of Mud. Pattern Languages of Program Design 4: 654-92; cited in Kitchin, Rob, and Martin Dodge. 2017. “The (in)security of Smart Cities: Vulnerabilities, Risks, Mitigation and Prevention.” SocArXiv. February 13. osf.io/preprints/socarxiv/f6z63.
  • 12. • Reverse engineering is the process of articulating the specifications of a system through a rigorous examination drawing on domain knowledge, observation, and deduction to unearth a model of how that system works. • By examining what data is fed into an algorithm and what output is produced it is possible to start to reverse engineer how the recipe of the algorithm is composed (how it weights and preferences some criteria) and what it does. Reverse engineering 12
  • 13. • HOW – With access to the code, data and parameter settings, HOW the output was produced can be ‘explained’. – High dimensionality can make the ‘explanation’ difficult to understand. – Dimensionality reduction can help to generate an approximate explanation that is understandable. • WHY – Can be (very) difficult to determine, especially if Machine Learning methods are used. – Approximate explanation based on the manually set optimization targets can help. Conclusion 13

Notes de l'éditeur

  1. researchers might search Google using the same terms on multiple computers in multiple jurisdictions to get a sense of how its PageRank algorithm is constructed and works in practice (Mahnke and Uprichard 2014), or they might experiment with posting and interacting with posts on Facebook to try and determine how its EdgeRank algorithm positions and prioritises posts in user time lines (Bucher 2012), or they might use proxy servers and feed dummy user profiles into e- commerce systems to see how prices might vary across users and locales (Wall Street Journal, detailed in Diakopoulos 2013).