2023-05-10-harnessing-data-science-for-africas-socio-economic-development.html

---
title: "Harnessing Data Science for Africa’s Socio-Economic Development"
venue: "DSA, Kigali, Rwanda"
author:
- given: Neil D.
  family: Lawrence
  url: http://inverseprobability.com
  institute: 
  twitter: lawrennd
  gscholar: 
  orcid: 
edit_url: https://github.com/lawrennd/talks/edit/gh-pages/_data-science/harnessing-data-science-for-africas-socio-economic-development.md
date: 2023-05-10
published: 2023-05-10
week: 0
reveal: 2023-05-10-harnessing-data-science-for-africas-socio-economic-development.slides.html
transition: None
ipynb: 2023-05-10-harnessing-data-science-for-africas-socio-economic-development.ipynb
layout: talk
categories:
- notes
---



<!-- Do not edit this file locally. -->
<!---->
<!-- Do not edit this file locally. -->
<!-- Do not edit this file locally. -->
<!-- The last names to be defined. Should be defined entirely in terms of macros from above-->
<!--

-->
<h2 id="henry-fords-faster-horse">Henry Ford’s Faster Horse</h2>
<div style="text-align:right">
<span class="editsection-bracket" style="">[</span><span
class="editsection"
style=""><a href="https://github.com/lawrennd/snippets/edit/main/_ai/includes/henry-ford-intro.md" target="_blank" onclick="ga('send', 'event', 'Edit Page', 'Edit', 'https://github.com/lawrennd/snippets/edit/main/_ai/includes/henry-ford-intro.md', 13);">edit</a></span><span class="editsection-bracket" style="">]</span>
</div>
<div class="figure">
<div id="ford-model-t-figure" class="figure-frame">
<div class="centered" style="">
<img class="" src="https://inverseprobability.com/slides/diagrams//ai/1925_Ford_Model_T_touring.jpg" width="70%" height="auto" align="center" style="background:none; border:none; box-shadow:none; display:block; margin-left:auto; margin-right:auto;vertical-align:middle">
</div>
</div>
<div id="ford-model-t-magnify" class="magnify"
onclick="magnifyFigure(&#39;ford-model-t&#39;)">
<img class="img-button" src="{{ '/assets/images/Magnify_Large.svg' | relative_url }}" style="width:1.5ex">
</div>
<div id="ford-model-t-caption" class="caption-frame">
<p>Figure: A 1925 Ford Model T built at Henry Ford’s Highland Park Plant
in Dearborn, Michigan. This example now resides in Australia, owned by
the founder of FordModelT.net. From <a
href="https://commons.wikimedia.org/wiki/File:1925_Ford_Model_T_touring.jpg"
class="uri">https://commons.wikimedia.org/wiki/File:1925_Ford_Model_T_touring.jpg</a></p>
</div>
</div>
<p>It’s said that Henry Ford’s customers wanted a “a faster horse”. If
Henry Ford was selling us artificial intelligence today, what would the
customer call for, “a smarter human”? That’s certainly the picture of
machine intelligence we find in science fiction narratives, but the
reality of what we’ve developed is much more mundane.</p>
<p>Car engines produce prodigious power from petrol. Machine
intelligences deliver decisions derived from data. In both cases the
scale of consumption enables a speed of operation that is far beyond the
capabilities of their natural counterparts. Unfettered energy
consumption has consequences in the form of climate change. Does
unbridled data consumption also have consequences for us?</p>
<p>If we devolve decision making to machines, we depend on those
machines to accommodate our needs. If we don’t understand how those
machines operate, we lose control over our destiny. Our mistake has been
to see machine intelligence as a reflection of our intelligence. We
cannot understand the smarter human without understanding the human. To
understand the machine, we need to better understand ourselves.</p>
<p>In Greek mythology, Panacea was the goddess of the universal remedy.
One consequence of the pervasive potential of AI is that it is
positioned, like Panacea, as the purveyor of a universal solution.
Whether it is overcoming industry’s productivity challenges, or as a
salve for strained public sector services, or a remedy for pressing
global challenges in sustainable development, AI is presented as an
elixir to resolve society’s problems.</p>
<p>In practice, translation of AI technology into practical benefit is
not simple. Moreover, a growing body of evidence shows that risks and
benefits from AI innovations are unevenly distributed across
society.</p>
<p>When carelessly deployed, AI risks exacerbating existing social and
economic inequalities.</p>
<h1 id="evolved-relationship-with-information">Evolved Relationship with
Information</h1>
<div style="text-align:right">
<span class="editsection-bracket" style="">[</span><span
class="editsection"
style=""><a href="https://github.com/lawrennd/snippets/edit/main/_data-science/includes/evolved-relationship.md" target="_blank" onclick="ga('send', 'event', 'Edit Page', 'Edit', 'https://github.com/lawrennd/snippets/edit/main/_data-science/includes/evolved-relationship.md', 13);">edit</a></span><span class="editsection-bracket" style="">]</span>
</div>
<p>The high bandwidth of computers has resulted in a close relationship
between the computer and data. Large amounts of information can flow
between the two. The degree to which the computer is mediating our
relationship with data means that we should consider it an
intermediary.</p>
<p>Originally our low bandwidth relationship with data was affected by
two characteristics. Firstly, our tendency to over-interpret driven by
our need to extract as much knowledge from our low bandwidth information
channel as possible. Secondly, by our improved understanding of the
domain of <em>mathematical</em> statistics and how our cognitive biases
can mislead us.</p>
<p>With this new set up there is a potential for assimilating far more
information via the computer, but the computer can present this to us in
various ways. If its motives are not aligned with ours then it can
misrepresent the information. This needn’t be nefarious it can be simply
because of the computer pursuing a different objective from us. For
example, if the computer is aiming to maximize our interaction time that
may be a different objective from ours which may be to summarize
information in a representative manner in the <em>shortest</em> possible
length of time.</p>
<p>For example, for me, it was a common experience to pick up my
telephone with the intention of checking when my next appointment was,
but to soon find myself distracted by another application on the phone
and end up reading something on the internet. By the time I’d finished
reading, I would often have forgotten the reason I picked up my phone in
the first place.</p>
<p>There are great benefits to be had from the huge amount of
information we can unlock from this evolved relationship between us and
data. In biology, large scale data sharing has been driven by a
revolution in genomic, transcriptomic and epigenomic measurement. The
improved inferences that can be drawn through summarizing data by
computer have fundamentally changed the nature of biological science,
now this phenomenon is also influencing us in our daily lives as data
measured by <em>happenstance</em> is increasingly used to characterize
us.</p>
<p>Better mediation of this flow requires a better understanding of
human-computer interaction. This in turn involves understanding our own
intelligence better, what its cognitive biases are and how these might
mislead us.</p>
<p>For further thoughts see Guardian article on <a
href="https://www.theguardian.com/media-network/2015/jul/23/data-driven-economy-marketing">marketing
in the internet era</a> from 2015.</p>
<p>You can also check my blog post on <a
href="http://inverseprobability.com/2015/12/04/what-kind-of-ai">System
Zero</a>. This was also written in 2015.</p>
<h2 id="new-flow-of-information">New Flow of Information</h2>
<div style="text-align:right">
<span class="editsection-bracket" style="">[</span><span
class="editsection"
style=""><a href="https://github.com/lawrennd/snippets/edit/main/_data-science/includes/new-flow-of-information.md" target="_blank" onclick="ga('send', 'event', 'Edit Page', 'Edit', 'https://github.com/lawrennd/snippets/edit/main/_data-science/includes/new-flow-of-information.md', 13);">edit</a></span><span class="editsection-bracket" style="">]</span>
</div>
<p>Classically the field of statistics focused on mediating the
relationship between the machine and the human. Our limited bandwidth of
communication means we tend to over-interpret the limited information
that we are given, in the extreme we assign motives and desires to
inanimate objects (a process known as anthropomorphizing). Much of
mathematical statistics was developed to help temper this tendency and
understand when we are valid in drawing conclusions from data.</p>
<div class="figure">
<div id="new-flow-of-information-3-figure" class="figure-frame">
<object class="svgplot " data="https://inverseprobability.com/slides/diagrams//data-science/new-flow-of-information003.svg" width="70%" style=" ">
</object>
</div>
<div id="new-flow-of-information-3-magnify" class="magnify"
onclick="magnifyFigure(&#39;new-flow-of-information-3&#39;)">
<img class="img-button" src="{{ '/assets/images/Magnify_Large.svg' | relative_url }}" style="width:1.5ex">
</div>
<div id="new-flow-of-information-3-caption" class="caption-frame">
<p>Figure: The trinity of human, data, and computer, and highlights the
modern phenomenon. The communication channel between computer and data
now has an extremely high bandwidth. The channel between human and
computer and the channel between data and human is narrow. New direction
of information flow, information is reaching us mediated by the
computer. The focus on classical statistics reflected the importance of
the direct communication between human and data. The modern challenges
of data science emerge when that relationship is being mediated by the
machine.</p>
</div>
</div>
<p>Data science brings new challenges. In particular, there is a very
large bandwidth connection between the machine and data. This means that
our relationship with data is now commonly being mediated by the
machine. Whether this is in the acquisition of new data, which now
happens by happenstance rather than with purpose, or the interpretation
of that data where we are increasingly relying on machines to summarize
what the data contains. This is leading to the emerging field of data
science, which must not only deal with the same challenges that
mathematical statistics faced in tempering our tendency to over
interpret data but must also deal with the possibility that the machine
has either inadvertently or maliciously misrepresented the underlying
data.</p>
<p>With new capabilities becoming available through very large
generational AI models, we can imagine different interfaces with that
information, but the potential for manipulation is if anything even
greater.</p>
<div class="figure">
<div id="new-flow-of-information-4-figure" class="figure-frame">
<object class="svgplot " data="https://inverseprobability.com/slides/diagrams//data-science/new-flow-of-information004.svg" width="70%" style=" ">
</object>
</div>
<div id="new-flow-of-information-4-magnify" class="magnify"
onclick="magnifyFigure(&#39;new-flow-of-information-4&#39;)">
<img class="img-button" src="{{ '/assets/images/Magnify_Large.svg' | relative_url }}" style="width:1.5ex">
</div>
<div id="new-flow-of-information-4-caption" class="caption-frame">
<p>Figure: New capabilities in language generation offer the tantalising
possibility for a better interface between the machine and it’s
understanding of data but characterising that communication channel
remains a major challenge.</p>
</div>
</div>
<h2 id="revolution">Revolution</h2>
<div style="text-align:right">
<span class="editsection-bracket" style="">[</span><span
class="editsection"
style=""><a href="https://github.com/lawrennd/snippets/edit/main/_ai/includes/cuneiform.md" target="_blank" onclick="ga('send', 'event', 'Edit Page', 'Edit', 'https://github.com/lawrennd/snippets/edit/main/_ai/includes/cuneiform.md', 13);">edit</a></span><span class="editsection-bracket" style="">]</span>
</div>
<p>Arguably the information revolution we are experiencing is
unprecedented in history. But changes in the way we share information
have a long history. Over 5,000 years ago in the city of Uruk, on the
banks of the Euphrates, communities which relied on the water to
irrigate their corps developed an approach to recording transactions in
clay. Eventually the system of recording system became sophisticated
enough that their oral histories could be recorded in the form of the
first epic: Gilgamesh.</p>
<div class="figure">
<div id="chicago-cuneiform-stone-figure" class="figure-frame">
<div class="centered" style="">
<img class="" src="https://inverseprobability.com/slides/diagrams//cuneiform/chicago-cuneiform-stone.jpg" width="40%" height="auto" align="center" style="background:none; border:none; box-shadow:none; display:block; margin-left:auto; margin-right:auto;vertical-align:middle">
</div>
</div>
<div id="chicago-cuneiform-stone-magnify" class="magnify"
onclick="magnifyFigure(&#39;chicago-cuneiform-stone&#39;)">
<img class="img-button" src="{{ '/assets/images/Magnify_Large.svg' | relative_url }}" style="width:1.5ex">
</div>
<div id="chicago-cuneiform-stone-caption" class="caption-frame">
<p>Figure: Chicago Stone, side 2, recording sale of a number of fields,
probably from Isin, Early Dynastic Period, c. 2600 BC, black basalt</p>
</div>
</div>
<p>It was initially develoepd for people as a recordd of who owed what
to whom, expanding individuals’ capacity to remember. But over a five
hundred year period writing evolved to become a tool for literature as
well. More pithily put, writing was invented by accountants not poets
(see e.g. this piece by Tim Harford <a
href="https://www.bbc.co.uk/news/business-39870485">has
highlighted</a>.</p>
<p>In some respects today’s revolution is different, because it involves
also the creation of stories as well as their curation. But in some
fundamental ways we can see what we have produced as another tool for us
in the information revolution.</p>
<h1 id="the-future-of-professions">The Future of Professions</h1>
<div style="text-align:right">
<span class="editsection-bracket" style="">[</span><span
class="editsection"
style=""><a href="https://github.com/lawrennd/snippets/edit/main/_books/includes/the-future-of-professions.md" target="_blank" onclick="ga('send', 'event', 'Edit Page', 'Edit', 'https://github.com/lawrennd/snippets/edit/main/_books/includes/the-future-of-professions.md', 13);">edit</a></span><span class="editsection-bracket" style="">]</span>
</div>
<div class="figure">
<div id="the-future-of-professions-figure" class="figure-frame">
<div class="centered" style="">
<img class="" src="https://inverseprobability.com/slides/diagrams//books/the-future-of-professions.jpg" width="40%" height="auto" align="center" style="background:none; border:none; box-shadow:none; display:block; margin-left:auto; margin-right:auto;vertical-align:middle">
</div>
</div>
<div id="the-future-of-professions-magnify" class="magnify"
onclick="magnifyFigure(&#39;the-future-of-professions&#39;)">
<img class="img-button" src="{{ '/assets/images/Magnify_Large.svg' | relative_url }}" style="width:1.5ex">
</div>
<div id="the-future-of-professions-caption" class="caption-frame">
<p>Figure: <a
href="https://www.amazon.co.uk/Future-Professions-Technology-Transform-Experts/dp/0198713398">The
Future of Professions</a> <span class="citation"
data-cites="Susskind-future15">(Susskind and Susskind, 2015)</span> is a
2015 book focussed on how the next wave of technology revolution is
going to effect the professions.</p>
</div>
</div>
<p>A question, to what extent do these challenges vary for the African
continent? Many of the skills that we are considering will be undermined
by ChatGPT aand equivalent technologies are actually skills that are
lacking on the continent, so does this provide an opportunity for
DSA?</p>
<p>There is potential for both explicit and implicit discrimination on
the basis of race, religion, sexuality or health status. All of these
are prohibited under European law but can pass unawares or be
implicit.</p>
<p>The GDPR is the General Data Protection Regulation, but a better name
for it would simply be Good Data Practice Rules. It covers how to deal
with discrimination which has a consequential effect on the individual.
For example, entrance to university, access to loans or insurance. But
the new phenomenon is dealing with a series of inconsequential decisions
that taken together have a consequential effect.</p>
<div class="figure">
<div id="woman-tends-house-in-village-of-uganda-africa-figure"
class="figure-frame">
<div class="centered" style="">
<img class="" src="https://inverseprobability.com/slides/diagrams//woman-tends-house-in-village-of-uganda-africa.jpg" width="60%" height="auto" align="center" style="background:none; border:none; box-shadow:none; display:block; margin-left:auto; margin-right:auto;vertical-align:middle">
</div>
</div>
<div id="woman-tends-house-in-village-of-uganda-africa-magnify"
class="magnify"
onclick="magnifyFigure(&#39;woman-tends-house-in-village-of-uganda-africa&#39;)">
<img class="img-button" src="{{ '/assets/images/Magnify_Large.svg' | relative_url }}" style="width:1.5ex">
</div>
<div id="woman-tends-house-in-village-of-uganda-africa-caption"
class="caption-frame">
<p>Figure: A woman tends her house in a village in Uganda.</p>
</div>
</div>
<p>Statistics as a community is also focused on the single consequential
effect of an analysis (efficacy of drugs, or distribution of Mosquito
nets). Associated with happenstance data is <em>happenstance decision
making</em>.</p>
<p>These algorithms behind these decisions are developed in a particular
context. The so-called Silicon Valley bubble. But they are deployed
across the world. To address this, a key challenge is capacity building
in contexts which are remote from the Western norm.</p>
<h2 id="coin-pusher">Coin Pusher</h2>
<div style="text-align:right">
<span class="editsection-bracket" style="">[</span><span
class="editsection"
style=""><a href="https://github.com/lawrennd/snippets/edit/main/_policy/includes/coin-pusher.md" target="_blank" onclick="ga('send', 'event', 'Edit Page', 'Edit', 'https://github.com/lawrennd/snippets/edit/main/_policy/includes/coin-pusher.md', 13);">edit</a></span><span class="editsection-bracket" style="">]</span>
</div>
<p>Disruption of society is like a coin pusher, it’s those who are
already on the edge who are most likely to be effected by
disruption.</p>
<div class="figure">
<div id="coin-pusher-figure" class="figure-frame">
<div class="centered" style="">
<img class="" src="https://inverseprobability.com/slides/diagrams//policy/Coin_pusher_2.jpg" width="70%" height="auto" align="center" style="background:none; border:none; box-shadow:none; display:block; margin-left:auto; margin-right:auto;vertical-align:middle">
</div>
</div>
<div id="coin-pusher-magnify" class="magnify"
onclick="magnifyFigure(&#39;coin-pusher&#39;)">
<img class="img-button" src="{{ '/assets/images/Magnify_Large.svg' | relative_url }}" style="width:1.5ex">
</div>
<div id="coin-pusher-caption" class="caption-frame">
<p>Figure: A coin pusher is a game where coins are dropped into th etop
of the machine, and they disrupt those on the existing steps. With any
coin drop, many coins move, but it is those on the edge, who are often
only indirectly effected, but also most traumatically effected by the
change.</p>
</div>
</div>
<p>One danger of the current hype around ChatGPT is that we are overly
focussing on the fact that it seems to have significant effect on
professional jobs, people are naturally asking the question “what does
it do for my role?”. No doubt, there will be disruption, but the coin
pusher hypothesis suggests that that disruption will likely involve
movement on the same step. However it is those on the edge already, who
are often not working directly in the information economy, who often
have less of a voice in the policy conversation who are likely to be
most disrupted.</p>
<h2 id="royal-society-report">Royal Society Report</h2>
<div style="text-align:right">
<span class="editsection-bracket" style="">[</span><span
class="editsection"
style=""><a href="https://github.com/lawrennd/snippets/edit/main/_ml/includes/rs-report-machine-learning.md" target="_blank" onclick="ga('send', 'event', 'Edit Page', 'Edit', 'https://github.com/lawrennd/snippets/edit/main/_ml/includes/rs-report-machine-learning.md', 13);">edit</a></span><span class="editsection-bracket" style="">]</span>
</div>
<div class="figure">
<div id="ml-report-cover-figure" class="figure-frame">
<div class="centered" style="">
<img class="" src="https://inverseprobability.com/slides/diagrams//ml/ml-report-cover-page.png" width="" height="auto" align="center" style="background:none; border:none; box-shadow:none; display:block; margin-left:auto; margin-right:auto;vertical-align:middle">
</div>
</div>
<div id="ml-report-cover-magnify" class="magnify"
onclick="magnifyFigure(&#39;ml-report-cover&#39;)">
<img class="img-button" src="{{ '/assets/images/Magnify_Large.svg' | relative_url }}" style="width:1.5ex">
</div>
<div id="ml-report-cover-caption" class="caption-frame">
<p>Figure: The Royal Society report on Machine Learning was released on
25th April 2017</p>
</div>
</div>
<p>A useful reference for state of the art in machine learning is the UK
Royal Society Report, <a
href="https://royalsociety.org/~/media/policy/projects/machine-learning/publications/machine-learning-report.pdf">Machine
Learning: Power and Promise of Computers that Learn by Example</a>.</p>
<h2 id="public-research">Public Research</h2>
<div style="text-align:right">
<span class="editsection-bracket" style="">[</span><span
class="editsection"
style=""><a href="https://github.com/lawrennd/snippets/edit/main/_ml/includes/rs-report-mori-poll-art.md" target="_blank" onclick="ga('send', 'event', 'Edit Page', 'Edit', 'https://github.com/lawrennd/snippets/edit/main/_ml/includes/rs-report-mori-poll-art.md', 13);">edit</a></span><span class="editsection-bracket" style="">]</span>
</div>
<div class="figure">
<div id="rs-report-mori-poll-cover-figure" class="figure-frame">
<div class="centered" style="">
<img class="" src="https://inverseprobability.com/slides/diagrams//ml/rs-report-mori-poll-cover.png" width="" height="auto" align="center" style="background:none; border:none; box-shadow:none; display:block; margin-left:auto; margin-right:auto;vertical-align:middle">
</div>
</div>
<div id="rs-report-mori-poll-cover-magnify" class="magnify"
onclick="magnifyFigure(&#39;rs-report-mori-poll-cover&#39;)">
<img class="img-button" src="{{ '/assets/images/Magnify_Large.svg' | relative_url }}" style="width:1.5ex">
</div>
<div id="rs-report-mori-poll-cover-caption" class="caption-frame">
<p>Figure: The Royal Society comissioned <a
href="https://royalsociety.org/-/media/policy/projects/machine-learning/publications/public-views-of-machine-learning-ipsos-mori.pdf">public
research from Mori</a> as part of the machine learning review.</p>
</div>
</div>
<div class="figure">
<div id="rs-report-mori-poll-1-figure" class="figure-frame">
<div class="centered" style="">
<img class="" src="https://inverseprobability.com/slides/diagrams//ml/rs-mori-views-of-specific-ml-applications-1.png" width="" height="auto" align="center" style="background:none; border:none; box-shadow:none; display:block; margin-left:auto; margin-right:auto;vertical-align:middle">
</div>
</div>
<div id="rs-report-mori-poll-1-magnify" class="magnify"
onclick="magnifyFigure(&#39;rs-report-mori-poll-1&#39;)">
<img class="img-button" src="{{ '/assets/images/Magnify_Large.svg' | relative_url }}" style="width:1.5ex">
</div>
<div id="rs-report-mori-poll-1-caption" class="caption-frame">
<p>Figure: One of the questions focussed on machine learning
applications.</p>
</div>
</div>
<div class="figure">
<div id="rs-report-mori-poll-2-figure" class="figure-frame">
<div class="centered" style="">
<img class="" src="https://inverseprobability.com/slides/diagrams//ml/rs-mori-views-of-specific-ml-applications-2.png" width="" height="auto" align="center" style="background:none; border:none; box-shadow:none; display:block; margin-left:auto; margin-right:auto;vertical-align:middle">
</div>
</div>
<div id="rs-report-mori-poll-2-magnify" class="magnify"
onclick="magnifyFigure(&#39;rs-report-mori-poll-2&#39;)">
<img class="img-button" src="{{ '/assets/images/Magnify_Large.svg' | relative_url }}" style="width:1.5ex">
</div>
<div id="rs-report-mori-poll-2-caption" class="caption-frame">
<p>Figure: The public were broadly supportive of a range of application
areas.</p>
</div>
</div>
<div class="figure">
<div id="rs-report-mori-poll-3-figure" class="figure-frame">
<div class="centered" style="">
<img class="" src="https://inverseprobability.com/slides/diagrams//ml/rs-mori-views-of-specific-ml-applications-3.png" width="" height="auto" align="center" style="background:none; border:none; box-shadow:none; display:block; margin-left:auto; margin-right:auto;vertical-align:middle">
</div>
</div>
<div id="rs-report-mori-poll-3-magnify" class="magnify"
onclick="magnifyFigure(&#39;rs-report-mori-poll-3&#39;)">
<img class="img-button" src="{{ '/assets/images/Magnify_Large.svg' | relative_url }}" style="width:1.5ex">
</div>
<div id="rs-report-mori-poll-3-caption" class="caption-frame">
<p>Figure: But they failed to see the point in AI’s that could produce
poetry.</p>
</div>
</div>
<h2 id="mercutio">Mercutio</h2>
<div style="text-align:right">
<span class="editsection-bracket" style="">[</span><span
class="editsection"
style=""><a href="https://github.com/lawrennd/snippets/edit/main/_ml/includes/chat-gpt-mercutio.md" target="_blank" onclick="ga('send', 'event', 'Edit Page', 'Edit', 'https://github.com/lawrennd/snippets/edit/main/_ml/includes/chat-gpt-mercutio.md', 13);">edit</a></span><span class="editsection-bracket" style="">]</span>
</div>
<p>It’s ironic that despite the public focus on transport, health,
cities, crime and their confusion as to why we might want AI to do art,
one area where significant progress has been made is on AIs that can
create literature.</p>
<div class="figure">
<div id="chat-gpt-mercutio-figure" class="figure-frame">
<div class="centered" style="">
<img class="" src="https://inverseprobability.com/slides/diagrams//ml/chat-gpt-mercutio-2.png" width="70%" height="auto" align="center" style="background:none; border:none; box-shadow:none; display:block; margin-left:auto; margin-right:auto;vertical-align:middle">
</div>
</div>
<div id="chat-gpt-mercutio-magnify" class="magnify"
onclick="magnifyFigure(&#39;chat-gpt-mercutio&#39;)">
<img class="img-button" src="{{ '/assets/images/Magnify_Large.svg' | relative_url }}" style="width:1.5ex">
</div>
<div id="chat-gpt-mercutio-caption" class="caption-frame">
<p>Figure: Despite the public’s desire to see challenges in health,
finance, transport, crime solved by machine learning and their
skepticism around poetry, one of the problems we have solved seems to be
poetry.</p>
</div>
</div>
<blockquote>
<p><strong>User</strong>: Hi ChatGPT, Could you write soliloquy that
introduces what a Large Language Model is as spoken by Mercutio?</p>
<p><strong>Machine</strong>: Ah, friends, lend me your ears, I prithee,
For now I must utter a tale of wonder, Of a creation divine, called the
Large Language Model, An oracle, a sorcerer, a wordsmith, yea verily, a
master of the quill.</p>
<p>From the depths of this scholarly dominion, A creature of artifice
did rise; Twas wrought of ones and zeroes, woven as if by Puck’s own
hand, To mimic our thoughts, our voice, our very essence.</p>
<p>A thousand minds, nay, a millionfold, Conjoined in this digital
Athenaeum, Words and phrases, like soldiers in battle, Marching to form
the verses of our age.</p>
<p>This Large Language Model, a changeling so fair, Hath the power to
bring forth wisdom, To transmute our queries, our curiosities, Into
answers, clear as a midsummer’s day.</p>
<p>Yet, beware, my companions, for magic hath its limits, Not unlike the
mortal bounds of we who dwell in flesh, The Large Language Model hath
its strengths, But ’tis not an all-knowing oracle, a god it is not.</p>
<p>As Mercutio, your humble servant, doth stand before thee, I marvel at
the art and science that hath brought forth this wondrous creation, This
Large Language Model, a testament to man’s yearning, To comprehend the
world and make meaning of the great tapestry of existence.</p>
<p>In faith, dear friends, let us embrace the magic and beauty of this
digital bard, And mayhaps, by its grace, we shall glean some wisdom, As
we wander together, hand in hand, Through this boundless realm of
knowledge and wonder.</p>
<p>ChatGPT transcript, 14th April 2023.</p>
</blockquote>
<h2 id="p-fairness-and-n-fairness"><span
class="math inline">\(p\)</span>-Fairness and <span
class="math inline">\(n\)</span>-Fairness</h2>
<div style="text-align:right">
<span class="editsection-bracket" style="">[</span><span
class="editsection"
style=""><a href="https://github.com/lawrennd/snippets/edit/main/_ai/includes/p-n-fairness.md" target="_blank" onclick="ga('send', 'event', 'Edit Page', 'Edit', 'https://github.com/lawrennd/snippets/edit/main/_ai/includes/p-n-fairness.md', 13);">edit</a></span><span class="editsection-bracket" style="">]</span>
</div>
<div class="figure">
<div id="n-p-fairness-figure" class="figure-frame">
<object class data="https://inverseprobability.com/slides/diagrams//ai/n-p-fairness.svg" width="80%" style=" ">
</object>
</div>
<div id="n-p-fairness-magnify" class="magnify"
onclick="magnifyFigure(&#39;n-p-fairness&#39;)">
<img class="img-button" src="{{ '/assets/images/Magnify_Large.svg' | relative_url }}" style="width:1.5ex">
</div>
<div id="n-p-fairness-caption" class="caption-frame">
<p>Figure: We seem to have two different aspects to fairness, which in
practice can be in tension.</p>
</div>
</div>
<p>We’ve outlined <span class="math inline">\(n\)</span>-fairness and
<span class="math inline">\(p\)</span>-fairness. By <span
class="math inline">\(n\)</span>-fairness we mean the sort of
considerations that are associated with <em>substantive</em> equality of
opportunity vs <em>formal</em> equality of opportunity. Formal equality
of community is related to <span
class="math inline">\(p\)</span>-fairness. This is sometimes called
procedural fairness and we might think of it as a <em>performative</em>
form of fairness. It’s about clarity of rules, for example as applied in
sport. <span class="math inline">\(n\)</span>-Fairness is more nuanced.
It’s a reflection of society’s normative judgment about how individuals
may have been disadvantaged, e.g. due to their upbringing.</p>
<p>The important point here is that these forms of fairness are in
tension. Good procedural fairness needs to be clear and understandable.
It should be clear to everyone what the rules are, they shouldn’t be
obscured by jargon or overly subtle concepts. <span
class="math inline">\(p\)</span>-Fairness should not be easily
undermined by adversaries, it should be difficult to “cheat” good <span
class="math inline">\(p\)</span>-fairness. However, <span
class="math inline">\(n\)</span>-fairness requires nuance, understanding
of the human condition, where we came from and how different individuals
in our society have been advantaged or disadvantaged in their upbringing
and their access to opportunity.</p>
<p>Pure <span class="math inline">\(n\)</span>-fairness and pure <span
class="math inline">\(p\)</span>-fairness both have the feeling of
dystopias. In practice, any decision making system needs to balance the
two. The correct point of operation will depend on the context of the
decision. Consider fair rules of a game of football, against fair
distribution of social benefit. It is unlikely that there is ever an
objectively correct balance between the two for any given context.
Different individuals will favour <span class="math inline">\(p\)</span>
vs <span class="math inline">\(n\)</span> according to their personal
values.</p>
<p>Given the tension between the two forms of fairness, with <span
class="math inline">\(p\)</span> fairness requiring simple rules that
are understandable by all, and <span class="math inline">\(n\)</span>
fairness requiring nuance and subtlety, how do we resolve this tension
in practice?</p>
<p>Normally in human systems, significant decisions involve trained
professionals. For example, judges, or accountants or doctors.</p>
<p>Training a professional involves lifting their “reflexive” response
to a situation with “reflective” thinking about the consequences of
their decision that rely not just on the professional’s expertise, but
also their knowledge of what it is to be a human.</p>
<p>This <em>marvellous</em> resolution exploits the fact that while
humans are increadibly complicated nuanced entities, other humans have
an intuitive ability to understand their motivations and values. So the
human is a complex entity that seems simple to other humans.</p>
<h2 id="a-question-of-trust">A Question of Trust</h2>
<div style="text-align:right">
<span class="editsection-bracket" style="">[</span><span
class="editsection"
style=""><a href="https://github.com/lawrennd/snippets/edit/main/_books/includes/a-question-of-trust.md" target="_blank" onclick="ga('send', 'event', 'Edit Page', 'Edit', 'https://github.com/lawrennd/snippets/edit/main/_books/includes/a-question-of-trust.md', 13);">edit</a></span><span class="editsection-bracket" style="">]</span>
</div>
<p>In Baroness Onora O’Neill’s Reeith Lectures from 2002, she raises the
challenge of trust. There are many aspects to her arcuments, but one of
the key points she makes is that we cannot trust without the notion of
duty. O’Neill is bemoaning the substitution of duty with process. The
idea is that processes and transparency are supposed to hold us to
account by measuring outcomes. But these processes themselves overwhelm
decision makers and undermine their professional duty to deliver the
right outcome.</p>
<div class="figure">
<div id="a-question-of-trust-figure" class="figure-frame">
<div class="centered" style="">
<img class="" src="https://inverseprobability.com/slides/diagrams//books/a-question-of-trust.jpg" width="40%" height="auto" align="center" style="background:none; border:none; box-shadow:none; display:block; margin-left:auto; margin-right:auto;vertical-align:middle">
</div>
</div>
<div id="a-question-of-trust-magnify" class="magnify"
onclick="magnifyFigure(&#39;a-question-of-trust&#39;)">
<img class="img-button" src="{{ '/assets/images/Magnify_Large.svg' | relative_url }}" style="width:1.5ex">
</div>
<div id="a-question-of-trust-caption" class="caption-frame">
<p>Figure: <a href="https://www.bbc.co.uk/programmes/p00gpzfq">A
Question of Trust by Onora O’Neil</a> which examines the nature of trust
and its role in society.</p>
</div>
</div>
<blockquote>
<p>Again Univesities are to treat each applicant fairly on the basis of
ability and promise, but they are supposed also to admit a socially more
representative intake.</p>
<p>There’s no guarantee that the process meets the target.</p>
<p>Onora O’Neill <em>A Question of Trust: Called to Account</em> Reith
Lectures 2002 <span class="citation" data-cites="ONeill-trust02">O’Neill
(2002)</span>]</p>
</blockquote>
<p>O’Neill is speaking in 2002, in the early days of the internet and
before social media. Much of her thoughts are even more relevant for
today than they were when she spoke. This is because the increased
availability of information and machine driven decision-making makes the
mistaken premise, that process is an adequate substitute for duty, more
apparently plausible. But this undermines what O’Neill calls
“intelligent accountability”, which is not accounting by the numbers,
but through professional education and institutional safeguards.</p>
<h2 id="naca-langley">NACA Langley</h2>
<div style="text-align:right">
<span class="editsection-bracket" style="">[</span><span
class="editsection"
style=""><a href="https://github.com/lawrennd/snippets/edit/main/_ai/includes/naca-proving.md" target="_blank" onclick="ga('send', 'event', 'Edit Page', 'Edit', 'https://github.com/lawrennd/snippets/edit/main/_ai/includes/naca-proving.md', 13);">edit</a></span><span class="editsection-bracket" style="">]</span>
</div>
<div class="figure">
<div id="naca-lmal-42612-figure" class="figure-frame">
<div class="centered" style="">
<img class="" src="https://inverseprobability.com/slides/diagrams//ai/NACA-LMAL-42612.jpg" width="60%" height="auto" align="center" style="background:none; border:none; box-shadow:none; display:block; margin-left:auto; margin-right:auto;vertical-align:middle">
</div>
</div>
<div id="naca-lmal-42612-magnify" class="magnify"
onclick="magnifyFigure(&#39;naca-lmal-42612&#39;)">
<img class="img-button" src="{{ '/assets/images/Magnify_Large.svg' | relative_url }}" style="width:1.5ex">
</div>
<div id="naca-lmal-42612-caption" class="caption-frame">
<p>Figure: 1945 photo of the NACA test pilots, from left Mel Gough, Herb
Hoover, Jack Reeder, Stefan Cavallo and Bill Gray (photo NASA, NACA LMAL
42612)</p>
</div>
</div>
<p>The NACA Langley Field proving ground tested US aircraft. Bob Gilruth
worked on the <a
href="https://ntrs.nasa.gov/search.jsp?R=19930091834">flying qualities
of aircraft</a>. One of his collaborators suggested that</p>
<blockquote>
<p>Hawker Hurricane airplane. A heavily armed fighter airplane noted for
its role in the Battle of Britain, the Hurricane’s flying qualities were
found to be generally satisfactory. The most notable deficiencies were
heavy aileron forces at high speeds and large friction in the
controls.</p>
<p>W. Hewitt Phillips<a href="#fn1" class="footnote-ref" id="fnref1"
role="doc-noteref"><sup>1</sup></a></p>
</blockquote>
<p>and</p>
<blockquote>
<p>Supermarine Spitfire airplane. A high-performance fighter noted for
its role in the Battle of Britain and throughout WW II, the Spitfire had
desirably light elevator control forces in maneuvers and near neutral
longitudinal stability. Its greatest deficiency from the combat
standpoint was heavy aileron forces and sluggish roll response at high
speeds.</p>
<p>W. Hewitt Phillips<a href="#fn2" class="footnote-ref" id="fnref2"
role="doc-noteref"><sup>2</sup></a></p>
</blockquote>
<p>Gilruth went beyond the reports of feel to characterise how the plane
should respond to different inputs on the control stick. In other words
he quantified that feel of the plane.</p>
<h2 id="ai-proving-grounds">AI Proving Grounds</h2>
<p>We need mechanisms to rapidly understand the capabilities of these
new tools, what is the potential of the technology, and what are the
pitfalls? With this in mind we can build a societal AI capability that
means understanding is pervasive.</p>
<p>Innovating to serve science and society requires a pipeline of
interventions. As well as advances in the technical capabilities of AI
technologies, engineering knowhow is required to safely deploy and
monitor those solutions in practice. Regulatory frameworks need to adapt
to ensure trustworthy use of these technologies. Aligning technology
development with public interests demands effective stakeholder
engagement to bring diverse voices and expertise into technology
design.</p>
<p>Building this pipeline will take coordination across research,
engineering, policy and practice. It also requires action to address the
digital divides that influence who benefits from AI advances. These
include digital divides within the socioeconomic strata that need to be
overcome – AI must not exacerbate existing equalities or create new
ones. In addressing these challenges, we can be hindered by divides that
exist between traditional academic disciplines. We need to develop
common understanding of the problems and a shared knowledge of possible
solutions.</p>
<h2 id="making-ai-equitable">Making AI equitable</h2>
<h2 id="data-science-africa">Data Science Africa</h2>
<div style="text-align:right">
<span class="editsection-bracket" style="">[</span><span
class="editsection"
style=""><a href="https://github.com/lawrennd/snippets/edit/main/_data-science/includes/data-science-africa.md" target="_blank" onclick="ga('send', 'event', 'Edit Page', 'Edit', 'https://github.com/lawrennd/snippets/edit/main/_data-science/includes/data-science-africa.md', 13);">edit</a></span><span class="editsection-bracket" style="">]</span>
</div>
<div class="figure">
<div id="data-science-africa-figure" class="figure-frame">
<div class="centered" style="">
<img class="" src="https://inverseprobability.com/slides/diagrams//data-science-africa-logo.png" width="30%" height="auto" align="center" style="background:none; border:none; box-shadow:none; display:block; margin-left:auto; margin-right:auto;vertical-align:middle">
</div>
</div>
<div id="data-science-africa-magnify" class="magnify"
onclick="magnifyFigure(&#39;data-science-africa&#39;)">
<img class="img-button" src="{{ '/assets/images/Magnify_Large.svg' | relative_url }}" style="width:1.5ex">
</div>
<div id="data-science-africa-caption" class="caption-frame">
<p>Figure: Data Science Africa <a href="http://datascienceafrica.org"
class="uri">http://datascienceafrica.org</a> is a ground up initiative
for capacity building around data science, machine learning and
artificial intelligence on the African continent.</p>
</div>
</div>
<div class="figure">
<div id="dsa-events-october-2021-figure" class="figure-frame">
<object class="svgplot " data="https://inverseprobability.com/slides/diagrams//dsa/dsa-events-october-2021.svg" width="60%" style=" ">
</object>
</div>
<div id="dsa-events-october-2021-magnify" class="magnify"
onclick="magnifyFigure(&#39;dsa-events-october-2021&#39;)">
<img class="img-button" src="{{ '/assets/images/Magnify_Large.svg' | relative_url }}" style="width:1.5ex">
</div>
<div id="dsa-events-october-2021-caption" class="caption-frame">
<p>Figure: Data Science Africa meetings held up to October 2021.</p>
</div>
</div>
<p>Data Science Africa is a bottom up initiative for capacity building
in data science, machine learning and artificial intelligence on the
African continent.</p>
<p>As of May 2023 there have been eleven workshops and schools, located
in seven different countries: Nyeri, Kenya (twice); Kampala, Uganda;
Arusha, Tanzania; Abuja, Nigeria; Addis Ababa, Ethiopia; Accra, Ghana;
Kampala, Uganda and Kimberley, South Africa (virtual), and in Kigali,
Rwanda.</p>
<p>The main notion is <em>end-to-end</em> data science. For example,
going from data collection in the farmer’s field to decision making in
the Ministry of Agriculture. Or going from malaria disease counts in
health centers to medicine distribution.</p>
<p>The philosophy is laid out in <span class="citation"
data-cites="Lawrence:dsa15">(Lawrence, 2015)</span>. The key idea is
that the modern <em>information infrastructure</em> presents new
solutions to old problems. Modes of development change because less
capital investment is required to take advantage of this infrastructure.
The philosophy is that local capacity building is the right way to
leverage these challenges in addressing data science problems in the
African context.</p>
<p>Data Science Africa is now a non-govermental organization registered
in Kenya. The organising board of the meeting is entirely made up of
scientists and academics based on the African continent.</p>
<div class="figure">
<div id="africa-benefit-data-revolution-figure" class="figure-frame">
<div class="centered" style="">
<img class="" src="https://inverseprobability.com/slides/diagrams//data-science/africa-benefit-data-revolution.png" width="70%" height="auto" align="center" style="background:none; border:none; box-shadow:none; display:block; margin-left:auto; margin-right:auto;vertical-align:middle">
</div>
</div>
<div id="africa-benefit-data-revolution-magnify" class="magnify"
onclick="magnifyFigure(&#39;africa-benefit-data-revolution&#39;)">
<img class="img-button" src="{{ '/assets/images/Magnify_Large.svg' | relative_url }}" style="width:1.5ex">
</div>
<div id="africa-benefit-data-revolution-caption" class="caption-frame">
<p>Figure: The lack of existing physical infrastructure on the African
continent makes it a particularly interesting environment for deploying
solutions based on the <em>information infrastructure</em>. The idea is
explored more in this Guardian op-ed on Guardian article on <a
href="https://www.theguardian.com/media-network/2015/aug/25/africa-benefit-data-science-information">How
African can benefit from the data revolution</a>.</p>
</div>
</div>
<p>Guardian article on <a
href="https://www.theguardian.com/media-network/2015/aug/25/africa-benefit-data-science-information">Data
Science Africa</a></p>
<h2 id="thanks">Thanks!</h2>
<p>For more information on these subjects and more you might want to
check the following resources.</p>
<ul>
<li>twitter: <a href="https://twitter.com/lawrennd">@lawrennd</a></li>
<li>podcast: <a href="http://thetalkingmachines.com">The Talking
Machines</a></li>
<li>newspaper: <a
href="http://www.theguardian.com/profile/neil-lawrence">Guardian Profile
Page</a></li>
<li>blog: <a
href="http://inverseprobability.com/blog.html">http://inverseprobability.com</a></li>
</ul>
<h1 class="unnumbered" id="references">References</h1>
<div id="refs" class="references csl-bib-body hanging-indent"
role="list">
<div id="ref-Lawrence:dsa15" class="csl-entry" role="listitem">
Lawrence, N.D., 2015. <a
href="https://www.theguardian.com/media-network/2015/aug/25/africa-benefit-data-science-information">How
<span>A</span>frica can benefit from the data revolution</a>.
</div>
<div id="ref-ONeill-trust02" class="csl-entry" role="listitem">
O’Neill, O., 2002. A question of trust. Cambridge University Press.
</div>
<div id="ref-Susskind-future15" class="csl-entry" role="listitem">
Susskind, R.E., Susskind, D., 2015. The future of the professions: How
technology will transform the work of human experts. Oxford University
Press.
</div>
</div>
<aside id="footnotes" class="footnotes footnotes-end-of-document"
role="doc-endnotes">
<hr />
<ol>
<li id="fn1"><p>monographs<a href="#fnref1" class="footnote-back"
role="doc-backlink">↩︎</a></p></li>
<li id="fn2"><p>monographs<a href="#fnref2" class="footnote-back"
role="doc-backlink">↩︎</a></p></li>
</ol>
</aside>