Upgrade to Pro — share decks privately, control downloads, hide ads and more …

AI For Good - Machine Learning For Kids

AI For Good - Machine Learning For Kids

AI For Good - Machine Learning For Kids

Nishan Chathuranga

November 07, 2020
Tweet

More Decks by Nishan Chathuranga

Other Decks in Education

Transcript

  1. NISHAN CHATHURANGA
    Software Engineer
    99X (Pvt) Ltd.
    University of Moratuwa
    Faculty of Information Technology
    WHO AM I

    View Slide

  2. AI FOR GOOD
    “Whether we are based on carbon or
    on silicon makes no fundamental
    difference; we should each be treated
    with appropriate respect.”
    - Sir Arthur C. Clarke (16 December 1917 – 19
    March 2008), 2010: Odyssey Two
    GITHUB REPOS - github.com/MLforKids
    USING ARIMA MODEL - bit.ly/AIforGoodArima
    USING PROPHET LIBRARY - bit.ly/AIforGoodProphet

    View Slide

  3. AI FOR GOOD
    Lecture #1

    View Slide

  4. LINE UP..
    AI FOR EARTH
    AI FOR
    CULTURAL HERITAGE
    DEMO
    Q/A

    View Slide

  5. AI FOR EARTH

    View Slide

  6. Understand the various ways AI can
    be used to make learning and life
    easier for the less privileged.
    Understand the severity of people’s
    actions and the toll it takes on the
    earth.
    > Learning Outcomes: AI for Earth

    View Slide

  7. How often have you heard that species of flora and fauna are
    facing extinction? Or forests are being cut down to create
    dwelling facilities?
    In the above-mentioned examples, we find that due to
    exploitation of the natural resources of the Earth, biodiversity is
    greatly affected.
    Animals, birds, insects are losing their habitats and are moving
    out of their designated areas. There are many areas on the
    Earth which are inhospitable for humans due to hostile climatic
    conditions.
    However, this cannot prevent us from conserving the flora and
    fauna at these places.
    AI FOR EARTH

    View Slide

  8. Using Satellite imagery for forest management
    Conserving our forests and
    what they contain (plants,
    animals, birds, insects etc.)
    will help us not only
    preserve its biodiversity but
    also help in tackling the
    challenges of global
    warming.
    It is essential to monitor our
    forests and the land they
    take up.
    Artificial Intelligence plays a
    particularly important role
    in such a scenario.
    Video: Mapping the future
    of our forests with Microsoft
    AI
    Satellite Imagery for Forest Management

    View Slide

  9. According to the University of British Columbia, “countries drastically underreport the number of fish caught
    worldwide.
    The new estimate, puts the annual global catch at roughly 109 million metric tons, about 30 per cent higher than the
    77 million officially reported in 2010 by more than 200 countries and territories.
    This means that 32 million metric tons of fish goes unreported every year, more than the weight of the entire
    population of the United States”.
    Sustainability for Global Fishing

    View Slide

  10. Enabling Precision Conservation and Sustainable
    Agriculture Practices
    In today’s age, as resources become
    scarce, it is imperative to ensure that we
    use the available resources in the best
    and most efficient way possible.
    In order to achieve this goal, we should
    adopt sustainable agricultural practices
    such as precision farming or precision
    agriculture.

    View Slide

  11. Enabling Precision Conservation and Sustainable Agriculture
    Practices
    Another term that needs
    to be understood in the
    same context is precision
    agronomics.
    This means to provide
    accurate farming
    techniques for the
    planting and growing of
    crops, and involves the
    following.
    Variable Rate Technology GPS Soil Sampling
    Computer Based Applications Remote Sensing Technology
    It involves the following:

    View Slide

  12. Enabling Precision Conservation and Sustainable Agriculture
    Practices
    CIC Holdings PLC (CIC), recently announced their latest innovation, the use of agriculture drones
    for Precision Agriculture Practices – Smart Farming. The technology helps to scan fields and
    distribute agro chemicals and fertilizer with the minimum human involvement and wastage. This
    is the first time in the world that areas are being identified and automatically treated using the
    drone and GPS technology.
    https://www.cic.lk/ci
    c-introduces-smart-
    farming-to-sri-lanka/

    View Slide

  13. Enabling Precision Conservation and Sustainable Agriculture
    Practices
    How does precision farming
    benefit farmers, and why should
    they choose it over traditional
    ways of farming?
    Here are a few reasons which
    makes it amply clear as to why
    precision farming is more
    beneficial over the age-old
    methods of farming.
    Video: Drones, scanners and GPS
    all part of the 'precision farming'
    arsenal
    Increases
    agricultural
    productivity
    Prevents soil
    degradation
    Reduces the
    application of
    chemicals in
    crop production
    More efficient
    use of water
    resources
    Disseminates
    modern farm
    practices to
    improve quality,
    quantity and
    reduced cost of
    production
    Develops more
    favorable
    attitudes
    Changes the
    socio-
    economic
    status of
    farmers

    View Slide

  14. Climate Related Risk
    One of the many changes that we see
    happening is global warming and its
    impact on climate change.
    Climate change is one of the biggest
    challenges that the world has ever faced.
    The consequences are enormous and are
    affecting not only we humans but also
    flora and fauna globally.

    View Slide

  15. AI for
    CULTURAL HERITAGE

    View Slide

  16. AI for Cultural Heritage
    Thinking of AI as a medium
    which changes our lives, what
    examples can you think of?
    Often the examples are chatbots,
    AI-powered personal digital
    assistants, apps working on
    sophisticated behavioural
    algorithms, AI-powered drones,
    self-driving cars, shopping bots,
    etc.
    AI is being used for the good of humanity in providing access
    and promoting a greater understanding of the rich and diverse
    cultural heritage of the bygone era.

    View Slide

  17. Preservation and Enrichment of Cultural Heritage around the
    World
    Oldest existing map engraved on this mammoth tusk, dated 25,000 BC
    In ancient times, going on a
    voyage was a matter of great
    concern as there were no
    maps.
    People had to rely on the
    North Star, the sun and the
    constellations to navigate.
    Though maps are known to
    have existed as early as 2300
    BCE on Babylonian clay tablets,
    cartography became a full-
    fledged science only during the
    era of the Greeks.
    Ptolemy is one of the most
    prominent Greek astronomers and
    geographers of his time.
    It is he who created the first world
    map by depicting the ‘Old World’
    from about 60°N to 30°S latitude.
    In France during the 17th and 18th
    centuries there was a trend of
    making 3D maps.
    These were large scale maps that
    were painstakingly precision built.
    Rulers of the time such as Napoleon
    and King Louis XVI considered them
    a strategic tool and as such kept
    them hidden from public view.

    View Slide

  18. Engaging with Communities around the World for Language
    Preservation
    Map by Ethnologue by SIL International
    In a world where more
    than 7000 languages
    are spoken, only a
    handful of languages
    are spoken by a large
    percentage of the
    population.
    One third of these
    languages have fewer
    than 1,000 people
    who continue to speak
    them.
    Segregation of languages according to EGIDS measurement tool

    View Slide

  19. Using Digital Tools to preserve Historical Artefacts,
    Paintings and other Works of Art
    According to the Internet
    Encyclopaedia of Philosophy,
    “Interpretation in art refers to
    the attribution of meaning to
    a work”.
    In order to interpret a work of
    art there are two prevalent
    concepts of isolationism and
    contextualism.
    Video: How Gen Studio was
    created for The Met using
    Microsoft AI
    Isolationism Contextualism

    View Slide

  20. DEMO
    Forecasting Future

    View Slide

  21. SOURCE CODE
    GITHUB REPOS - github.com/MLforKids
    USING ARIMA MODEL - bit.ly/AIforGoodArima
    USING PROPHET LIBRARY - bit.ly/AIforGoodProphet

    View Slide

  22. Moving Average (Rolling Mean)
    A moving average helps cut down the amount of "noise" on a price chart. Look at the direction of the moving average
    to get a basic idea of which way the price is moving. If it is angled up, the y-variable is moving up (or was recently)
    overall; angled down, and the y-variable is moving down overall; moving sideways, and the y-variable is likely in a
    range.
    BASIC TERMINOLOGY

    View Slide

  23. View Slide

  24. Stationarity
    In the most intuitive sense, stationarity means that the statistical properties of a process generating a time series do
    not change over time. It does not mean that the series does not change over time, just that the way it changes does
    not itself change over time. The algebraic equivalent is thus a linear function, perhaps, and not a constant one; the
    value of a linear function changes as grows, but the way it changes remains constant — it has a constant slope; one
    value that captures that rate of change.
    BASIC TERMINOLOGY

    View Slide

  25. ARIMA Model
    An Autoregressive Integrated Moving Average (ARIMA) model is a generalization of an autoregressive moving average
    (ARMA) model. Both of these models are fitted to time series data either to better understand the data or to predict
    future points in the series (forecasting).
    The AR part of ARIMA indicates that the evolving variable of interest is regressed on its own lagged (i.e., prior) values.
    The MA part indicates that the regression error is actually a linear combination of error terms whose values occurred
    contemporaneously and at various times in the past. The I (for "integrated") indicates that the data values have been
    replaced with the difference between their values and the previous values
    BASIC TERMINOLOGY

    View Slide

  26. View Slide

  27. FEEDBACK
    Visit
    https://www.rateevent.com
    /speeches/SCAAA038
    I would love to hear your
    thoughts or feedback on how I
    can improve your experience!

    View Slide