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

Towards global and human-centered explanations ...

Towards global and human-centered explanations for machine learning models

In this talk, Carla presents the existing literature and contributions already done in the field of XAI, including a prospect toward what is yet to be reached. She also provides newcomers to the field of XAI with an overview that can serve as reference material in order to stimulate future research advances, but also to encourage professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.

Carla Vieira

October 31, 2022
Tweet

More Decks by Carla Vieira

Other Decks in Technology

Transcript

  1. DATA ENGINEER AND AI ETHICS RESEARCHER LEADDEV SAN FRANCISCO 2022

    Towards global and human- centered explanations for machine learning models TALK CARLA VIEIRA
  2. Get to Know Me I'm Carla, Data Engineer and Google

    Developer Expert in Machine Learning. Master student in Artificial Intelligence. First time in the U.S.A First time speaking in an international conference First LeadDev Event Fun facts: @carlaprvieira / carlavieira.dev
  3. Potential Harms Caused by AI Systems BIAS AND DISCRIMINATION DENIAL

    OF INDIVIDUAL AUTONOMYAND RIGHTS 01 02 NON-TRANSPARENT, UNEXPLAINABLE, OR UNJUSTIFIABLE OUTCOMES 03 INVASIONS OF PRIVACY 04 UNRELIABLE, UNSAFE, OR POOR- QUALITY OUTCOMES 05 Leslie, D. (2019). Understanding artificial intelligence ethics and safety: A guide for the responsible design and implementation of AI systems in the public sector. The Alan Turing Institute.
  4. What is bias in ML/AI? Algorithmic bias is when a

    computer system reflects the implicit values of the humans who created it. Source: Better Images of AI project
  5. Joy Buolamwini "Despite our aspirations for tech to be better

    than us, to be more objective than we are, the machines we create are a reflection of both our aspirations and our limitations."
  6. How bias become part of AI systems? Let's explore how

    this happens in the ML Lifecycle. Source: Better Images of AI project
  7. Data generation bias "Datasets are like textbooks for your student

    to learn from. Textbooks have human authors, and so do datasets." (Cassie Kozyrkov)
  8. Historical bias "Historical bias arises even if data is perfectly

    measured and sampled, if the world as it is or was leads to a model that produces harmful outcomes." (Suresh et. al. 2019)
  9. Evaluation bias "The dominant values in ML are Performance, Generalization,

    (...) Efficiency, and Novelty. These are often portrayed as innate and purely technical." (Birhane et al., 2021)
  10. Evaluation bias Recent research has proposed new metrics to evaluate

    the performance of the model considering notions of bias, fairness and discrimination. measure the accuracy in the groups separately: a facial recognition model can have an accuracy of 80% on average, but 60% for black women and 90% for white men. another way is to assess disproportionate impacts, that is, to assess the balance between false positives for each group; Examples:
  11. Deployment Bias "Deployment bias arises when there is a mismatch

    between the problem a model is intended to solve and the way in which it is actually used." Source: Better Images of AI project
  12. Algorithms, the illusion of neutrality Fred Benenson This is called

    Mathwashing. When power and bias hide behind the facade of "neutral" math.
  13. HOW DOES THE MODEL WORKS? WHAT IS DRIVING DECISIONS? CAN

    I TRUST THE MODEL? INPUT OUTPUT ML MODEL BIAS BIAS BIAS
  14. What can we do to solve this? Machine intelligence makes

    human morals more important. "We cannot outsource our responsibilities to machines." (Zeynep Tufekci)
  15. Fairness “An algorithm is fair if it makes predictions that

    do not favour or discriminate against certain individuals or groups based on sensitive characteristics.”
  16. Explainable and Interpretable AI Explainability is not a new issue

    for AI systems. But it has grown along with the success and adoption of deep learning.
  17. Lack of global explanation methods How to avoid ground truth

    unjustification? How can we better evaluate explanations? Can we do better explanations for non-expert users? How does fairness interact with interpretability? How can we build more robust interpretability methods? How to combine and deploy interpretable Machine Learning models? Challenges XAI
  18. Who is your invention for? Who benefits from it? 🤔

    This is a great time to consult with a UX (user experience) specialist and map out your application’s users.
  19. Is it ethical to proceed? 🤔 Just because you can

    do something, doesn't mean you should.
  20. Summary TECHNOLOGY IS NOT FREE OF HUMANS EVERY SINGLE HUMAN

    IS BIASED. MATH CAN OBSCURE THE HUMAN ELEMENT AND GIVE AN ILLUSION OF OBJECTIVITY. 01 02 03