Interpretable Neural Networks for Computer Vision: Clinical Decisions that are Computer-Aided, not Automated

  • * Register (or log in) to the Neural Network to add this session to your agenda or watch the replay

  • Date
    9 December 2021
    Timeframe
    14:00 - 15:00
    Duration
    60 minutes
    Share this session

    Let us consider a difficult computer vision challenge. Would you want an algorithm to determine whether you should get a biopsy, based on an x-ray? That’s usually a decision made by a radiologist, based on years of training. We know that algorithms haven’t worked perfectly for a multitude of other computer vision applications, and biopsy decisions are harder than just about any other application of computer vision that we typically consider. The interesting question is whether it is possible that an algorithm could be a true partner to a physician, rather than making the decision on its own. To do this, at the very least, we would need an interpretable neural network that is as accurate as its black box counterparts. In this talk, I will discuss two approaches to interpretable neural networks: (1) case-based reasoning, where parts of images are compared to other parts of prototypical images for each class, and (2) neural disentanglement, using a technique called concept whitening. The case-based reasoning technique is strictly better than saliency maps, and the concept whitening technique provides a strict advantage over the posthoc use of concept vectors.

    Share this session
    In partnership with
    Discover more from programme stream
    AI liability in the EU and the US: stifling or...

    AI liability in the EU and the US: stifling or...

    3 April 2023 - 16:00 to 18:00

    Living with ChatGPT: Detecting AI text without destroying trust

    Living with ChatGPT: Detecting AI text without destroying trust

    16 February 2023 - 16:00 to 17:30

    AlphaTensor: discovering mathematical algorithms with reinforcement learning

    AlphaTensor: discovering mathematical algorithms with reinforcement learning

    12 January 2023 - 17:00 to 18:15

    A fundamental problem of AI on digital hardware: Will true...

    A fundamental problem of AI on digital hardware: Will true...

    12 December 2022 - 15:00 to 16:10

    How to make AI more fair and unbiased

    How to make AI more fair and unbiased

    28 November 2022 - 15:00 to 16:30