We are always looking for innovative and inspiring speakers. If you know somebody who would be an excellent fit for our meetup, we would highly appreciate if you help us and recommend this speaker to us. To recommend a speaker for CAIML, please fill out this form (https://forms.gle/Kgh4aDmDKRe3rWgA7).
What if we train a model to classify dogs and cats, but it is later tested with an image of a human? Generally the model will output either dog or cat, and has no ability to signal that the image has no class that it can recognize.
This is because classical neural networks do not contain ways to estimate their own uncertainty (so called epistemic uncertainty), and this has practical consequences for the use of these models, like safety when cooperating with humans, autonomous systems like robots, and computer vision systems. A possible solution is the bayesian neural network.
In this talk I will cover the basic concepts of bayesian neural networks, and how they can help us to produce safer robots, with respect to their visual perception and control. I will include examples from the literature and my own research.
We will share the full agenda soon and the link to the online event will be shared shortly before the meetup itself.