Viewing profile — Quetelet

Next year I’m finishing my PhD in a pretty niche (though crucial) subfield of an area that’s grown tremendously in the last few years (perception for autonomous vehicles) and my co…

Representation learning and probabilistic methods are huge sub-areas of modern machine learning, just take a look at the proceedings of ICLR2019.

These adversarial examples are generated in a very artificial way that will not be present in natural images (and if you’re thinking of security issues, the attacker needs access t…

You might be confusing the historical use of the sigmoid activation function with probabilistic modeling, neural networks in the 80s were used similarly to how they are today, albe…

Actually most modern neural networks are not probabilistic, they are deterministic function approximators. Also your point 3) isn’t quite correct either, often a “standard” archite…

I've seen a lot of interesting applications of CV in virtual reality (e.g. Oculus Rift) but is it necessary to have a graduate degree in CV to work in the field? What are some intr…