Uncertainty (Aleatoric vs Epistemic) | Machine Learning

Machine/Deep learning models have been revolutionary in the last decade across a range of fields. However, sometimes we need to consider the uncertainty of models so we can gauge how confident the model is in its predictions. The total uncertainty in a prediction occurs from a combination of data (aleatoric) and model (epistemic) uncertainty. Check out the video to understand what these types of uncertainty mean and how the total uncertainty can be decomposed into these two terms.

[nickrhee]

Only the seed was changed to get the uncertainty area in 2d plain but there are many other sources of uncertainties that we should have included to get more comprehensive picture of the uncertainty.

[nThHouse]

You explain perfectly! been looking for videos about uncertainty and you explained it the best!

[方郁文-sw]

Great Video! I was wondering, what happen if there exist an "Out of Domain Class" (a class not in the training dataset), but the model, or even the ensemble model, still gives a high confidence for the prediction.

[cdngclips]

you don't know how helpful your channel is, thank you!!!

[AbhishekSinghSambyal]

Any good resource to read in detail what you explained?

[TheSwordfish-gr]

What about in regression and not classification?

[PranavAshok]

Thanks for the great introduction to this topic! In your explanation about the model uncertainty, you were varying the seeds (and hence indirectly the weights) in order to get all the different models for the same network architecture. Did you choose to do that for the sake of simplicity? Do we also have to think about the various possible model architectures (or alternate models) as well when trying to estimate the model uncertainty more accurately?

[amortalbeing]

Hi, Thanks a lot really appreciate it.
what book or books should I read /or video/courses to watch to know what you know here?

[echolee]

Thanks for explanation! Is the model uncertainty here the variance of Gaussian distribution? Can we define a different total uncertainty?

[MrVaunorage]

Okay but how do you calculate the epistemic uncertainty? How do you get the gaussian distribution over the model predictions ? Do you absolutely need to sample or you can get it using the alpha parameters? Thank you

[InquilineKea]

How much does VC dimension contribute to uncertainty in each? [and does high-VC dimension adapt itself well better to aleatoric uncertainty). it sounds like a functional analysis thing

[sak]

How can calculate the uncertainty both data and model in an already developed model?

[rodi]

How do you compute the total uncertainty ?

[ShireenKudukkilManchingal]

Isn't this the same as deep ensembles?

[annap]

Great video!! Does the same framework apply to random forests?

[kassemhussein]

Could you provide a simple mathematical example on how to run the calculations? I've looked for a simple practical example on how to do the calculations but only found complex papers

[EigenA]

Great work! Thank you for the presentation.

[ryanyoung]

Excellent video. Great speaking tempo. Easy to follow.

[anujshah]

Thanks for the lucid explanation. I have one doubt regarding aleatoric uncertainty. From the paper of kendel and Gal, the aleatoric uncertainty is obtained by modifying the loss function, so is that aleatoric same as total - epsitemic

[paulorjr]

Great video! One question: the mean of predictions is equal to the predictive entropy (and thus the total uncertainty)?