Hi all, I am trying to replicate a Likelihood Approximation Network (LAN) with Flux.jl. LANs are used to learn the likelihood function of intractable computational models. As a proof of concept, I am trying to apply the method to two simple models for which the likelihood function is known: a Gaus…

I tracked down the problem to a few large outliers in the training data, which caused a NaN when passed to tanh. So far, removing the outliers seems to have solved the problem.

Indeed, it would be helpful to know where the NaN originated. As far as I can tell, I replicated the procedure described in the paper. This makes me wonder whether there is a problem with the AD.

I was wondering whether someone might be able to tell me if I misspecified the NN model or if NaNs are likely due to a bug?

NaN errors in Flux

General Usage

goerch April 26, 2022, 9:53pm 2

Just to reiterate an old point of discussion: signaling NaNs would help you to discover the root of the problem…

Topic		Replies	Views
Why does my Flux model return in all NaN? Machine Learning question , flux	2	823	October 9, 2023
How come Flux.jl's network parameters go to NaN? Machine Learning first-steps , flux	10	4191	June 9, 2021
Flux training gives NaNs Machine Learning	3	1182	July 3, 2023
Flux error: Loss is NaN New to Julia flux	5	1038	August 4, 2019
Getting NaNs in the hello world example of Flux Machine Learning question	2	772	October 28, 2021

NaN errors in Flux

Related topics