Please add LaTeX support

[Mahmoud_Abdelkhalek]

In this post:

NaN's in gradients due to multi-objective loss function

Context I’m currently trying to implement the following architecture: [Screenshot 2021-02-12 210143] Where x is an audio signal, h_\theta is a linear filter, f_\phi is a network that predicts one of two classes, either y_hat = 0 or y_hat = 1, and g_\psi is an autoencoder that attempts to reconstruct x as x_\hat. Here is how I pass a batch of x’s through the filter h_\theta: x = filt(x) Where filt is a nn.Module object with trainable parameters: filt = Filter(bias = True, kernel_size = 201,…

I tried to use LaTeX with no luck. This would have saved me a lot of time. Could you please add it to the site? It seems that there is a plugin already available:

Discourse Math

[Royi]

Any chance to enable this?
It will assist greatly when talking about technical math things.