File tree Expand file tree Collapse file tree 1 file changed +6
-4
lines changed Expand file tree Collapse file tree 1 file changed +6
-4
lines changed Original file line number Diff line number Diff line change 487
487
"id" : " KV1khmq5wt-K"
488
488
},
489
489
"source" : [
490
- " The equations for both of these losses are provided below :\r\n " ,
490
+ " The equation for the latent loss is provided by :\r\n " ,
491
491
" \r\n " ,
492
492
" $$L_{KL}(\\ mu, \\ sigma) = \\ frac{1}{2}\\ sum_{j=0}^{k-1} (\\ sigma_j + \\ mu_j^2 - 1 - \\ log{\\ sigma_j})$$\r\n " ,
493
493
" \r\n " ,
494
- " $$L_{x}{(x, \\ hat{x})} = ||x- \\ hat{x}||_1$$ \r\n " ,
494
+ " The equation for the reconstruction loss is provided by: \r\n " ,
495
495
" \r\n " ,
496
- " <!-- $$L_{KL}( \\ mu, \\ sigma) = \\ frac{1}{2} \\ sum \\ limits_{j=0}^{k-1} \\ small{( \\ sigma_j + \\ mu_j^2 - 1 - \\ log{ \\ sigma_j})}$$ --> \r\n " ,
496
+ " $$L_{x}{(x, \\ hat{x})} = ||x- \\ hat{x}||_1$$ \r\n " ,
497
497
" \r\n " ,
498
498
" Thus for the VAE loss we have:\r\n " ,
499
499
" \r\n " ,
500
- " $$L_{VAE} = c\\ cdot L_{KL} + L_{x}{(x,\\ hat{x})}$$"
500
+ " $$L_{VAE} = c\\ cdot L_{KL} + L_{x}{(x,\\ hat{x})}$$\r\n " ,
501
+ " \r\n " ,
502
+ " where $c$ is a weighting coefficient used for regularization. Now we're ready to define our VAE loss function:"
501
503
]
502
504
},
503
505
{
You can’t perform that action at this time.
0 commit comments