Questions tagged [autoencoders]
Feedforward neural networks trained to reconstruct their own input. Usually one of the hidden layers is a "bottleneck", leading to encoder->decoder interpretation.
647
questions
0
votes
1
answer
18
views
Exploring vae latent space
I recently trained a AE and a VAE and used the latent variables of each for a clustering task. It seemed to work well, sensible clusters. The main reason for training the VAE was too gain more ...
0
votes
0
answers
15
views
difference between l2 penalty and l2 loss in SAE
I was reading this paper from Anthropic https://transformer-circuits.pub/2024/scaling-monosemanticity/index.html and in the paper loss is defined like this :$$
L = \mathbb{E}_x \left[ \| x - \hat{x} \|...
2
votes
0
answers
100
views
Anomaly detection for Multivariate Time-Series data from multiple sensors
I work with tabular time-series data from multiple sensors and my goal is to detect abnormal behavior in battery discharge.
Here is an example of data (example contains records only for one device ...
1
vote
0
answers
22
views
Multi-task learning-Loss function
0
I am training a convolutional autoencoder with two velocity fields (2D array) as inputs and outputs. These fields represent wind velocities in both the x and y directions within a square domain. My ...
2
votes
1
answer
47
views
Why is the forward process referred to as the "ground truth" in diffusion models?
I've seen in many tutorials on diffusion models refer to the distribution of the latent variables induced by the forward process as "ground truth". I wonder why. What we can actually see is ...
2
votes
2
answers
73
views
Why does Variational Inference work?
ELBO is a lower bound, and only matches the true likelihood when the q-distribution/encoder we choose equals to the true posterior distribution. Are there any guarantees that maximizing ELBO indeed ...
2
votes
1
answer
40
views
VAEs: Why do we need the encoder for image generation?
I'm probably missing something obvious, but if we're only looking to generate images and are not interested in the latent space, why do we even need the encoder in VAEs?
In my understanding, the ...
0
votes
0
answers
15
views
ShapeNet VAE KL Divergence issues
I am trying to train a VAE on shapenet but I can't seem to make it work. Any help or ideas would be highly appreciated. Now the problem is whenever I apply the KL divergence loss the network seems to ...
3
votes
1
answer
132
views
Are there any situations where orthogonality is not optimal?
Data reduction is often used to avoid overfitting and to enhance explainability. Popular data reduction techniques, such as SVD or PCA map/project high-dimensional data to a lower-dimensional ...
0
votes
0
answers
10
views
Creating a light image generation model for a specific distribution
I am currently working on how a user can introduce bias in a neural network model.
To do so, I am creating an image2image model that only works on the training distribution.
For example, let's say I ...
0
votes
0
answers
9
views
Clarification about varitional autoencoders training
I have one specific question about VAEs as I try to work through the math on my own. I found from this paper that to training a VAE model involves optimizing a lower-bound of the marginal log-...
1
vote
0
answers
27
views
1 dimensional autoencoder as a clustering tool?
I am looking for references (as I prefer to sit over the giant's shoulders...) to something it "seems" to work well...
When we do clustering to analyse some data, to understand its structure ...
0
votes
0
answers
21
views
Multivariate Variational Autoencoder and Positive Definite Covariance Matrix
This might be a naive question from a non-statistician but here we go. I understand that the challenges that hamper the use multivariate variational encoder where a covariance matrix is used instead ...
1
vote
0
answers
25
views
why Conditional VAE require conditioning of the encoder
looking at this blogpost and in many other, the cVAE looks like this:
Now, my question is... why do we need the label on the encoder level? Clearly that information is already inside the image, thus ...
0
votes
0
answers
13
views
How can probability variables of different dimensions share the same parameter in VAE?
I am confused while studying VAE(Auto-Encoding Variational Bayes).
My problem is as follows:
We have a continuous variable $x$ and a random variable $z$.
The dimensions of $x$ and $z$ are different, ...