Questions tagged [autoencoders]
For questions about autoencoders, a type of unsupervised artificial network for learning efficient data codings.
117
questions
0
votes
0
answers
9
views
Extracting behavior (switch On/Off) of an electric load from unlabeled time series data
Following are the details of my dataset:
sampling frequency: 1 Hz
No. of useful features: 10
The time series dataset is from household wherein I'm required to find ...
- 71
0
votes
1
answer
45
views
Reconstructing 3D models from 2D images using autoencoders
I went through a research paper ("Voxel-Based 3D Object Reconstruction from Single 2D Image Using Variational Autoencoders") and tried to implement the approach following this diagram:
0
votes
1
answer
27
views
What is the distribution of autoencoder embeddings?
Is there any result on the distribution of autoencoder embeddings?
For example, the following image (taken from this article) visualizes the latent space with t-SNE. As you can see, images from the ...
- 161
0
votes
1
answer
31
views
Autoencoders: Where does the encoder end and the decoder begin?
Consider a simple Autoencoder neural net:
...
- 101
6
votes
2
answers
203
views
Is plain autoencoder a generative model?
I am wondering how a plain auto encoder is a generative model though its version might be but how can a plain auto encoder can be generative. I know that Vaes which is a version of the autoencoder is ...
- 81
1
vote
0
answers
40
views
Is there a name for this model?
I have an image autoencoder model trained as follows:
Step 1) train a GAN to obtain a generator capable of drawing from the data manifold by sampling a normal distribution in latent space
Step 2) ...
- 11
-1
votes
1
answer
78
views
Denoise autoencoder not training properly [closed]
I'm trying to make a denoise autoencoder wherein the encoder part is vgg16 and decoder is opposite of vgg16(encoder) network. My dataset consists of 5K images in grayscale.
Now while training, the ...
0
votes
0
answers
30
views
Why does the feature space of an autoencoder typically contain more info than a teacher-student model?
This is a question our Prof gave us as exam preparation, but I don't know why the Autoencoder should contain more info than the Teacher Student model.
Teacher Student Models are a class of models in ...
- 348
0
votes
0
answers
19
views
Do channels on the encoder's output layer really matter in convolutional autoencoders?
I viewed the example in Keras for a convolutional autoencoder. I noticed that the number of units in each layer of both the encoder and decoder never falls below that of the input. In other words, ...
- 53
0
votes
2
answers
123
views
Strange artifacts in autoencoder outputs
I'm training an autoencoder, that does not downsample images but processes them in the same size. For example, a 256x256 input will always be processed at 256x256 resolution, only the channels ...
- 115
0
votes
0
answers
59
views
VAEs vs Autoencoders with BatchNorm and Dropout?
It struck me that regular auto-encoders with batch-norm and dropout have quite similar properties to VAEs which made me wonder whether VAEs where really much better than this simpler alternative. Let ...
- 296
0
votes
1
answer
15
views
Do Quo et al (2013) perform backpropagation between layers?
Le et al. 2013's non-weight sharing CNN has inspired me to ask two questions on this site previously.
When training the three-layer autoencoder, do they compute dL/dW (where L is equation 1) ...
- 151
0
votes
1
answer
205
views
What is the state of the art concerning autoencoder that connect 2 images that are not similar but are physicaly related?
I am currently working on an autoencoder that connect two images. The first one can be seen as the electron flow and the second one is the electrostatic potential seen by the electrons. Long story ...
1
vote
1
answer
35
views
Why is training all layers at a time effective for a multi-layer autoencoder?
This training of all layers of a CNN simultaneously is standard practice today. It is found in every CNN (AlexNet (2012), VGG, Inception, GANs, etc) and even pre-CNN networks such as Le et al. 2012.
...
- 151
4
votes
2
answers
160
views
Can I apply reparametrization trick on "any" deep neural network?
I came across the "reparametrization trick" for the first time in the following paragraph from the chapter named Vector Calculus from the test book titled Mathematics for Machine Learning ...
- 3,191
0
votes
0
answers
30
views
Masked Autoencoder Structure
In the following structure when we use MADE due to the constraints for making a masked autoencoder, it seems some inputs do not have any connection to the next layer, and also there is the output that ...
- 1
0
votes
0
answers
29
views
Adversarial Autoencoder is not working and not learning properly
I am trying to get an Adversarial AutoEncoder going using keras Fit method on a keras.model class but for some reason it is not working.
Keep in mind that I tried updating encoder and decoder at the ...
- 1
3
votes
1
answer
140
views
How to determine the quality of synthetic data?
I'm working on a VAE model to produce synthetic data of X-Ray diffraction spectrums.
I try to figure out how I can measure the quality of the spectrums. The goal would be to produce synthetic data ...
- 33
1
vote
1
answer
51
views
Why is the prior on the latent variable standard gaussian in VAE?
While training a standard VAE, we assume that the prior on the latent variable Z is the standard gaussian and we use KL divergence to push the posterior as close as possible to the standard gaussian. ...
1
vote
2
answers
299
views
Are mean and standard deviation in variational autoencoders unique?
In general, if I have a collection of data then mean(Expectation) and standard deviation are calculated as follows
$$\text{mean } = \mu = \mathbb{E}[X] = \sum\limits_{i = 1}^n p_ix_i $$
$$\text{...
- 3,191
0
votes
0
answers
31
views
Train separate AutoEncoder's on each class or one AE for all classes to learn features?
I'm working on a project where the dataset contains time series of three classes, depending on the shape of the series. I want to learn the representations of these series as vectors, so naturally I ...
- 1
1
vote
0
answers
35
views
What is the conceptual difference between convolutional neural networks and auto-encoders?
I'm familiar with Auto-Encoders and I'm about to dive into CNNs. By having a look at the most important component of a CNN, the filter:
I wonder how it is different from Auto-Encoders:
For me, it ...
- 205
0
votes
0
answers
34
views
Weird KL divergence behaviour
I'm training a complex model for motion prediction using a VAE, however the KL divergence has a very strange behavior.
A scheleton of the network is the following:
At the end my network compute the ...
- 159
0
votes
0
answers
130
views
Why would an auto-encoder produce latent vectors with many zeros?
My autoencoder give latent vectors with many zeroes components like:
...
- 103
1
vote
0
answers
35
views
How do I select the number of neurons for each layer in an auto-encoder for dimensionality reduction?
I am trying to apply an auto-encoder for dimensionality reduction. I wonder how it will be applied on a large dataset.
I have tried this code below. I have total of 8 features in my data and I want to ...
- 111
0
votes
1
answer
32
views
How to train a model for 1 image class to detect anomaly?
I want to train a model with python over the images, and these images are for a metal product.
my aim is to detect the defects, to notice if a product is a failure.
what kind of architecture do you ...
- 1
0
votes
2
answers
1k
views
In variational autoencoders, why do people use MSE for the loss?
In VAEs, we try to maximize the ELBO = $\mathbb{E}_q [\log\ p(x|z)] + D_{KL}(q(z \mid x), p(z))$, but I see that many implement the first term as the MSE of the image and its reconstruction. Here's a ...
- 129
0
votes
0
answers
130
views
What is the difference between the forward pass of the Multi-Layer Perceptron, Deep AutoEncoder and Deep Belief Network?
Multi-Layer Perceptron (MLP), Deep AutoEncoder (DAE), and Deep Belief Network (DBN) are trained differently.
However, do they follow the same process during the inference phase, i.e., do they ...
- 73
0
votes
1
answer
79
views
Convert LSTM univariate Autoencoder to multivariate Autoencoder
I have the following code snippet which takes in a single column of value i.e. 1 feature. How do I modify the LSTM model such that it accepts 3 features?
...
- 21
0
votes
1
answer
83
views
Why Autoencoder Weights Are Not Always Tied
To me, tying weights in an autoencoder makes sense if we think of the auto encoder as doing PCA. Why in any situation would it make sense to not tie the weights? If we don't tie the weights, would it ...
- 116
1
vote
0
answers
20
views
Dealing with bias in multi-channel auto encoders
The problem
I have a multi-channel 1D signal I want to auto-encode.
I am unable to resonstruct the input when the number of channels increases.
Code
I am using a convolutional encoder, and a ...
- 669
1
vote
0
answers
53
views
Underfitting a single batch: Can't cause autoencoder to overfit multi-sample batches of 1d data. How to debug?
TL;DR
I am unable to overfit batches with multiple samples using autoencoder.
Fully connected decoder seems to handle more samples per batch than conv decoder, but then also fails when number of ...
- 669
2
votes
1
answer
91
views
How does replacing states with latent representations help RL agents?
I have seen many papers using autoencoders to replace images (states) with latent representations. Some of those methods have shown higher rewards using such techniques. However, I do not understand ...
- 339
1
vote
0
answers
57
views
variational auto encoder loss goes down but does not reconstruct input. out of debugging ideas
My variational autoencoder seems to work for MNIST, but fails on slightly "harder" data.
By "fails" I mean there are at least two apparent problems:
Very poor reconstruction, for ...
- 669
2
votes
1
answer
209
views
VAE giving near zero output when latent space dimension is large
I'm training a VAE to reconstruct some input (channels picked up by some MIMO BS for context) and I ran an experiment on the training set to see how the performance improves with the latent space ...
- 21
2
votes
0
answers
32
views
Literature on the advantages of using an auto-encoder for classification
Given a supervised problem with X, y input pairs, one can do two things for obtaining the function f that maps X with y with Neural Networks (and in general in machine learning):
Deploy directly a ...
0
votes
1
answer
132
views
Autoencoder: predictions missing for nodes in the bottleneck layer
I'm using tf.Keras to build a deep-fully connected autoencoder. My input dataset is a dataframe with shape (19947,), and the purpose of the autoencoder is to predict normalized gene expression values. ...
- 11
2
votes
0
answers
31
views
Compressing Parameters of an Response System
I have an input-output system, which is fully determined by 256 parameters, of which I know a significant amount are of less importance to the input-output pattern.
The data I have is some (64k in ...
- 121
0
votes
2
answers
82
views
Which models can I use for supervised learning with images?
I have to do a project that detects fabric surface errors and I will use machine learning methods to deal with it. I have a dataset that includes around six thousand fabric surface images with the ...
1
vote
0
answers
35
views
How can I improve the performance on unseen data for semantic segmentation using an auto-encoder?
I am using simple autoencoders for the task of semantic segmentation on the VOC2012 dataset. I am currently using a simple autoencoder based model. It is trained on adam optimizer with cross-entropy ...
- 121
1
vote
1
answer
55
views
Why do we add additional axis in CNN autoencoder while denoising?
I am currently learning about autoencoders and I follow https://www.tensorflow.org/tutorials/generative/autoencoder
When denoising images, authors of tutorial add an additional axis to the data and I ...
- 141
1
vote
0
answers
51
views
how to handle highly imbalanced multilabel classification?
I am working on a multilabel classification in which I am having 206 labels. When I saw the percentage of the number of 1's in each label they are way less than 0.1% for each label. The maximum ...
- 47
1
vote
2
answers
446
views
Is it possible to have a variable-length latent vector in an autoencoder?
I'm trying to have a simple autoencoder but with variable latent length (the network can produce variable latent lengths with respect to the complexity of the input), but I've not seen any related ...
- 430
1
vote
1
answer
99
views
Why does the training time of SVMs dramatically decrease after applying dimensionality reduction to the features?
Training an SVM with an RBF kernel model with c = 5.5 and gamma = 1.06, for a 5-class classification problem on the NSL-KDD ...
- 13
1
vote
0
answers
73
views
Role of autoencoder in Hierarchical Extreme Learning Machine
I want to build HELM neural network that consists of autoencoder (AE) and one class classification (OC).
HELM with AE and OC have following shape:
That is, hidden layer output of AE is input of OC.
...
- 11
2
votes
1
answer
123
views
Are Autoencoders for noise-reduction only suited to deal with salt-and-pepper kind of noise?
I'm currently looking at NN to deal with noisy data. I like the Autoencoder approach https://medium.com/@aliaksei.mikhailiuk/unsupervised-learning-for-data-interpolation-e259cf5dc957 because it seems ...
3
votes
0
answers
29
views
How to quantify the amount of information lost by the decoder NN in an AE?
Is there a way to quantify the amount of information lost in the lossy part of an autoencoder where the original input is compressed to a representation with less degrees of freedom?
I was thinking ...
- 261
0
votes
0
answers
186
views
What is the time complexity for training a single-hidden layer auto-encoder?
What is the time complexity for training a single-hidden layer auto-encoder, for 1 epoch?
You can assume that there are $n$ training examples, $m$ features, and $k$ neurons in the hidden layer, and ...
3
votes
0
answers
47
views
Enforcing sparsity constraints that make use of spatial contiguity
I have a deep learning network that outputs grayscale image reconstructions. In addition to good reconstruction performance (measured through mean squared error or some other measure like psnr), I ...
- 143
7
votes
1
answer
175
views
Are there transformer-based architectures that can produce fixed-length vector encodings given arbitrary-length text documents?
BERT encodes a piece of text such that each token (usually words) in the input text map to a vector in the encoding of the text. However, this makes the length of the encoding vary as a function of ...
- 241