Questions tagged [autoencoder]

Autoencoders are a type of neural network that learns a useful encoding for data in an unsupervised manner.

Filter by
Sorted by
Tagged with
0 votes
0 answers
23 views

Is it possible to use text Auto Encoders without text generation?

I have a use case where I have large texts, and a lot of it. Pretty often the sequence length exceeds 1000 tokens. I need a lower dimensional compression of the texts as an input for a classifier. The ...
  • 101
0 votes
0 answers
13 views

Generative Autoencoder with latent vector size as a parameter?

I am interested in using a generative autoencoder (something like a VAE maybe) to sample very high dimensional data more easily (making use of the fact that the autoencoder reduces the dimensionality ...
0 votes
0 answers
9 views

How to build Stacked Autoencoder using Keras?

Stacked Autoencoder I have tried to create a stacked autoencoder using Keras but I couldn't do the last part of this autoencoder. Here I have created three autoencoders. It works fine individually ...
  • 1
0 votes
0 answers
9 views

How is the encoder state passed to the decoder (LSTM, Keras)

My understanding is that in the Encoder Decoder LSTM, the decoder first state is same as the encoder final state (both hidden and cell states) . But I don't see that written explicitly in the code ...
0 votes
0 answers
9 views

Autoencoder on spectral image ASCII data file

I am discovering Autoencoder CNN, I took a look around on tutorials, I see lot's of examples with images as input. I was wondering if it is possible to use files whose pixels are represented by Ascii ...
0 votes
2 answers
17 views

Autoencoder vs Pre-trained network for feature extraction

I wanted to know if anyone has any sort of guidance on what is better for image classification on a lot of classes (about 400) with a small amount of samples per class (around 20), for relatively big ...
0 votes
0 answers
10 views

tensorflow is not learning

I am writing this code from the tensorflow tutorial about Autoencoders ...
0 votes
0 answers
19 views

Practical application of denoising autoencoders

I have been reading into autoencoders for the purpose of denoising data. In the examples i found (eg. [1, 2, 3], which are the first few google results) they have the following input/output: Input ...
0 votes
1 answer
17 views

Questions on GLM: General Language Model Pretraining with Autoregressive Blank Infilling

For GLM: General Language Model Pretraining with Autoregressive Blank Infilling , May I ask how is the sampling for input division in step (b) being done ? why in step (c), the green ...
  • 283
0 votes
1 answer
13 views

What says the output of autoencoder?

What is the meaning of output of autuencoders? Can we say it is the noise removed version of actual dataset and should it be symmetrical?
  • 11
1 vote
0 answers
14 views

How can I use autoencoders for noise detection and removal

How can I use autoencoders for noise detection and removal in a dataset with only 2 features and no labels? How should my architecture be like, such as 2 1 1 1 2 or any other? And does the output of ...
  • 11
0 votes
0 answers
12 views

How to remove noise with autoencoders?

I have a dataset with only 2 features and without labels ans size 1 million. I need to detect noise and remove them with an autoencoder system. I have input layer with 2 node 1 hidden layer with only ...
0 votes
1 answer
14 views

Trimming "unused" neurons from the bottleneck of an autoencoder

I'm working with autoencoding data in segments, and working with the latent space afterwards (I am also working on VAEs, but this segment of the project concerns deterministic AEs). I've noticed that ...
  • 101
1 vote
0 answers
16 views

How to implement simple VAE with sparse tensor in Tensorflow

thanks for reading. I have been attempting to train a simple VAE on very sparse 2D and 3D data. So far I have been training using dense tensors which - I think - is resulting in horrible training due ...
  • 11
1 vote
0 answers
19 views

Training a straight "copy the input to the output" autoencoder for audio is strangely slow

As a learning exercise, I'm training a "perfect" audio autoencoder. It has a hidden layer just as wide as the input layer, with linear activation. The expectation is that the network should ...
0 votes
0 answers
14 views

Analyzing strange shaped predicted vs actual value graph of a predicted variable

I am training an autoencoder to compress some graph data to a latent space of n variables, and then training a neural network to predict some other structural data about that graph from the latent ...
1 vote
0 answers
24 views

Deep learning model to predict the actual input values

I have some observed parameters to be used as input to the deep learning model. This problem comes from the wireless field where we transmit $x$. The channel $h$ is random in nature. The received ...
  • 11
0 votes
1 answer
41 views

Autoencoder general questions and poor loss

I'm trying to get a simple autoencoder working on the iris dataset to explore autoencoders at a basic level. I'm running into an issue where the loss of the model is extremely high (>20). Can ...
0 votes
0 answers
20 views

Mix of time-dependent and constant features for a transformer

I'm using the transformer architecture to predict future time-points from previous time-points. Each item of the input sequence is a vector of ...
0 votes
1 answer
32 views

KL divergence loss first decreases and then increases in VAE training

I am training a VAE on CelebA HQ (resized to 256x256). The training is going well, the reconstruction loss is decreasing and reconstructions are also meaningful. But, the problem is with KL divergence ...
0 votes
0 answers
23 views

Using large CNNs (e.g., ResNet) in convolutional autoencoders for image representation learning

I am confused about which CNNs are generally used inside autoencoder architectures for learning image representations. Is it more common to use a large existing network like ResNet or VGG, or do most ...
0 votes
1 answer
43 views

An autoencoder setup for anomaly detection

I am doing anomaly detection using machine learning. i have tried different models like isolation forest, SVM and KNN. The maximum accuracy that I can get from each of them is $80\%$ accordind to my ...
  • 11
0 votes
0 answers
45 views

Tensorflow.js - CNN/or autoencoder denoiser architecture?

I am new to machine learning. I have 10,000 examples of 128x256 array of values 0.0-1.0. Each example consists of a pair of a clean example and the other with noise added. I am aiming to train a CNN / ...
0 votes
0 answers
30 views

What model and attributes would be good for this data?

I have the following set of data like in the picture, with 366 Temperature values for one year. The first set of data would be for training and the second one for test. I would like to detect the ...
0 votes
0 answers
31 views

How to detect anomalies?

I have timeseries data with one value per day for a year. (there is one column with temperature data). I am using autoencoders to train a reconstruction model with mse loss. Firstly, I normalized the ...
0 votes
0 answers
9 views

Auto encoder network

Is there any rule that we should use only deconvolution operations in decoder block of auto encoder network or we can use convolution in such way that it up-samples or mirrors the corresponding ...
  • 1
0 votes
0 answers
16 views

How to improve L2 loss for generative autoencoder

I am working with a modified generative autoencoder and having issues getting the L2 sufficiently low. I think problem is that because my data is over a very large range and is standardized to values ...
0 votes
1 answer
77 views

Training data for anomaly detection using LSTM Autoencoder

I am building an time-series anomaly detection engine using LSTM autoencoder. I read this article where the author suggests to train the model on clean data only in response to a comment. However, in ...
0 votes
0 answers
35 views

LSTM Autoencoders vs LSTM

I'm working on a time-series anomaly detection project. I have read that both LSTM Autoencoders and LSTM can do the job. Can someone please help me understand what are the advantages of each i.e. when ...
0 votes
0 answers
9 views

LSTM Auto-encoder Implementation

I'm trying to implement an LSTM auto-encoder in PyTorch for time-series data (univariate and/or multi-variate). Initially, I assumed it would be fairly easy but I realised there are a few ...
0 votes
0 answers
17 views

Can I use Variational Autoencoder/GAN for image manipulation?

I have a CT image with the tumor and the corresponding Radiotherapy image. I want to predict the CT-Image with the corresponding change. For my training, I do have input CT image, Radiation therapy ...
0 votes
0 answers
26 views

Automatic feature extraction from EMG, autoencoder vs variational autoencoder?

Thanks for checking my question! From the EMG signals of Parkinon's patients, I want to extract rigidity and bradykinesia information. In order to do that, we need feature engineering. But, I would ...
  • 1
0 votes
0 answers
493 views

LSTM Autoencoder set-up for multiple features using Pytorch

I am building an LSTM autoencoder to denoise signals and will take more than 1 feature as it's input. I have setup the model Encoder part as follows which works for single feature inputs (i.e. ...
  • 13
0 votes
1 answer
93 views

Incremental learning on Autoencoder for anomaly detection

I want to incrementally train my pre-trained autoencoder model on data being received every minute. Based on this thread, successive calls to model.fit will incrementally train the model. However, the ...
  • 11
1 vote
0 answers
32 views

Does Sliced Wasserstein Distance work in higher than 2 dimensions?

I had thought that it only worked for 2D distributions. I am trying to implement a sliced Wasserstein autoencoder and I was wondering if my latent space can be larger than 2D.
1 vote
1 answer
54 views

Latent space vs Embedding space | Are they same?

I am going through variational autoencoders and it is mentioned that: continuity (two close points in the latent space should not give two completely different contents once decoded) and completeness ...
  • 135
0 votes
0 answers
26 views

Re-train the decoder of an autoencoder?

Can the decoder of the pre-trained autoencoder be trained again by taking the feature vector of the Siamese Neural Network (SNN) as input? I have trained the SNN model. Additionally, I trained ...
  • 1
0 votes
0 answers
76 views

Keras autoencoder gives same output

I have a convolutional auto-encoder which is created like this: ...
0 votes
0 answers
17 views

Variational Autoencoder assumtions

I am currently reading the paper "Importance Weighted Autoencoders" and am having a hard time understanding something regarding the original Variational Autoencoder (VAE) as described here ...
0 votes
0 answers
14 views

Importance Weighted Autoencoder update rule

I am currently reading the paper "Importance Weighted Autoencoders" and am having a hard time grasping something. Firstly, the paper discusses a proposed upgraded lower bound to the original ...
0 votes
1 answer
57 views

Build autoencoder for single matrix with integer numbers

Can you please tell me how to build an autoencoder with a single matrix(4,4) with integer numbers? I want to build an autoencoder for the below-mentioned data. I don't know whether I should convert ...
0 votes
0 answers
45 views

Loss value in Autoencoder neural network

We have an autoencoder neural network and we get a loss value (loss = binary cross entropy) convergent to a certain number. What can we deduce from this value ? Is this value strictly related to the ...
0 votes
1 answer
36 views

Generate new distribution from auto-encoder /variational autoencoder

I know that autoencoders can be used to generate new data. From what I could understand.. The autoencoder uses the original distribution X to learn a random gaussian distribution described by mean and ...
2 votes
1 answer
2k views

Variational Autoencoders VS Transformers

I'm relatively new to the field, but I'd like to know how do variational autoencoders fare compared to transformers?
0 votes
0 answers
80 views

CNN auto-encoder performs much worse than Fully connected auto-encoder

I am trying to develop a one-class classifier, that will learn regular examples, and, hopefully, will have hard times reconstructing anomaly observations. I have 1D signals which I tried to ...
0 votes
0 answers
167 views

Reference code for LSTM Variational Autoencoder for dimensionality reduction

I have time series data, with many features. I would like to reduce the dimentionality by using LSTM VAE. Does anybody know an example code or a reference to guide me to impolement it? Both Pytorch ...
0 votes
0 answers
136 views

Variational autoencoder for time series denoising and dimentionality reduction

I have a dataset X of multiple series say 100 (size=100). I would like to use VAE to both denoise the data and reduce the dimensions to a smaller latent space Z (size Z << size X), because I ...
0 votes
0 answers
56 views

Expectation of ELBO in Variational Autoencoder

I am working with VAEs. My input is x, which is a product of two variables $x_1$ and $x_2$. The objective (ELBO) of VAE in terms of x is: $E_{z\sim Q}[\log P(x|z)] - \mathcal{D}[Q(z|x)||P(z)]$. I want ...
1 vote
1 answer
25 views

Can we use autoencoders to change an existing image instead of create one from scratch?

I'm trying to think if we can use autoencoders to edit an existing image instead of saying, creating a new one from scratch. To give an example, say I train my data on the MNIST dataset. If I now give ...
1 vote
0 answers
45 views

How should I think when I want to compare mu and sigma for different images in VAE?

I'm searching for a way to compare mu and sigma values of the encoder network's output of variational autoencoders. In detail, imagine I trained my VAE on the MNIST digits dataset using the official ...

1
2 3 4 5
7