Stack Exchange Network

Stack Exchange network consists of 175 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [autoencoder]

Autoencoders are a type of neural network that learns a useful encoding for data.

1
vote
0answers
12 views

Tensor Shape 'Reshape' during the dataflow

I would like to combine an Autoencoder with a LSTM. However, the 'timestep' is a block for the implements and I would like to train them together. Is there a solution to the tensor 'reshape'? I mean, ...
1
vote
0answers
14 views

Various Distances between probability distributions

I was reading about different distribution distance - and came across Kullback-Leibler divergence, Jensen-Shannon divergence, MMD, and Wasserstein distance - the book was too abstract for me to absorb....
1
vote
1answer
35 views

Variational auto-encoders (VAE): why the random sample?

Why do people train variational auto-encoders (VAE) to encode means and variances (regularised towards 0 and 1), and then sample a random Gaussian, rather that simply encode latent vectors and ...
0
votes
1answer
24 views

normalization in auto-encoder [closed]

I am using auto-encoder for anomaly detection problem. dataset consist of machine's sensor data. each feature has different scale range. for example, one of sensor's range is 0-5 and another's range ...
0
votes
1answer
14 views

Help required to implement the below model using Bi-GRU

As you can see in above images I need to model Bi-GRUs stacked as shown in table which takes input (N,1,64) and outputs (N,204). The input data is binary number stream and so is output data. Can ...
0
votes
0answers
11 views

The Probability distribution of an Adversarial Autoencoder

As I want to gain more knowledge about Adversarial Autoencoders, I'm reading this series on "towardsDataScience" about the subject. Now I do have a decent understanding of statistics (at least about ...
0
votes
0answers
26 views

Autoencoder in R

I am new in neural network and trying to replicate autoencoder in R from https://statslab.eighty20.co.za/posts/autoencoders_keras_r/ I received an error when executing this line: ...
0
votes
1answer
47 views

what is correct way to perform normalization on data in Auto encoder?

working on anomaly detection problem. i'm using auto-encoder to denoise given input. I trained network with normal data(anomaly free). so model predict normal state of given input. Normalization of ...
3
votes
2answers
67 views

Transform an Autoencoder to a Variational Autoencoder?

I want to compare between the training by an Autoencoder and a variational autoencoder. I have already run the traing using AE. I want to know if it's possible to transform this AE into a VAE and ...
0
votes
0answers
13 views

Encoder Decoder Network Image Compression

Could you train an encoder decoder network to take an image in and attempt to recreate that image as an output. I am basically interested at looking at the intermediate feature vector representation ...
0
votes
0answers
33 views

Autoencoder for Dimensionality Reduction

My task is to reduce the features of my temporal sequence. Each input is of the shape (timesteps, features) = (240,117). I am using an autoencoder consisting of intermediate lstm layers and I am ...
0
votes
0answers
36 views

How to set the Reconstruction error threshold for anomaly detection using autoencoders?

Hi I am doing anomaly detection using auto encoders.I have trained the model using 'Non Anomalous' values.Now when I give anomalous points as test data. What should be the Reconstruction error ...
1
vote
1answer
15 views

Autoencoder Dimensionality Error

Thanks for taking a look! I have an auto-encoder that I am trying to use for anomaly detection. I have 2 log files, logfile.log and testfile.log. They're essentially the same logfile, I just split ...
1
vote
0answers
19 views

Train autoencoder on 1D data with high and low amplitudes

I'm using an autoencoder-RNN combination to predict colliding waves in 1D. The training data is obtained by using the 1D Euler equations along with boundary conditions to preduce to waves (left and ...
0
votes
0answers
9 views

Deep Learning Book Manifold Learning Example need to be explained

I was learning neural network using the book "Deep Learning" by Ian Goodfellow, Yoshua Bengio and Aaron Courville.I section 14.6 the author makes an example of figure 14.6 and it says: Blockquote ...
1
vote
1answer
19 views

Autoencoder doesn't learn to reduce dimesions

I coded a neural network from scratch in Python. I tried it with the XOR problem and it learned correctly. So I tried to encode an Autoencoder with 3 inputs (and therefore with also 3 outputs) to ...
1
vote
0answers
10 views

Any heuristic for minimal DCGAN latent space dimension?

I am highly interested in approaching minimal latent space dimension (as many other may be) for DCGANs or autoencoders. In this example of DCGAN on the MNIST dataset, the person uses a 100-...
0
votes
0answers
41 views

CNN for Keras Autoencoder

I'm working on my first Autoencoder with Keras. To do so, I followed these two tutorials: Version 1) https://blog.keras.io/building-autoencoders-in-keras.html Version 2) https://ramhiser.com/post/...
0
votes
0answers
9 views

How do you feed a VAE input layer a complex dataset form - an array with multiple sub-arrays?

I am currently trying to to pipe data into a simple VAE using Tensorflow but have encountered an issue. All the literature on VAEs are for images where tensors are typically squashed into 1D. The ...
0
votes
0answers
12 views

Problems successfuly implementing stacked autoencoder in binary classification problem

Hi im currently working on a binary classification problem, currently i haven't had much success with it however. From the paper A https://journals.plos.org/plosone/article?id=10.1371/journal.pone....
0
votes
0answers
9 views

Perplexity calculation in variational neural topic models

I'm looking at this 2016 paper from Miao et al. https://arxiv.org/abs/1511.06038 where they use a variational autoencoder for topic modelling. To evaluate the effectiveness of their model, they use ...
0
votes
0answers
13 views

LSTM Autoencoder on Patterns of Labels

Currently, I am trying to do anomaly detection on univariate data consisting of labels. For example: [A, A, B, C] is good but [A, A, A, A] is anomalous. I'm dealing with more than just ABC. Is an LSTM ...
2
votes
0answers
45 views

Build an Autocomplete model for document titles

I want to build an autocomplete model using RNN where input is article names (documents title). X: ['Billing', 'Loan status', 'Filling loan application', 'Contact Info', ...] The article name can ...
-1
votes
0answers
85 views

Controlling how much a VAE overfits

I want to make my VAE overfit to the training sample to some degree. What is the best to way to control it? Weighting the KL divergence loss term, which basically becomes beta-VAE if I'm not wrong? ...
-1
votes
0answers
281 views

Outliner detection with LSTM autoencoder

I am learning about autoencoders for outlier detection. I have searched enough and internet suggest to use LSTM autoencoders for outlier detection from multivariant time series data. I have watched ...
0
votes
1answer
36 views

KL divergence in VAE

If I understand correctly KL-divergence is relative entropy of two distributions. To calculate KL divergence of two distributions, you would need two vectors of random variables. What I do not ...
0
votes
1answer
66 views

Training multiple keras models and combining outputs to determine losses

I'm trying to predict the future states of a 1D travelling wave (square, triangle and sawtooth) using a deep learning setup in Keras. The waves are discretised in a 1024 data points. As this gives a ...
1
vote
1answer
44 views

Training 128x128 autoencoders on 512x512 images, produces strange gridline after recombining

So I'm training an autoencoder that can recreate 128x128 images, so it can recreate any images by splitting them into 128x128 patches first, running it through the autoencoder, and having them ...
1
vote
0answers
76 views

What is the mathematical definition of the latent space [closed]

I have been seeking a mathematical explanation of the latent space of a neural network. The best I have gotten is "The latent space is the space in which the data lies in the bottleneck layer." ...
1
vote
1answer
37 views

Do anomalous input features to autoencoder result in high errors on the corresponding output features?

An autoencoder is trained by replicating each training instance to both input and output. However, when predicting for anomaly detection, will the output error be local to the same output feature(s) ...
0
votes
0answers
22 views

Encoder Decoder networks with varying image sizes

Encoder Decoder Network - Computerphile : At the very beginning of this video, Michael Pound goes on to say: So it (encoder decoder network) makes no assumptions about the size of the input the ...
0
votes
1answer
871 views

Validation loss is lower than the training loss

I am using autoencoder for anomaly detection in warranty data. Architecture 1: The plot shows the training vs validation loss based on Architecture 1. As we see in the plot, validation loss is ...
0
votes
2answers
333 views

How to use Autoencoders for outlier detection on images

I have a bunch of images taken from a camera showing a pipe and would like to detect if the pipe is leaking or not. There are very few examples of leaking pipe in the data set. So considering this ...
1
vote
1answer
34 views

Is train/test-Split in unsupervised learning of neural network necessary?

I am using autoencoder for anomaly detection in warranty data. It is unsupervised. I calculate the reconstruction error by the model and the records with high reconstruction error value is considered ...
1
vote
0answers
58 views

What is an intuitive explanation for the Importance Weighted Autoencoder?

I have been reading a paper by Burda et al. on Importance Weighted Autoencoders(IWAE) but I can't quite grasp what they mean by sampling the terms h1...hk. Do they mean you have separate models from ...
0
votes
1answer
33 views

Denoising Autoencoder Parameter Search

I have ran a hyperparameter search for a denoising autoencoder and the results suggest I should make the sizes of my hidden layers as large as possible (within the range of values I allowed it to ...
3
votes
1answer
211 views

What mu and sigma vector really mean in VAE?

In standard autoencoder, we encode data to bottleneck, then decode with using initial input as output to compute loss. We do activate matrix multiplication all over the network and if we are good, ...
3
votes
1answer
142 views

How can I prove bottleneck layer of my CNN auto encoder contain useful information?

I am using CNN autoencoder to create a state representation layer which I will later be feed into my Reinforcement Agent. So I trained my CNN autoencoder and it is giving nice state representations. ...
1
vote
0answers
19 views

Quantifying feature importances using Auto-encoders

I have a set of features(mixture of numerical and categorical), each of size n. I am embedding them into a dense lower dimensionality space using an auto-encoder. I want to know if it is possible to ...
1
vote
1answer
88 views

More weightage to a categorical feature for an Autoencoder model

I am using autoencoder for anomaly detection. I don't have any labels already and so its unsupervised. If I have categorical variables, I usually one hot encode before giving it to the model. I would ...
1
vote
0answers
91 views

Preserve colour in convolutional autoencoder

at the moment i work with convolutional autoencoder and now I'am looking for paper or methods that adresses a colour preversation. Most of the AE paper use grayscale images and loss functions such as ...
3
votes
1answer
287 views

How design a autoencoder architecture

I would like to build an autoencoder (CNN) to learn a representation of my data. I never built such a network and I have some experience in supervised learning (classification). I would like to know ...
3
votes
1answer
91 views

Fluctuating accuracy of Autoencoder

I am working on an Autoencoder in keras with the following setting: 185-86-32-2-32-86-185. The problem is that its accuracy is fluctuating, besides it gives new accuracy at every run. If this is due ...
1
vote
2answers
203 views

Cross validation for anomaly detection using autoencoder

I am using autoencoder for anomaly detection in warranty data. I don't have any ground truth labels to confirm whether the anomalies detected by the model is really an anomaly or not. Since I don't ...
1
vote
0answers
22 views

Autoencoder ambivalent about order of input data?

The problem I'm working to solve is this: Given a musician's prerecorded free-form playing. I want to analyze each of the individual notes to determine how "in-rhythm" it is. See the graph in the ...
2
votes
1answer
19 views

How do you know if your Autoencoder network is fully connected?

I am new in deep learning and I am confused about fully connected network. Is an Autoencoder with more than one hidden layers a type of deep neural network (DNN)? Is DNN always fully connected? Let's ...
2
votes
0answers
73 views

Encoder-Decoder Sequence-to-Sequence Model for Translations in Both Directions

Is it possible to use a pre-trained sequence to sequence encoder-decoder model which translates an input text in source language to an output in target language to do an inverse translation? That is, ...
2
votes
1answer
92 views

Why don't we want Autoencoders to perfectly represent their training data?

From Ian Goodfellow's Deep Learning Book: If an autoencoder succeeds in simply learning to set g(f(x)) = x everywhere, then it is not especially useful. Instead, ...
3
votes
2answers
460 views

Latent loss in variational autoencoder drowns generative loss

I'm trying to run a variational auto-encoder on the CIFAR-10 dataset, for which I've put together a simple network in TensorFlow with 4 layers in the encoder and decoder each, an encoded vector size ...
1
vote
1answer
149 views

Using DONUT algorithm with keras

I am trying to get this repo of Xu's DONUT algorithm running, however I am getting an error I do not quite understand. The readme says I should load raw_data as follows: ...