An autoencoder, autoassociator or Diabolo network is an artificial neural network used for learning efficient codings.
1
vote
1answer
56 views
Ada-Delta method doesn't converge when used in Denoising AutoEncoder with MSE loss & ReLU activation?
I just implemented AdaDelta (http://arxiv.org/abs/1212.5701) for my own Deep Neural Network Library.
The paper kind of says that SGD with AdaDelta is not sensitive to hyperparameters, and that it ...
1
vote
1answer
33 views
mlpack sparse coding solution not found
I am trying to learn how to use the Sparse Coding algorithm with the mlpack library. When I call Encode() on my instance of mlpack::sparse_coding:SparseCoding, I get the error
[WARN] There are 63 ...
0
votes
1answer
33 views
Theano implementation of Stacked DenoisingAutoencoders - Why same input to dA layers?
In the tutorial Stacked DenoisingAutoencoders on http://deeplearning.net/tutorial/SdA.html#sda, the pretraining_functions return a list of functions which represent the train function of each dA ...
3
votes
2answers
50 views
Using large input values with Auto Encoders
I have created an Auto Encoder Neural Network in MATLAB. I have quite large inputs at the first layer which I have to reconstruct through the network's output layer. I cannot use the large inputs as ...
1
vote
0answers
38 views
Machine Learning: Simulated Annealing on Autoencoders
I have implemented simulated annealing for solving the cost function of a simple weight tying neural network, but am receiving some weird results.
Logic:
Forward prop : f(W*x+b), where f = tanh, W ...
3
votes
1answer
171 views
Deep Belief Networks vs Convolutional Neural Networks
I am new to the field of neural networks and I would like to know the difference between Deep Belief Networks and Convolutional Networks.
Also, is there a Deep Convolutional Network which is the ...
1
vote
1answer
49 views
How do you decide the parameters of a Convolutional Neural Network for image classification?
I am using Convolutional Neural Networks (Unsupervised Feature learning to detect features + Softmax Regression Classifier) for image classification. I have gone through all the tutorials by Andrew NG ...
1
vote
1answer
24 views
Autoencoders: Papers and Books regarding algorithms for Training
Which are some of the famous research papers and/or books which concern Autoencoders and the various different training algorithms for Autoencoders?
I'm talking about research papers and/or books ...
0
votes
1answer
28 views
Does Theano support variable split?
In my Theano program, I want to split the tensor matrix into two parts, with each of them making different contributions to the error function. Can anyone tell me whether automatic differentiation ...
1
vote
1answer
29 views
Feature Construction for Text Classification using Autoencoders
Autoencoders can be used to reduce dimensionallity in feature vectors - as far as I understand. In text classification a feature vector is normally constructed via a dictionary - which tends to be ...
0
votes
0answers
59 views
How to implement denoised autoencoder which receives continuous input vector?
I want to write denoised autoencoder with Java. My auto encoder was written as this.
DenoisedAutoencoder.java
This is implemented as simple neural network which uses backpropagation algorithm for ...
1
vote
0answers
176 views
Auto-encoder to reduce input data size
Currently, I want to use the autoencoder for reducing the input data size in order to use the reduced data for another neural networks. My task is to take a video and then give the images of the video ...
0
votes
1answer
322 views
Implementation of Autoencoder [closed]
I'm trying to implement an Auto-encoder by my own in Java. From the theory, I understood that auto-encoder is basically a symmetric network.
So, if I chose to have 5 layers in total, do I have to use ...
