Search Results
| Search type | Search syntax |
|---|---|
| Tags | [tag] |
| Exact | "words here" |
| Author |
user:1234 user:me (yours) |
| Score |
score:3 (3+) score:0 (none) |
| Answers |
answers:3 (3+) answers:0 (none) isaccepted:yes hasaccepted:no inquestion:1234 |
| Views | views:250 |
| Code | code:"if (foo != bar)" |
| Sections |
title:apples body:"apples oranges" |
| URL | url:"*.example.com" |
| Saves | in:saves |
| Status |
closed:yes duplicate:no migrated:no wiki:no |
| Types |
is:question is:answer |
| Exclude |
-[tag] -apples |
| For more details on advanced search visit our help page | |
Results tagged with neural-networks
Search options not deleted
user 49646
Artificial neural networks (ANNs) are a broad class of computational models loosely based on biological neural networks. They encompass feedforward NNs (including "deep" NNs), convolutional NNs, recurrent NNs, etc.
1
vote
How do I use intensity levels in a neural network?
I would use these "intensity" levels to modify the loss function. From your description of these intensity values, I would intuitively want my model to be more sure about the more intense examples.
S …
- 1,447
2
votes
Accepted
How are the numbers of a filter decided in a Convolutional neural network?
Or are they random numbers that backpropagation will soon change to fit best with the data?
In short, yes.
The numbers in a filter (yes, they are called the weights) are usually randomly initial …
- 1,447
3
votes
Accepted
How does neural network training work, if there are A HUGE number of points that not differe...
The simple and perhaps unsatisfying answer is that we arbitrarily choose a gradient at 0.
Typically deep learning libraries will choose to have a gradient of 0. We can see this using the python libra …
- 1,447
5
votes
What is the loss function used for CNN?
As Jan says in a comment, AlexNet uses cross entropy as the loss function.
It's important to note, though, that a Convolutional Neural Network describes the architecture of the network, not the goal …
- 1,447
1
vote
Accepted
Train an ensemble of neural networks on different datasets, what is the best way to scale th...
I would normalize the data using the statistics from the entire training data.
If min/max scaling is what you've determined to be the best, then I'd use the min/max from the whole training data.
I w …
- 1,447
8
votes
Accepted
How to train an LSTM when the sequence has imbalanced classes
Inversely proportional contributions to cost function
Another way of dealing with imbalanced data is to weight each label's contribution to the cost function inversely proportional to the frequency o …
- 1,447
7
votes
Accepted
What can Deep Neural Networks do that Support Vector Machines can't?
I will list a few areas where I am fairly confident DNNs perform better than SVMs, and it's not just the "hype". I'm sure there are more, just as I'm sure there are places where SVMs would do better. …
- 1,447
1
vote
Use of stack of tanh layers
In your linked paper (you should provide the full citation to avoid link rot) we see the following
Our neural network classifier, depicted in Figure 3 (and based
on a one-layer model in …
- 1,447
1
vote
Accepted
Accelerating multi-label classification using NNs
I use sigmoid when there are an arbitrary number of possible labels. In your case, you know you have exactly two labels. I would instead use softmax and divide the true label by two, for example [0,.. …
- 1,447
1
vote
(Deep learning) classification confidence
You have not informed your model that there are other options, so in some ways it may be unsurprising that it guesses one. The softmax function in particular is designed to accentuate even slight diff …
- 1,447
1
vote
When to stop training of neural network when validation loss is still decreasing but gap wit...
As long as your validation loss is continuing to decrease, your model is continuing to perform better in a generalized setting.
A growing gap between training and validation performance does mean tha …
- 1,447
7
votes
Accepted
RNN vs Convolution 1D
Yes the interpretation of the dimensions is pretty similar in both cases.
An important case where RNNs are easier to use is with data of unknown lengths. For example, in sentence translation (e.g. t …
- 1,447
14
votes
Accepted
Variable importance in RNN or LSTM
In short, yes, you can get some measure of variable importances for RNN based models. I won't iterate through all of the listed suggestions in the question, but I will walk through an example of sensi …
- 1,447
1
vote
How to extract the features making up the hidden layers in Autoencoders
Most neural-network based autoencoders I am familiar with do not make a hard decision on which input features will be kept and which will be thrown away. Think of a typical Fully Connected autoencoder …
- 1,447
29
votes
Accepted
Hidden Markov Model vs Recurrent Neural Network
Summary
Hidden Markov Models (HMMs) are much simpler than Recurrent Neural Networks (RNNs), and rely on strong assumptions which may not always be true. If the assumptions are true then you may see b …
- 1,447