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-network
Search options not deleted
user 76883
Artificial neural networks (ANN), are composed of 'neurons' - programming constructs that mimic the properties of biological neurons. A set of weighted connections between the neurons allows information to propagate through the network to solve artificial intelligence problems without the network designer having had a model of a real system.
1
vote
why variational inference in variational autoencoder if dealing with simple graphical model
I'm not sure if I get the question correctly, but we use variational inference, because we do have many dependencies. X and Z are usually high-dimensional vectors with complex relationships.
- 1,555
1
vote
how to design sigma(std) vector to have values above > 0 in VAE autoencoder
Yeah, almost, except that Relu might cause problems ones it goes to zero (having zero variance is a little odd and the gradient goes to zero as well). Usually you'd go with
$$ \sigma = \exp(\rho) $$
…
- 1,555
2
votes
Accepted
Trouble understanding the partial differentiation used in reinforcement learning
Your understanding of what's going on seems to be correct, just one little clarification: $u$ should be the model parameters of the deterministic policy $\mu(s,u)$ and not a distribution itself, same …
- 1,555
1
vote
Accepted
neural network probability output and loss function (example: dice loss)
I think there is a bit of confusion here. The dice coefficient is defined for binary classification. Softmax is used for multiclass classification.
Softmax and sigmoid are both interpreted as probabi …
- 1,555
6
votes
How can you include information not present in an image for neural networks?
Edit: after the edit in the question, 1) does not relate so much anymore, but 2) still does.
It depends a bit on the form of the location data. If you have a segmentation mask (i.e. another image wit …
- 1,555
1
vote
Why do we operate with graphical models in VAE, if there are no probabilites involved?
Not sure which type of code you were looking at but e.g. here they do sampling of random variables. The encoder deterministically maps the input X to mean and standard deviation vectors. Using these v …
- 1,555
4
votes
Accepted
Dealing with irrelevant features in dataset (Homework)
This could be many things.
Since you want to calssify the data into three classes, I would use one-hot-encoding, rather than the binary enumeration, because you kind of introduce the information to …
- 1,555
2
votes
Accepted
Bayesian regularization vs dropout for basic ann
It actually makes perfect sense to use both. Gal et al. provided a nice theory on how to interpret dropout through a Bayesian lense. In a nutshell, if you use dropout + regularization you are implicit …
- 1,555
0
votes
What do graphs of signal vs background neural network outputs represent?
Okay, your output makes sense, given what you wrote in the comments. But if you don't know where the other output comes from, all else is speculation. It could be that it was generated by a neural net …
- 1,555
0
votes
Clause type classification
Not sure where you are in terms of prior knowledge, but this blog post might get you started.
- 1,555
12
votes
Accepted
Why must a CNN have a fixed input size?
I think the answer to this question is weight sharing in convolutional layers, which you don't have in fully-connected ones. In convolutional layers you only train the kernel, which is then convolved …
- 1,555
0
votes
Why do we need convolutions over volume in convolutional neural networks for image recognition?
I'm not sure if the information in the colours is as redundant for real images as you say. I could imagine a scenario where the colours around an edge are relevant, e.g. training a network to tell bro …
- 1,555
2
votes
Accepted
Backpropagation and Stochastic Gradient Descent(SGD)
Stochastic Gradient Descent (SGD) is an optimization method. As the name suggests, it depends on the gradient of the optimization objective.
Let's say you want to train a neural network. Usually, the …
- 1,555
1
vote
Convolutional neural network giving high confidence on wrong classification
Since your model seems to be doing fine on the correct hand signs, I don't think there is anything wrong. It's a common misconception that you can interpret the model output as a confidence measure. C …
- 1,555