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 28175
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
How does neural network solve XOR problem
The table that you are referring to is doing OR operation. whenever you have just a neuron in your net you are able to have one line to separate your data. but for xor data you have to have two line s …
- 14.2k
1
vote
AlexNet second layer understanding
It uses same padding which means the output of max-pooling is padded with zeros in a way that the output of next layer preserves the width and height. for information take a look at here.
- 14.2k
6
votes
2
answers
7k
views
Does MLP always find local minimum
In linear regression we use the following cost function which is a convex function:
We Use the following cost function
in logistic regression because the preceding cost function is not convex whe …
- 14.2k
12
votes
2
answers
10k
views
Why large weights are prohibited in neural networks?
Why weights with large values cause neural networks to be overfitted, and consequently we use approaches like regularization to neutralize weights with large values?
- 14.2k
1
vote
RNN vs CNN at a high level
If I want to tell you, both are based on a same concept, and that is weight sharing. It is better to think about them in this way.
In CNNs, we try to find similar patterns throughout the input which c …
- 14.2k
1
vote
Accepted
Building CNN, Need More Images
I recommend you using Keras and employing its pre-trained models. Because of low number of data-set, you should use transfer learning. There are lots of researches about that like here. Based on the d …
- 14.2k
-1
votes
Meaning of Perceptron optimal weights
Using perceptron, you specify a cost function, Mean Squared Error for regression tasks or maybe Cross Entropy for classification tasks. The input data are the constants and the weights are the paramet …
- 14.2k
1
vote
Should the different layers of deep learning models have same size or they should be changed...
Actually it is not completely clear which deep neural nets you are referring to but I guess you are referring to Dense, aka fully connected, networks. It depends on your data but for simplification, b …
- 14.2k
2
votes
Neural Network Performs Bad On MNIST
I guess you are doing something wrong in your code. I guess its better to use gradient checking approach for figuring out whether the whole code has any problem or not.
Based on the comments, if I w …
- 14.2k
1
vote
Deep learning technique to recognize a person's silhouette
For this purpose you have to have a data-set that can be interpreted by the human. I mean an expert should label the data samples without hesitating. Then you can make a typical neural network and tra …
- 14.2k
0
votes
Why do we have multiple neurons in the output layer of a neural network?
Neural networks can be used for classification and regression tasks. They are also used for transcription and clustering. Each of them can have their own characteristics. For classification tasks you …
- 14.2k
0
votes
What to do when we can't trust our human classifiers?
I have the following solutions:
If you have abundant data you can shuffle them and make validation and training data. After that, your neural network should exploit generalization techniques not to …
- 14.2k
1
vote
What is the role of the bias?
Bias simply means how much the output does not depend on the inputs. It is exactly equivalent to intercept term which means by dropping all the inputs what the outputs will be.
We usually set bias te …
- 14.2k
2
votes
How to know the name of the predicted class?
You as the designer of the network specify each class in the training example. You set e.g. a car class to label $0$ and another class to $1$. During training your classifier tries to map the inputs t …
- 14.2k
1
vote
How to build a classifier with a rejection class
What is the best way to do that? Should I just add a new class label that includes pictures of anything but food?
Adding a new class which can be called none is a thing that is usual for such tas …
- 14.2k