This refers to techniques for configuring the structure and parameters of neural network parameters.
0
votes
1answer
10 views
Designing Neural Networks
I am learning about Neural Networks and back-propagation. I think I understand how the network works, in terms of input, output, hidden layers, weights, bias etc However, I still don't fully ...
1
vote
1answer
26 views
scaling inputs data to neural network
Do we have to scale input data for neural network? How does it affect the final solution of neural network?
I've tried to find some reliable sources on that. The book "elements of statistical ...
0
votes
1answer
95 views
Continuously train MATLAB ANN, i.e. online training?
I would like to ask for ideas what options there is for training a MATLAB ANN (artificial neural network) continuously, i.e. not having a pre-prepared training set? The idea is to have an "online" ...
1
vote
2answers
679 views
How to customize error function of MATLAB Neural Network
I want to implement this function as the error function for training a neural network:
function err = MyErrorFunction(T,O)
d = T - O;
err = -d*( exp(-d) - 1 );
end
where T is target value and O ...
0
votes
1answer
96 views
Issue with gradient calculation in a Neural Network (stuck at 7% error in MNIST)
Hi I am having an issue with my calculation of checking the gradient when implementing a neural network in python using numpy.
I am using mnist dataset to try and trying to using mini-batch gradient ...
1
vote
0answers
35 views
Configuring ANN for face recognition
Before I ask my question, here's a brief summary of my project:
I'm using OPENCV's built-in function to detect a face in a
cam-feed.
After that I'm processing the image which contains the face, ...
0
votes
0answers
15 views
FANN for function approximation
I need some help with learning a neural network using FANNTool (automatical parameters setting) with a given data file, which can be found here: http://goo.gl/mV34T. This data was generated with a ...
1
vote
1answer
37 views
Neural Network seems to work fine until used for processing data (all of the results are practically the same)
I have recently implemented a typical 3 layer neural network (input -> hidden -> output) and I'm using the sigmoid function for activation. So far, the host program has 3 modes:
Creation, which ...
2
votes
1answer
45 views
Multi threaded AForge.NET training
I am using AForge.NET ANN and training it on my training set. Because the training is single threaded and the process can take ages, I wondered if it's possible to run a multi threaded training.
...
0
votes
1answer
323 views
Neural network for multiple input and multi output (MIMO) systems
I want to build a neural network for a multi input and multi output (MIMO) system described as:
y1(t)= f1( x1(t), x2(t),...xn(t))
y2(t)= f2( x1(t), x2(t),...xn(t))
.....
.....
ym(t)= fm( x1(t), ...
2
votes
1answer
193 views
Neural network, is it worth changing learning rate and momentum over time
Is it worth to change learning rate after certain conditions are met? And how and why to do it? For example net will start with high learning rate and after squared error is low enough learning rate ...
0
votes
1answer
127 views
How to extend upper and lower limits of ANFIS membership function in MATLAB?
I am trying to implement ANFIS on MATLAB. My input data operating range is 0-180, but MATLAB generates ANFIS membership function limits within 0-10. How to extend it from 0 to 180?
Also another ...
2
votes
0answers
55 views
Training a neural network with constrained units
Motivation:
The state of the art algorithm for object recognition is a deep convolutional neural net trained through backpropagation, where the main problem is getting the network to settle in a ...
1
vote
3answers
322 views
neural network training set
My question is about a training set in a supervised artificial neural network (ANN)
Training set, as some of you probably know, consists of pairs (input, desired output)
Training phase itself is the ...
0
votes
1answer
59 views
Neural Network for Phishing detection , features to be extracted from URL and contents to pass as input
This is in continuation with my Previous question
We successfully extracted the URL and contents from a website which we are supposed to check for phish .
Now we have a database of whitelist and ...
