-3
votes
0answers
28 views

opennn simple example(neural network)?

Library opennn. I need simple example: With flower. flower: fragrant: 1.0 // properties(params) color: 2.0 evaluated object fragrant: -1.0 color: 2.0 After run. Neuron response ...
-2
votes
0answers
33 views

How to implement ANFIS in OpenCV? [closed]

I am new to machine learning....looking for some guidance. Could somebody please suggest me/link/idea on how to implement ANFIS in opencv? Is there any built-in learning scheme for this in OpenCV? I ...
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 ...
3
votes
0answers
102 views

Why is neural network not predicting?

I am trying to train a neural network using backpropagation algo. in OpenCV 2.3. However it is not predicting correctly....not even on training dataset. Could anybody please help me find whats wrong ...
0
votes
1answer
51 views

How to use Cross-Validation in OpenCV?

Can somebody please tell me how to employ cross-validation in OpenCV? I am working with Neural Networks module in OpenCV and there is no in-built option for cross-validation as in the case of Decision ...
-1
votes
0answers
38 views

Handwritten text recognition using NN in C++ [closed]

I would like to create a NN that has a scanned handwritten document as input and a digital version of it as output. I know the basics of MLP NNs and the only programming languages I know are C++ and ...
0
votes
0answers
70 views

How to correlate (X,Y) coordinate pairs in one meaningful unit

I have a 2D Array, where each row is a feature vector. Each feature vector is like: [x1 y1 x2 y2 x3 y3 x4 y4] where, (x1,y1) are coordinates of first feature point, (x2, y2) of second feature point ...
1
vote
1answer
91 views

Blondie24 and Evolving Artificial Neural Network [closed]

I have problem with understanding implementation of system called Blondie24 made by David Fogel. In this system we are using "Evolving Artificial Neural Network" (EANN) which is based on 4 layers of ...
0
votes
1answer
100 views

How to process multiple inputs in c++ for artificial neural network

How does C++ process multiple inputs for an artificial neural network in real-time? I'm assuming this is without using a spiking neural network, but a more traditional one (i.e. just a basic neural ...
-1
votes
1answer
255 views

C++ - Neural Network output always 1

Hello right now I'm developing an neural network application but I have a problem when I'm trying to print the output of the feedforward the console show this value the output always 1 1 1 1 1 I'm ...
1
vote
1answer
262 views

My neural net learns sin x but not cos x

I have build my own neural net and I have a weird problem with it. The net is quite a simple feed-forward 1-N-1 net with back propagation learning. Sigmoid is used as activation function. My ...
0
votes
1answer
90 views

Neural network output in c++

I want to create a function that calculates neural network output. The elements of my NN is a 19D input vector and a 19D output vector. I choose one hidden layer with 50 neurons. My code is the ...
2
votes
1answer
134 views

My classification neural network is having logic issues

I made my first 1 dimensional classification neural network in C++ in which the logic is as follows: If input <= 1: f(x) = 1 If input > 1: f(x) = -1 I made it extremely sloppy at first, but ...
0
votes
1answer
125 views

How to dynamically set the number and behavior of inputs/outputs in a neural network?

How would one implement a feed-forward neural network with a configurable number and dynamic behavior of inputs and outputs? I am trying to add neural networks to the entities in a game I'm working ...
1
vote
0answers
268 views

how to parallalize a backpropagation algorithm [closed]

I have problems parallelizing this code, can you help me please parallelizing it? Backpropagation is a method for computing how to adjust the values of the weight matrices so that output values are ...
0
votes
1answer
146 views

parallelizing dynamic arrays

this is part of back-propagation algorithm code on neural networks. in our case we want to parallelize the for( pt=0; pt< N_PT_pair; pt++) loop, the for(epoch=0; epoch< MaxEpoch; epoch++) can ...
1
vote
1answer
157 views

Different number of threads, different answers [closed]

So I have some neural network simulator code that works correctly on the CPU, and the parallel version agrees with the serial version to at least 6 decimal places with a 32-thread single block on both ...
2
votes
0answers
286 views

Opencv ML functions want CvFileStorage* instead of cv::FileStorage*

I am using the CvANN_MLP functions from the machine learning libraries in Opencv, and I want to write my trained network to a file. I have been able to do this fine with cv::FileStorage for keypoints ...
2
votes
1answer
737 views

Implementation of a softmax activation function for neural networks

I am using a Softmax activation function in the last layer of a neural network. But I have problems with a safe implementation of this function. A naive implementation would be this one: Vector y = ...
2
votes
2answers
784 views

Using FANN library

I've been experimenting with the FANN library, which seems to be a great library for neural network, and I'm having some issue on how to use it. So what I'm trying to do here is training a neural ...
1
vote
1answer
92 views

Unpredicted results from running while using ANN library (using FANN)

I am currently trying to get my ANN implementation to work (using FANN library) but somehow I always get very unpredictable results. I am training my network on such a training file 132 600 3 1 1 1 1 ...
1
vote
1answer
173 views

Numbers recognition, neural net not working properly

I'm doing an OCR project, trying to recognize numbers, at least. I have Hamming neural network with two layers. If it will solve the problem, I'll post a source here. The problem is that this network ...
1
vote
0answers
253 views

How to compile FANN with C++ wrapper?

I am trying to wrap the FANN library with attached to the download zip wrapper (fann_cpp.h) but I have no idea how to do it. When I compile the library normally i don't get any errors but when I ...
1
vote
2answers
731 views

Face Recognition Using Backpropagation Neural Network?

I'm very new in image processing and my first assignment is to make a working program which can recognize faces and their names. Until now, I successfully make a project to detect, crop the detected ...
0
votes
0answers
520 views

NeuralNetwork: Backpropagation

I've been scratching my head a long time on this... Basically I'm trying to do Neural Network Backpropagation training. I believe I have the error back propagation correct; but it doesn't seem to ...
3
votes
1answer
427 views

What is the way to implement neural networks in c/c++?

I wanted to use neural networks for pattern matching in c++. The scenario is like this: The main goal is to determine a product by name when captured by a camera. A rectangular pack of a product ...
1
vote
4answers
213 views

How to map 10 bits to 6 bits in C++ (as efficiently as possible)?

So I know functionally what I would like to happen, I just don't know the best way to make a computer do it... in C++... I would like to implement a C++ function that maps a 10 bit sequence to a 6 ...
0
votes
3answers
856 views

Neural network with genetic algorithm question

Since this question is going to quite long you can read cliff notes at the bottom, or read the full text here. I'm playing around with genetic algorithms and neural networks (i.e. using genetic ...
0
votes
1answer
470 views

capture packets then drop packet IPS system

Is there any possible way in windows to "drop" packets like a true IPS(intrusion prevention system) similar to iptables in unix. Also if im using matlab is there a way to "capture packets on the ...
2
votes
1answer
368 views

C# C++ dropping packets

Is there a way to drop packets like iptables in Unix using c# or c++? Im looking to develop a Bayesian neural network utilising fuzzy logic for a Intrusion Prevention System and im not sure which way ...
0
votes
1answer
366 views

what c++ for feedforward neural network do you suggest?

I want to do some classification problem (word sense disambiguation) in c++; and I need a a feedforward neural network (MLP). I know there are many libraries but I want the one that is not very large, ...
-1
votes
2answers
114 views

Segmentation fault in neural network

I have been writing a code for a neural network using back propagation algorithm and for propagating inputs I have written the following code,but just for two inputs,its displaying segmentation ...
10
votes
2answers
779 views

Problem with simple artificial neural network — adding

I am trying to make a simple artificial neural network work with the backpropagation algorithm. I have created an ANN and I believe I have implemented the BP algorithm correctly, but I may of course ...
3
votes
1answer
564 views

How to manage connections of neurons inside ANN using OpenCV::ML?

So there is grate sample (only one real sample we found). And it is quite limiting. It shows how to create an architecture of artificial neutral network where all neurons of one layer are connected ...
6
votes
1answer
611 views

OpenCV::ML - is it possible to tell openCV which parts of data we want to send to which neuron?

So here is shown a simple example - 2 floats as data + 1 float as output: Layer 1: 2 neurons (2 inputs) Layer 2: 3 neurons (hidden layer) Layer 3: 3 neurons (hidden ...
0
votes
1answer
888 views

Where to get a source example of creation of a Multi-layer Perceptron using OpenCV?

I need an example of Multi-layer Perceptron (with at least 3 layers) C/C++ programm using OpenCV. Where can I get one?
0
votes
2answers
382 views

FANN Error 1: unable to open file

I was trying this code but i get error, I can't solve this problem! anybody have idea? #include<iostream> using namespace std; #include <cv.h> #include <highgui.h> #include ...
0
votes
2answers
894 views

matlab neural network toolbox

I used the matlab neural network to train on some data but I want to run this neural network in c++ program,how to do that?
4
votes
2answers
792 views

Using genetic algorithms for neural networks

Currently I am working on a project that would use genetic algorithms to optimize neural networks. I do realize this is probably not the best way to optimize them, but I'm new to both so I just ...
2
votes
3answers
119 views

What tool/library can help me to generate and test model of neural network that would work with X*Y int arrays as input and N*4 int arrays as output?

I want to make simple neural network that from given gray-scale 2d arrays like [[1 1 1] [0 0 0] [1 1 1]] would give me line coordinates [[1 2] [3 2]] I have a C++ program that has a real ...
0
votes
1answer
558 views

Neural network programming; converting Matlab to C++

We have a program written in matlab software. It contains a Hopfield net that saves a pattern after searching a large picture to find it. Is it possible to rewrite this code in a programming language ...
3
votes
4answers
511 views

How to go about searching for a player models in COD with OpenCV

I am attempting to create a program that can find human figures in video of game play of call of duty. I have compiled a list of ~2200 separate images from this video that either contain a human ...
2
votes
6answers
1k views

c++ or java for robotics [closed]

I know embedded C is used for micro-controllers along with other languages. but what if the control was from a PC, well I had two possible candidates (java and c++) Java is simple and easy also ...
4
votes
1answer
950 views

Neural Networks: Minimal, open source example with exhaustive training data?

I am currently searching for a neural network (toy) example, that I might optimize using GPU kernels. I need clean & minimal code (no fancy optimizations, max. a few thousand sloc) ample ...
2
votes
1answer
197 views

c++ matrix template library need for neural networks computations

hi i'm implementing some neural network algorithms and i'll be needing a matrix library, I've looked and found that there are ones like ( boost::ublas ) , (blitz++), TNT... I need experts opinion ...
5
votes
3answers
2k views

Getting a simple Neural Network to work from scratch in C++

I have been trying to get a simple double XOR neural network to work and I am having problems getting backpropagation to train a really simple feed forward neural network. I have been mostly been ...
17
votes
5answers
7k views

Modern C++ style neural network libraries?

Looking for neural network libraries (providing the basic multi-layer-perceptron with back-propagation and possibly teachers) I did find only libraries which seem to come from the 1990s and don't use ...
1
vote
7answers
5k views

C++ boost shared_ptr as a hash_map key

I'm making a neural network and wanted to use a hash_map to keep weight references for output neurons for each neuron: class Neuron; //forward declaration was there (sorry I forgot to show it ...
4
votes
3answers
5k views

Neural network XOR backpropagation info needed

Does anyone know where I can find some sample codes about the NN Back propagation for XOR, that I can also test the system after it was trained? Preferably in C++ or MATLAB.
4
votes
7answers
913 views

C++/Java Performance for Neural Networks?

I was discussing neural networks (NN) with a friend over lunch the other day and he claimed the the performance of a NN written in Java would be similar to one written in C++. I know that with 'just ...