-
dammikasandaruwan
visual-studio-2010 visual-c++ neural-network fann
i am new to the c++ working environment and these days i am working in a neural network project. so i decided to use FANN neural network library. i create my own c++ win 32 solution and add all the relavant files from FANN downloaded source folder. then i run the xor sample example which is in FANN 2.2/vs2010 folder. but when i run the project it generates unhandled exception called Unhandled exception at 0x77ea15ee in test7.exe: 0xC0000005: Access violation writing location 0x003a6010.in the de
-
shridatt
android neural-network noclassdeffounderror
I am using neuroPh 2.7 for my android app. When i tried to load the neural network i get the following error. The stacktrace is as follows06-01 12:50:14.353: W/dalvikvm(2780): VFY: unable to resolve static method 4482: Lorg/neuroph/core/NeuralNetwork;.load (Ljava/io/InputStream;)Lorg/neuroph/core/NeuralNetwork; 06-01 12:50:14.353: W/dalvikvm(2780): VFY: unable to resolve virtual method 4483: Lorg/neuroph/core/NeuralNetwork;.setInput ([D)V 06-01 12:50:14.363: W/dalvikvm(2780): VFY: unable to reso
-
David Williams
python neural-network swig fann
I just built and installed libfann and the associated python bindings. The python setup seemed to run ok:$ sudo python setup.py install Running SWIG before: swig -c++ -python pyfann/pyfann.i running install running build running build_py copying pyfann/libfann.py -> build/lib.macosx-10.5-x86_64-2.7/pyfann running build_ext building ‘pyfann._libfann’ extension gcc -fno-strict-aliasing -I/Users/dwilliams/Desktop/Anaconda/include -arch x86_64 -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -D
-
Smi
matlab neural-network sim-card
My project is to recognize ancient coins. I am using Matlab. I already have a feature file which contains both inputs and output. I have trained 3 types of coins using newff and net had been saved. For the three types of coins, I used 01, 10 and 11 as targets. Now I want to use that trained net for testing. I have test images too. I coded like this:load net.mat; load features.mat; testInputs = Features’; out = sim(net,testInputs); [dummy, I]=max(out);Value of I is using to check the coin type. I
-
Franck Dernoncourt
matlab neural-network matlab-toolbox
In MATLAB, feedforwardnet(8) creates a feedforward network with one hidden layer containing 8 hidden neurons. MATLAB stores numeric data as double-precision floating point (double) by default. Therefore feedforwardnet(8) is equivalent to feedforwardnet(double(8)). However, feedforwardnet(int32(8)) will raise the following error:Undefined function or variable ‘ind’.Error in network/subsasgn>setLayerSize (line 1170)err = sprintf(‘”layers{%g}.size” must be a positive integer.’,ind);Error in netw
-
MHardy
artificial-intelligence neural-network ubuntu-12.04 fann
I am trying to build fann neural network library in ubuntu 12.04 but failed to use it as the testing routine is not working. Following the instructions in http://leenissen.dk/fann/wp/help/installing-fann/. After cmake and install when I want to test if the library is working, by cd to examples and then running:make runtestwhat I get is here:gcc -O3 xor_train.c -o xor_train -lfann -lm gcc -O3 xor_test.c -o xor_test -lfann -lm gcc -O3 -DFIXEDFANN xor_test.c -o xor_test_fixed -lfixedfann -lm gcc -O
-
Trung Huynh
python artificial-intelligence neural-network time-series
I want to use neural networks to predict a timeseries B in the next 30 days from now based on a series A (I have the full history of series A), and a list of events E in the next 30 days (E is a list of binary units). Knowing that B is linearly proportional to A and when an event in day i happens (E[i] = 1), it triggers a spike on B (the ratio is unknown). I have training data containing tuples of (A, E, B). I have tested with feed forward network, but it doesn’t perform very well (not predictin
-
user1068446
machine-learning neural-network weka xor
I’m just getting started with Weka and having trouble with the first steps.We’ve got our training set:@relation PerceptronXOR @attribute X1 numeric @attribute X2 numeric @attribute Output numeric @data 1,1,-1 -1,1,1 1,-1,1 -1,-1,-1First step I want to do is just train, and then classify a set using the Weka gui. What I’ve been doing so far:Using Weka 3.7.0.Start GUI. Explorer. Open file -> choose my arff file. Classify tab. Use training set radio button. Choose-> functions>multilayer_perceptr
-
muntoo
java matlab neural-network
I’m working on my final year project. I need to load Matlab neural network from Java.This is the method I have created to load the neural network:function [result] = viewforecasteddata(newinputs)%#function network load(‘Test.mat’,’net’);result = net(newinputs);endThis how I’m calling from Java:result = theCost.viewforecasteddata(1,mWNumericArray);I’m getting these warnings and exceptions:{Warning: While loading an object of class ‘nnetWeight’: Undefined function or method ‘initzero’ for input a
-
MrLinjak
visual-studio-2010 neural-network neural-network-tuning fann
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, i.e. converting it to grayscale, resizing it to 40X40 pixels and equalizing its’ histogram. The pixel values of the image are then read, normalized (i.e. divided by 256 since FANN works with values between 0 and 1, or -1 and 1, depending on the used function) and saved into an array of 1600 elements. This
-
Sahar
matlab neural-network outofmemoryerror
I have a problem which occurs when I write the command line of the rbf (radial basis function) neural networknet = newrb(T, D);I get the error **??? Error using ==> unknown Out of memory. Type HELP MEMORY for your options.Error in ==> dist>apply at 119 z = zeros(S,Q);Error in ==> boiler_weight at 38 result = apply(a,b,c);Error in ==> dist at 90 boiler_weightError in ==> newrb>designrb at 143 P = radbas(dist(p’,p)*b);Error in ==> newrb at 127 [w1,b1,w2,b2,tr] = designrb(p,