Questions tagged [Fast Artificial Neural Network] (14)

0
answer

How to drive the input data in pfan_type?

Use the fann library, never figured out how to drive in the input vector data (Pfann_type) that after learning to run fann_run(ann,pfan_type(Here I do not understand)) please tell me.
Aurelio64 asked April 3rd 20 at 16:55
2
answers

How much data is needed for training a neural network?

I tried to write a bot for betting. Used the library FANN. Taught at 40,000 matches, check the next 10,000 unknown data, the network showed 66-69% of correct results. 1. So many matches you can make any conclusions, or need any sample is much superior to this? 2. After each run of 40 000 data, the results ranged from 66 to ...
shanel_Bechtelar22 asked April 2nd 20 at 15:46
1
answer

FANN php I do not understand how to start?

Good day! Read a bunch of information and I can not figure out how can I make the data on the training! I have a database of 50,000 texts in the database have an index/ weight/ and the result is the text positive or not! I understand that I need to take the index and the weight and result and submit to Naranco her to unders...
Jon_Crist asked March 31st 20 at 15:02
1
answer

The integration of the fann library in android studio where to find the files libfann.so?

Trying to integrate the fann library in android studio, but all the even. In my project I also use libgdx and I have the files:arm64-v8a armeabi armeabi-v7a x86 x86-64 In all of these files I have: libjnidispath.so - this file for each folder. When I run the project, I have it falls with error java.lang.An unsatisfiedlinke...
0
answer

Error when calling a Cuda kernel?

Good afternoon, in the program class:class neuralNet { float input_nodes; float hidden_nodes; float output_nodes; float learning_grade; float* wih; float* who; public: neuralNet(int in, int hid, int out, float lr); ~neuralNet(); float*activation_function(float* a, int n); void train(float*inputs, float*targets); ...
Berniece_Cron asked March 20th 20 at 11:23
2
answers

In the kernel to cause the kernel?

Hello, I am writing a neural network for digit recognition (to start) on CUDA. Need to write a function on the device, which in each block calls the function of the neural network training. Just the workouts, and therefore blocks should be 60 000. The workouts function I have written, but it is also running on the device. N...
Mackenzie_Feeney asked March 20th 20 at 11:20
0
answer

Is there any solution for Windows for text generation based on neural networks?

There is a narrowly-specific text information of the order of 50 MB, you need to multiply every 20-30, even with the loss of quality and some share of meaning. I want to try the neural network, but absolutely zero in this technology. Googled it https://github.com/sherjilozair/char-rnn-tensorflow but I do not understand from...
Icie72 asked March 13th 20 at 14:50
1
answer

How to work with function fann_test_data()?

How to use the function fann_test_data() ? I don't understand is the second parameter? How do we get a second function argument?
dayna.Marvin22 asked March 11th 20 at 20:42
2
answers

FANN + C# + 64x = fail

The problem is that the FANN library, and therefore the code described heredoes not work on 64x systems. What is the problem, maybe it's the wrapper .NETŠ° curve? Off the forum I answer not given
Jeramy.Schaden asked October 8th 19 at 00:54
1
answer

How to Connect the library to intellij idea?

Look , there is a library , fann , it is written in C++ , I need to integrate it into java , I found two jar file , fannj_0_6 and jna_4_1_0. I turned them on , but during the implementation climbs error "Exception in thread "main" java.lang.An unsatisfiedlinkerror: Unable to load library 'fannfloat'" I realized that this i...
tomas_Bru asked September 9th 19 at 13:41