Stack Overflow
Stack Overflow

Questions tagged [encog]

Encog is an advanced neural network and machine learning framework.

Encog is an advanced neural network and machine learning framework. Encog contains classes to create a wide variety of networks, as well as support classes to normalize and process data for these neural networks. Encog trains using multithreaded resilient propagation. Encog can also make use of a GPU to further speed processing time. A GUI based workbench is also provided to help model and train neural networks. Encog has been in active development since 2008.

Encog is available for Java, .Net and C/C++.

243 questions
0
votes
1 answer

Reducing the number of output neurons

I am trying to train a neural network to control a characters speed in 2 dimensions. x and y between -1 and 1 m/sec. Currently I split the range into 0.1 m/sec intervals so I end up with 400 output neurons (20 x values * 20 y values) if I increase…
Hamza Yerlikaya
  • 49,047
  • 44
  • 147
  • 241
0
votes
1 answer

Encog: weights keep increasing

I am trying to train a neural network with Encog library. Dataset (~7000 examples) before splitting (into training (60%), cross-validation (20%) and testing (20%)) is linearly normalised so that it looks like this: Min=-1.000000; Max=1.000000;…
Pijusn
  • 11,025
  • 7
  • 57
  • 76
0
votes
1 answer

Selecting a machine learning training method

I have the following data which has already been normalized: customer id customer age customer location home owner car vale risk factor married package a package b package c Based on all the factors above, I would like to predict what packages;…
user1477388
  • 20,790
  • 32
  • 144
  • 264
0
votes
1 answer

Simple neural network multiply training on untrained data gives big errors

i have made small multiplication neural network by using encog library with sigmoid activation function on the basic network. My problem is i got big errors on untrained datas. How can i enhance untrained data more good results.Less error…
Kadir BASOL
  • 729
  • 2
  • 10
  • 20
0
votes
1 answer

Encog3 Neural Networks C# : What is the interface used to input multiple data points in encog3?

Here's the pdf! which I used to learn about encog implementation. I get how it works for one data point, my input has multiple data points. From my understanding, I think ILayer interface is used to define each layer, which I am not sure, Please…
Satt
  • 63
  • 1
  • 1
  • 8
0
votes
1 answer

Cannot scale data with encog

currently I'm trying to scale my data file (train.nn) by using encog 3, my data file looks like this (This is a simplified example, in my real file, I have up to 249 features for each sample SP): 1,0,1,2,SP 4,5,6,1,SP And this is my code for…
Xitrum
  • 7,765
  • 26
  • 90
  • 126
0
votes
1 answer

Format of training data in CSV type for encog 3.0 and using it

I wonder that how can I make a csv file for storing training data in encog. Currently I have 200 features (f) as inputs and multi outputs (o) (for example author A, B ,C...). So how can organize the CSV file ? Should I look like this? f1, f2, f3…
Xitrum
  • 7,765
  • 26
  • 90
  • 126
0
votes
1 answer

C# ENCOG SVM classification with my own dataset

I would like to do a multiclass classification application in C#. I decided to use encog to do so. Now I am stuck at one point. I found a XOR example, which I understand. But when I am going to use my own dataset, app is computing only with one…
user2886091
  • 725
  • 7
  • 16
  • 29
0
votes
2 answers

Proofing encog xor results in excel

I'm working to proof basic neural network results and so far haven't been able to. I'm doing a feed-forward xor problem in encog and export the final weights and calculated output. To proof I just have an excel sheet where I input the weights,…
Israel
  • 3
  • 2
0
votes
1 answer

SVM outputting the same prediction value for every input... Why is that?

I use Encog and I use SVM for predict data. My training set values are not normalized but they are in [-1,1] range originally. I don't understand why the problem occurs. My training…
Marton Horvath
  • 31
  • 4
0
votes
1 answer

training Hopefield network with encog in java

I started working with this network. And I wrote some code, but I am not sure whether I am doing it right or not. here is what I do: First create the network HopefieldNetwork net = new HopefieldNetwork(50). Than add all patterns, with…
vfsoraki
  • 2,186
  • 1
  • 20
  • 45
0
votes
1 answer

Neural network for pattern recognition

I want you to help me figure out which problem am I dealing with (pattern recognition or time series forecasting) and find the best NN architecture suited for this problem. In my problem, I have many finite sets of two dimensional data (learning…
Tarik Mokafih
  • 1,247
  • 7
  • 19
  • 38
0
votes
2 answers

Using a Radial basis function with back propagation in c# using Encog library

I have created a simple RBF network with a gaussian function by using, RBFNetwork newNetwork = new RBFNetwork(28,14,1,RBFEnum.Gaussian); I need to create a RBF Network with back propagation having 28 inputs and only one output giving 0 or 1 as a…
Sujan
  • 1,542
  • 2
  • 22
  • 42
0
votes
1 answer

Neural network scaling input and descaling output

I have methods for scaling inputs and descaling outputs of NN that I found somewhere long time ago but I am not sure if they are valid,im using encog library for NN: public static double Scale(double X) { double fieldlow = 0; …
formatc
  • 4,261
  • 7
  • 43
  • 81
-1
votes
1 answer

Encog output have values less that 0

I try to train the network to classify texts. At the entrance I submit a vector only from 0 and 1. Everything works well :) Noticed that Compute returns a vector of negative values like {0.56, -0.09, -0.01}. There can be only one negative value or…
millworm
  • 3
  • 1
1 2 3
…
16
17