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
2
votes
2 answers

import encog examples into eclipse

I am trying to import encog example into eclipse. encog is basically a java library to implement neural network and another machine learning algorithm but I am keep getting the error: Description Resource Path Location Type Project…
java bigner
  • 41
  • 3
2
votes
1 answer

Encog SVM won't train

I am trying to train a SVM to classify two spiral data. My input is a 3 column CSV file, the first two columns are the (x, y)-coordinates of a point on a spiral (not normalised) and the third column is the spiral (class) that the point belongs to. I…
Bidski
  • 435
  • 1
  • 4
  • 6
2
votes
1 answer

encog java exporting network weights

I am using encog to do some of my university assignments and I would like to export a list of all the connections in the networks and their associated weights. I saw the dumpWeights() function that is part of the BasicMLNetwork class (im using…
Bidski
  • 435
  • 1
  • 4
  • 6
2
votes
2 answers

Best number of neurons in hidden layer of Encog neural network

i have a neural network with a structure: 7 input neurons, 3 output neurons. On the internet it was said that the best results are usully achieved when the number of neurons on the hidden layer is 1.5 - 2 times as big as the number of neurons in…
Alex
  • 4,607
  • 9
  • 61
  • 99
2
votes
1 answer

Does Encog has good perfomance at multisocket motherboards with multiple processors?

Encog has multithreading support. But as far as I understand, it's good in paralleling at one processor with for example 8 cores. Will it work faster, if I'll buy motherboard with 4 sockets, and install there four Intel Xeon E5-4600? Does anybody…
Yuriy Zaletskyy
  • 4,983
  • 5
  • 34
  • 54
2
votes
1 answer

Encog CSV Loading Exception: "Can't access column 15 in a file that has only 15 columns."

Using encog-core-cs, whose assembly info reports is 3.3.0.0. When I EncogUtility.LoadCSV2Memory() the call fails with the message described in the Title here. I am providing LoadCSV2Memory() with what appears to be a properly normalized csv file,…
user74754
2
votes
1 answer

OCR using a Neural Network

I'm working my way toward understanding the usage of a NN in order to perform OCR, my goal is a bit different than the usual OCR algorithms. My objective is to be able to determine if a specific input is a specific letter, for example I'm expecting…
Aviran
  • 5,160
  • 7
  • 44
  • 76
2
votes
1 answer

Neural network with custom error function

I am developing a forecasting application with the use of feedforward networks. The problem I have, is that data I would like to forecast is mostly trended. Therfore, a model I am trying to develop is following: y_model = f(x) + g(t) Where x is…
Kędrzu
  • 2,385
  • 13
  • 22
2
votes
1 answer

How to recognize Array pattern with C# Encog

I made an Encog based ANN to recognize material's spectrum. I train the network passing more spectrum into matrix. Example: input[0] = material 0 input[1] = material 1 Each vector is of 10000 element, After the training I want recognize one of…
Antonio
  • 1,181
  • 4
  • 15
  • 34
2
votes
1 answer

Training and Validating Correctly With Encog

I think I'm doing something wrong with Encog. In all of the examples I've seen, they simply TRAIN until a certain training error is reached and then print the results. When is the gradient calculated and the weights of the hidden layers updated? …
poorly_built_human
  • 55
  • 6
2
votes
2 answers

Neural Network Outputs Are Not Changing Very Much

I have 20 output neurons on a feed-forward neural network, for which I have already tried varying the number of hidden layers and number of neurons per hidden layer. When testing, I've noticed that while the outputs are not always exactly the…
poorly_built_human
  • 55
  • 6
2
votes
1 answer

Encog query classification

I'm trying to process this dataset using Encog. In order to do so, I combined the outputs into one (can't seem to figure out how to use multiple expected outputs, even tho I unsuccessfully tried to manually train a NN with 4 output neurons) with the…
gcandal
  • 937
  • 8
  • 23
2
votes
1 answer

Using neural network with true and false outputs

Since I'm new to neural network, there is a few questions I would like to ask to understand it more clearly. Q1: I would like to test for true/false results (pattern recognition), so does it mean that my output layer will have 2 neutrons? Q2:…
Xitrum
  • 7,765
  • 26
  • 90
  • 126
2
votes
1 answer

Encog Framework not giving acceptable error rate

I have a very small dataset, only 200 rows. I have only 3 columns; the first two are numeric (negative and positive) and the last is letter. I am attempting to classify the last column based on the first two numeric columns. My comma separated…
user1477388
  • 20,790
  • 32
  • 144
  • 264
2
votes
0 answers

Encog : Reinforcement Learning / Actor-Critic Model

I have a basic neural net problem where I want a "rocket" to maintain it's altitude at a given height. (This is a simple version of the problem, it will get more complex). I am using the encog platform and it isn't clear how to use it to implement…
Josh T
  • 564
  • 3
  • 12
1 2 3
…
16 17