org.neuroph.util.benchmark
Class MyBenchmarkTask

java.lang.Object
  extended by org.neuroph.util.benchmark.BenchmarkTask
      extended by org.neuroph.util.benchmark.MyBenchmarkTask

public class MyBenchmarkTask
extends BenchmarkTask

This class is example of custom benchmarking task for Multi Layer Perceptorn network Note that this benchmark only measures the speed at implementation level - the speed of data flow forward and backward through network

Author:
Zoran Sevarac

Constructor Summary
MyBenchmarkTask(String name)
           
 
Method Summary
 void prepareTest()
          Benchmrk preparation consists of training set and neural networ creatiion.
 void runTest()
          This method should hold the code to benchmark
 
Methods inherited from class org.neuroph.util.benchmark.BenchmarkTask
getName, getTestIterations, getWarmupIterations, setName, setTestIterations, setWarmupIterations
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

MyBenchmarkTask

public MyBenchmarkTask(String name)
Method Detail

prepareTest

public void prepareTest()
Benchmrk preparation consists of training set and neural networ creatiion. This method generates training set with 100 rows, where every row has 10 input and 5 output elements Neural network has two hiddden layers with 8 and 7 neurons, and runs learning rule for 2000 iterations

Specified by:
prepareTest in class BenchmarkTask

runTest

public void runTest()
Description copied from class: BenchmarkTask
This method should hold the code to benchmark

Specified by:
runTest in class BenchmarkTask


Copyright © 2012. All Rights Reserved.