i want train neural network sine() function. currently use code , ( cerebrum gem): require 'cerebrum' input = array.new 300.times |i| inputh = hash.new inputh[:input]=[i] sinus = math::sin(i) inputh[:output] = [sinus] input.push(inputh) end network = cerebrum.new network.train(input, { error_threshold: 0.00005, iterations: 40000, log: true, log_period: 1000, learning_rate: 0.3 }) res = array.new 300.times |i| result = network.run([i]) res.push(result[0]) end puts "#{res}" but not work, if run trained network weird output values (instead of getting part of sine curve). so, doing wrong? cerebrum basic , slow nn implementation. there better options in ruby, such ruby-fann gem. most problem network simple. have not specified hidden layers - looks code assigns default hidden layer 3 neurons in case. try like: network = cerebrum.new({ learning_rate: 0.01, momentum: 0.9, hidden_l...
i have android project built in eclipse, , wish migrate android studio. though android studio works fine without gradle build files, want create them using eclipse adt explained here . however, when trying generate gradle files, eclipse shows me error log click on "finish". have tried decode means no avail. here error in question: java.lang.reflect.invocationtargetexception @ org.eclipse.jface.operation.modalcontext.runincurrentthread(modalcontext.java:477) @ org.eclipse.jface.operation.modalcontext.run(modalcontext.java:372) @ org.eclipse.jface.wizard.wizarddialog.run(wizarddialog.java:1028) @ com.android.ide.eclipse.adt.internal.wizards.exportgradle.gradleexportpage.generatebuildfiles(gradleexportpage.java:293) @ com.android.ide.eclipse.adt.internal.wizards.exportgradle.gradleexportwizard.performfinish(gradleexportwizard.java:32) @ org.eclipse.jface.wizard.wizarddialog.finishpressed(wizarddialog.java:827) @ org.eclipse.jface.wizard.wizarddialog.buttonpressed(wizar...
Comments
Post a Comment