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 mac el capitan, 10.11.5, used rweka package, downloaded correctly , initialized error, when apply j48(species ~ ., data = iris) i have error error in .jnew("weka/core/attribute", attname[i], .jcast(levels, "java/util/list")) : java.lang.unsupportedclassversionerror: weka/core/attribute : unsupported major.minor version 51.0 i used java version these details, 52f85:~ kameljabreen$ java -version java version "1.7.0_79" java(tm) se runtime environment (build 1.7.0_79-b15) java hotspot(tm) 64-bit server vm (build 24.79-b02, mixed mode) please me solve problems, problm since 1 month, read lot problem in web sites. did thing, installing java jdk version 1.8 .... ect. used java 1.7. please give me solutions. in advance the rweka package depends on rjava package r-to-java communication, includes , uses own java 1.6 runtime. make things worse, behavior of rjava package platform dependent - uses "built-in" java on p...
Comments
Post a Comment