使用多种训练方法通过 Encog 训练 ANN

Question

我想知道在使用弹性传播训练之前使用遗传算法、粒子群优化和模拟退火训练前馈神经网络是否会改善结果。

这是我使用的代码：

                    CalculateScore score = new TrainingSetScore(trainingSet);
                    StopTrainingStrategy stop = new StopTrainingStrategy();
                    StopTrainingStrategy stopGA = new StopTrainingStrategy();
                    StopTrainingStrategy stopSIM = new StopTrainingStrategy();
                    StopTrainingStrategy stopPSO = new StopTrainingStrategy();

                    Randomizer randomizer = new NguyenWidrowRandomizer();
                    //Backpropagation train = new Backpropagation((BasicNetwork) network, trainingSet, 0.2, 0.1);
                    //  LevenbergMarquardtTraining train = new LevenbergMarquardtTraining((BasicNetwork) network, trainingSet);
                    int population = 500;
                    MLTrain trainGA =  new MLMethodGeneticAlgorithm(new MethodFactory(){
                        @Override
                        public MLMethod factor() {
                            final BasicNetwork result = createNetwork();
                            ((MLResettable)result).reset();
                            return result;
                        }}, score,population);


                    Date dStart = new Date();

                    int epochGA = 0;
                    trainGA.addStrategy(stopGA);
                    do{
                        trainGA.iteration();
                        if(writeOnStdOut)
                            System.out.println("Epoch Genetic #" + epochGA + " Error:" + trainGA.getError());
                        epochGA++;//0000001
                        previousError = trainGA.getError();
                        Date dtemp = new Date();
                        totsecs = ((double)(dtemp.getTime()-dStart.getTime())/1000);
                    } while(previousError > maximumAcceptedErrorTreshold && epochGA < (maxIterations/5) && !stopGA.shouldStop()  && totsecs < (secs/3));

                    NeuralPSO trainPSO = new NeuralPSO((BasicNetwork) network, randomizer, score, 100);

                    int epochPSO = 0;
                    trainPSO.addStrategy(stopPSO);
                     dStart = new Date();
                    do{
                        trainPSO.iteration();
                        if(writeOnStdOut)
                            System.out.println("Epoch Particle Swarm #" + epochPSO + " Error:" + trainPSO.getError());
                        epochPSO++;//0000001
                        previousError = trainPSO.getError();
                        Date dtemp = new Date();
                        totsecs = ((double)(dtemp.getTime()-dStart.getTime())/1000);
                    } while(previousError > maximumAcceptedErrorTreshold && epochPSO < (maxIterations/5) && !stopPSO.shouldStop() && totsecs < (secs/3));

                    MLTrain trainSIM = new NeuralSimulatedAnnealing((MLEncodable) network, score, startTemperature, stopTemperature, cycles);

                    int epochSA = 0;
                    trainSIM.addStrategy(stopSIM);
                    dStart = new Date();
                    do{
                        trainSIM.iteration();
                        if(writeOnStdOut)
                            System.out.println("Epoch Simulated Annealing #" + epochSA + " Error:" + trainSIM.getError());
                        epochSA++;//0000001
                        previousError = trainSIM.getError();
                        Date dtemp = new Date();
                        totsecs = ((double)(dtemp.getTime()-dStart.getTime())/1000);
                    } while(previousError > maximumAcceptedErrorTreshold && epochSA < (maxIterations/5) && !stopSIM.shouldStop() && totsecs < (secs/3));




                    previousError = 0;
                    BasicTraining train = getTraining(method,(BasicNetwork) network, trainingSet);


                    //train.addStrategy(new Greedy());
                    //trainAlt.addStrategy(new Greedy());
                    HybridStrategy strAnneal = new HybridStrategy(trainSIM);

                    train.addStrategy(strAnneal);
                    //train.addStrategy(strGenetic);
                    //train.addStrategy(strPSO);

                    train.addStrategy(stop);
                    // 
                    //  Backpropagation train = new Backpropagation((ContainsFlat) network, trainingSet, 0.7, 0.3);
                    dStart = new Date();

                    int epoch = 1;

                    do {
                        train.iteration();
                        if(writeOnStdOut)
                            System.out.println("Epoch #" + epoch + " Error:" + train.getError());
                        epoch++;//0000001
                        if(Math.abs(train.getError()-previousError)<0.0000001) iterationWithoutImprovement++; else iterationWithoutImprovement = 0;
                        previousError = train.getError();

                        Date dtemp = new Date();
                        totsecs = ((double)(dtemp.getTime()-dStart.getTime())/1000);
                    } while(previousError > maximumAcceptedErrorTreshold && epoch < maxIterations && !stop.shouldStop() && totsecs < secs);//&& iterationWithoutImprovement < maxiter);

如您所见，应该改进整体训练的一系列训练算法。

请让我知道它是否有意义以及代码是否正确。它似乎在工作，但我想确定，因为有时我看到 GA 取得的进展是从 PSO 重置的。

谢谢

Answer 1

这似乎合乎逻辑，但行不通。

使用 RPROP 的默认参数，此序列不太可能起作用。原因是在您之前的训练之后，神经网络的权重将接近局部最优值。由于接近局部最优值，仅对权重进行微小的更改就会更接近最优值（降低错误率）。默认情况下，RPROP 在权重矩阵中使用 0.1 的 initialUpdate 值。对于如此接近最佳状态的网络来说，这是一个巨大的价值。你是"unleashing a bull in a china shop at this point"。第一次迭代将使网络远离最佳状态，并且实质上将开始新的全局搜索。

降低 initialUpdate 值应该会有帮助。我不确定有多少。您可能想用您的数据查看火车的平均 RPROP 权重更新值以获得一个想法。或者尝试将它设置得非常小，然后按照自己的方式进行备份。

使用多种训练方法通过 Encog 训练 ANN

Use multiple training methods to train a ANN with Encog

simulated-annealing

neural-network

genetic-algorithm

particle-swarm

encog