Neural Network

Convolutional neural networks About convolution can be abstracted into mathematical expressions: I can represent the matrix of an image, K is the convolution kernel The computational layer of the convolution Object Recogition with Gradient-Based Learning input layer Input Layer Convolution Layer Conv Layer Restricted Layer RELU Layer pooling layer Pooling Layer full connected layer Creating a network Basic learning to distinguish between dogs and cats (* Create model *) myCatDogModel = NetChain[{ ConvolutionLayer[32, 3], Ramp, PoolingLayer[2, 2], ConvolutionLayer[64, 3], Ramp, PoolingLayer[2, 2], FlattenLayer[], 128, Ramp, 2, SoftmaxLayer[]}, "Input" -> NetEncoder[{"Image", {224, 224}, ColorSpace -> "RGB"}] , "Output" -> NetDecoder[{"Class", {"cat", "dog"}}]] (* Collect samples, training set and test set *) (* Convert data sets to Association format *) dataSetsConvert[dateSets_] := Module[ {}, File[#] -> StringSplit[FileBaseName[#], "."] [[1]] & /@ dateSets] traingDataFiles = RandomSample[dataSetsConvert[traingData]]; testDataFiles = RandomSample[dataSetsConvert[testData]]; SetDirectory[ "/Users/alexchen/datasets/Convolutional_Neural_Networks/dataset"]; FileNames["*.jpg", "training_set/cats/"]; FileNames["*.jpg", "training_set/dogs/"]; traingData = Join[FileNames["*.jpg", "training_set/cats/"], FileNames["*.jpg", "training_set/dogs/"]]; testData = Join[FileNames["*.jpg", "test_set/cats"], FileNames["*.jpg", "test_set/dogs"]]; (* Generate training and validation sets *) traingDataFiles = RandomSample[dataSetsConvert[traingData]]; testDataFiles = RandomSample[dataSetsConvert[testData]]; (* sample is randomly selected for display *) RandomSample[traingDataFiles, 5] (* train the model *) mytrainedModel = NetTrain[catdogModel, traingDataFiles, All, ValidationSet -> testDataFiles, MaxTrainingRounds -> 20] (* Generate training model evaluation report *) myModelPlot = mytrainedModel["FinalPlots"] (* Generate the trained model to calculate the model correctness *) myTrainedNet = mytrainedModel["TrainedNet"] ClassifierMeasurements[myTrainedNet, testDataFiles, "Accuracy"] ...

关于人工神经网络 人工神经网络模型判断手写数字 我们首先在Mathematica中徒手打造一个人工神经网络，然后对该神经网络进行训练，最后用训练得到的模型来判断图片上的手写数字是多少。 trainingData = ResourceData["MNIST", "TrainingData"]; testData = ResourceData["MNIST", "TestData"]; net = NetInitialize@NetChain[{ FlattenLayer[], LinearLayer[500], ElementwiseLayer["Sigmoid"], LinearLayer[100], ElementwiseLayer["Sigmoid"], LinearLayer[10], SoftmaxLayer[]}, "Input" -> NetEncoder[{"Image", {12, 12}, "ColorSpace" -> "Grayscale"}], "Output" -> NetDecoder[{"Class", Range[0, 9]}]] NetEncoder告诉我们输入的单通道12*12的图像 NetDecoder告诉我们我们的神经网络模型最后输出的是一个分类，类别分别是0-9中的一个数字 网络层的模型为： FlattenLayer[] 图像中的像素数据即两纬数据排列成一纬数据做为输入 LinearLayer[500] 第一层线性层，输出数据为500个，限定函数为Sigmoid LinearLayer[100] 第二层线性层，输出数据为100个，限定函数为Sigmoid LinearLayer[10] 最后一层输出，因为我们需要有10个分类，所以这里设定是10，限定函数为 Softmax 神经网络层形象的展示如下: 训练数据标记，左边是实际的手写数字，右边是对应标签 RandomSample[trainingData, 10] 在未对模型进行训练前，使用随机的权重来判断图片，我们可以确定错误率接近100% 对模型进行训练 trained = NetTrain[net, trainingData, ValidationSet -> testData, MaxTrainingRounds -> 50 ] 从以上图表中我们大致可以看出正确率已经接近97% 再次预测上述图片，模型已经可以正确预测给出的图片数字为6 measurements = ClassifierMeasurements[trained, testData] 运行 measurements[“Accuracy”] 我们可以得到模型的正确率为98.02% ...