dfnn matlab,Matlab NN Toolbox [教程].ppt

朴灿烈づ我的快乐病毒、 2023-01-14 04:51 168阅读 0赞

Matlab NN Toolbox \[教程\]

Matlab NN Toolbox / Implementation 1. Loading data source. 2. Selecting attributes required. 3. Decide training, validation, and testing data. 4. Data manipulations and Target generation. (for supervised learning) 5. Neural Network creation (selection of network architecture) and initialisation. 6. Network Training and Testing. 7. Performance evaluation. Loading and Saving data load: retrieve data from disk. In ascii or .mat format. Matrix manipulation region = data(:,1); training = data(\[1:500\],:) w=\[1;2\]; w\*w’ => \[1,2;2,4\]; w=\[1,2;2,4\]; w.\*w => \[1,4;4,16\]; Plotting Data Network creation Network creation (cont.) Network Initialisation Initialise the net’s weighting and biases >> net = init(net);% init is called after newff re-initialise with other function: net.layers\{1\}.initFcn = 'initwb'; net.inputWeights\{1,1\}.initFcn = 'rands'; net.biases\{1,1\}.initFcn = 'rands'; net.biases\{2,1\}.initFcn = 'rands'; Neurons activation Network Training The overall architecture of your neural network is store in the variable net; variable can be reset. net.trainParam parameters: epochs: 100 goal: 0 max\_fail: 5 mem\_reduc: 1 min\_grad: 1.0000e-010 mu: 0.0010 mu\_dec: 0.1000 mu\_inc: 10 mu\_max: 1.0000e+010 show: 25 time: Inf net.trainFcn options net.trainFcn=trainlm ; a variant of BP based on second order algorithm (Levenberg-Marquardt) Network Training(cont.) >> TRAIN(NET,P,T,Pi,Ai) NET - Network. P - Network inputs. T - Network targets, default = zeros. Pi - Initial input delay conditions, default = zeros. Ai - Initial layer delay conditions, default = zeros. Network Training(cont.) >>TRAIN(NET,P,T,Pi,Ai) NET - Network. P - Network inputs. T - Network targets, default = zeros. (optional only for NN with targets) Pi - Initial input delay conditions, default = zeros. Ai - Initial layer delay conditions, default = zeros. Simulation of the