Main Content

train

Train shallow neural network

collapse all in page

Syntax

trainedNet = train(net,X,T,Xi,Ai,EW)
[trainedNet,tr] = train(net,X,T,Xi,Ai,EW)
[trainedNet,tr] = train(net,X,T,Xi,Ai,EW,Name,Value)

Description

This function trains a shallow neural network. For deep learning with convolutional or LSTM neural networks, seetrainNetworkinstead.

example

trainedNet= train(net,X,T,Xi,Ai,EW)trains a networknetaccording tonet.trainFcnandnet.trainParam.

[trainedNet,tr] = train(net,X,T,Xi,Ai,EW)also returns a training record.

example

[trainedNet,tr] = train(net,X,T,Xi,Ai,EW,Name,Value)trains a network with additional options specified by one or more name-value pair arguments.

Examples

collapse all

Here inputxand targetstdefine a simple function that you can plot:

x = [0 1 2 3 4 5 6 7 8]; t = [0 0.84 0.91 0.14 -0.77 -0.96 -0.28 0.66 0.99]; plot(x,t,'o')

Herefeedforwardnetcreates a two-layer feed-forward network. The network has one hidden layer with ten neurons.

net = feedforwardnet(10); net = configure(net,x,t); y1 = net(x) plot(x,t,'o',x,y1,'x')

The network is trained and then resimulated.

net = train(net,x,t); y2 = net(x) plot(x,t,'o',x,y1,'x',x,y2,'*')

This example trains an open-loop nonlinear-autoregressive network with external input, to model a levitated magnet system defined by a control currentxand the magnet’s vertical position responset, then simulates the network. The functionpreparetsprepares the data before training and simulation. It creates the open-loop network’s combined inputsxo, which contains both the external inputxand previous values of positiont. It also prepares the delay statesxi.

[x,t] = maglev_dataset; net = narxnet(10); [xo,xi,~,to] = preparets(net,x,{},t); net = train(net,xo,to,xi); y = net(xo,xi)

This same system can also be simulated in closed-loop form.

netc = closeloop(net); view(netc) [xc,xi,ai,tc] = preparets(netc,x,{},t); yc = netc(xc,xi,ai);

Parallel Computing Toolbox™ allows Deep Learning Toolbox™ to simulate and train networks faster and on larger datasets than can fit on one PC. Parallel training is currently supported for backpropagation training only, not for self-organizing maps.

Here training and simulation happens across parallel MATLAB workers.

parpool [X,T] = vinyl_dataset; net = feedforwardnet(10); net = train(net,X,T,'useParallel','yes','showResources','yes'); Y = net(X);

Use Composite values to distribute the data manually, and get back the results as a Composite value. If the data is loaded as it is distributed then while each piece of the dataset must fit in RAM, the entire dataset is limited only by the total RAM of all the workers.

[X, T] = vinyl_dataset; Q = size(X,2); Xc = Composite; Tc = Composite; numWorkers = numel(Xc); ind = [0 ceil((1:numWorkers)*(Q/numWorkers))];fori=1:numWorkers indi = (ind(i)+1):ind(i+1); Xc{i} = X(:,indi); Tc{i} = T(:,indi);endnet = feedforwardnet; net = configure(net,X,T); net = train(net,Xc,Tc); Yc = net(Xc);

Note in the example above the function configure was used to set the dimensions and processing settings of the network's inputs. This normally happens automatically when train is called, but when providing composite data this step must be done manually with non-Composite data.

Networks can be trained using the current GPU device, if it is supported by Parallel Computing Toolbox. GPU training is currently supported for backpropagation training only, not for self-organizing maps.

[X, T] = vinyl_dataset; net = feedforwardnet(10); net = train(net,X,T,'useGPU','yes'); y = net(X);

To put the data on a GPU manually:

[X, T] = vinyl_dataset; Xgpu = gpuArray(X); Tgpu = gpuArray(T); net = configure(net,X,T); net = train(net,Xgpu,Tgpu); Ygpu = net(Xgpu); Y = gather(Ygpu);

Note in the example above the function configure was used to set the dimensions and processing settings of the network's inputs. This normally happens automatically when train is called, but when providing gpuArray data this step must be done manually with non-gpuArray data.

To run in parallel, with workers each assigned to a different unique GPU, with extra workers running on CPU:

net = train(net,X,T,'useParallel','yes','useGPU','yes'); y = net(X);

Using only workers with unique GPUs might result in higher speed, as CPU workers might not keep up.

net = train(net,X,T,'useParallel','yes','useGPU','only'); Y = net(X);

Here a network is trained with checkpoints saved at a rate no greater than once every two minutes.

[x,t] = vinyl_dataset; net = fitnet([60 30]); net = train(net,x,t,'CheckpointFile','MyCheckpoint','CheckpointDelay',120);

After a computer failure, the latest network can be recovered and used to continue training from the point of failure. The checkpoint file includes a structure variablecheckpoint, which includes the network, training record, filename, time, and number.

[x,t] = vinyl_dataset; loadMyCheckpointnet = checkpoint.net; net = train(net,x,t,'CheckpointFile','MyCheckpoint');

Another use for the checkpoint feature is when you stop a parallel training session (started with the'UseParallel'parameter) even though the Neural Network Training Tool is not available during parallel training. In this case, set a'CheckpointFile', use Ctrl+C to stop training any time, then load your checkpoint file to get the network and training record.

Input Arguments

collapse all

Input network, specified as anetworkobject. To create anetworkobject, use for example,feedforwardnetornarxnet.

Network inputs, specified as anR-by-Qmatrix or anNi-by-TScell array, where

  • Ris the input size

  • Qis the batch size

  • Ni = net.numInputs

  • TSis the number of time steps

trainarguments can have two formats: matrices, for static problems and networks with single inputs and outputs, and cell arrays for multiple timesteps and networks with multiple inputs and outputs.

  • The matrix format can be used if only one time step is to be simulated (TS = 1)。它是方便网络只有一个输入ut and output, but can be used with networks that have more. When the network has multiple inputs, the matrix size is (sum ofRi)-by-Q.

  • The cell array format is more general, and more convenient for networks with multiple inputs and outputs, allowing sequences of inputs to be presented. Each elementX{i,ts}is anRi-by-Qmatrix, whereRi = net.inputs{i}.size.

If Composite data is used, then'useParallel'is automatically set to'yes'. The function takes Composite data and returns Composite results.

If gpuArray data is used, then'useGPU'is automatically set to'yes'. The function takes gpuArray data and returns gpuArray results

Note

If a column of X contains at least oneNaN,traindoes not use that column for training, testing, or validation.

Network targets, specified as aU-by-Qmatrix or anNo-by-TScell array, where

  • Uis the output size

  • Qis the batch size

  • No = net.numOutputs

  • TSis the number of time steps

trainarguments can have two formats: matrices, for static problems and networks with single inputs and outputs, and cell arrays for multiple timesteps and networks with multiple inputs and outputs.

  • The matrix format can be used if only one time step is to be simulated (TS = 1)。它是方便网络只有一个输入ut and output, but can be used with networks that have more. When the network has multiple inputs, the matrix size is (sum ofUi)-by-Q.

  • The cell array format is more general, and more convenient for networks with multiple inputs and outputs, allowing sequences of inputs to be presented. Each elementT{i,ts}is aUi-by-Qmatrix, whereUi = net.outputs{i}.size.

If Composite data is used, then'useParallel'is automatically set to'yes'. The function takes Composite data and returns Composite results.

If gpuArray data is used, then'useGPU'is automatically set to'yes'. The function takes gpuArray data and returns gpuArray results

Note thatTis optional and need only be used for networks that require targets.

Note

AnyNaNvalues in the targetsTare treated as missing data. If an element ofTisNaN, that element is not used for training, testing, or validation.

Initial input delay conditions, specified as anNi-by-IDcell array or anR-by-(ID*Q)matrix, where

  • ID = net.numInputDelays

  • Ni = net.numInputs

  • Ris the input size

  • Qis the batch size

For cell array input, the columns ofXiare ordered from the oldest delay condition to the most recent:Xi{i,k}is the inputiat timets = k - ID.

Xiis also optional and need only be used for networks that have input or layer delays.

Initial layer delay conditions, specified as aNl-by-LDcell array or a (sum ofSi)-by-(LD*Q) matrix, where

  • Nl = net.numLayers

  • LD = net.numLayerDelays

  • Si = net.layers{i}.size

  • Qis the batch size

For cell array input, the columns ofAiare ordered from the oldest delay condition to the most recent:Ai{i,k}is the layer outputiat timets = k - LD.

Error weights, specified as aNo-by-TScell array or a (sum ofUi)-by-Qmatrix, where

  • No = net.numOutputs

  • TSis the number of time steps

  • Ui = net.outputs{i}.size

  • Qis the batch size

For cell array input. each element电子战{我,ts}is aUi-by-Qmatrix, where

  • Ui = net.outputs{i}.size

  • Qis the batch size

The error weightsEWcan also have a size of 1 in place of all or any ofNo,TS,UiorQ. In that case,EWis automatically dimension extended to match the targetsT. This allows for conveniently weighting the importance in any dimension (such as per sample) while having equal importance across another (such as time, withTS=1)。If all dimensions are 1, for instance ifEW = {1}, then all target values are treated with the same importance. That is the default value ofEW.

As noted above, the error weightsEWcan be of the same dimensions as the targetsT, or have some dimensions set to 1. For instance ifEWis 1-by-Q, then target samples will have different importances, but each element in a sample will have the same importance. IfEWis (sum ofUi)-by-1, then each output element has a different importance, with all samples treated with the same importance.

Name-Value Arguments

Specify optional comma-separated pairs ofName,Valuearguments.Nameis the argument name andValueis the corresponding value.Namemust appear inside quotes. You can specify several name and value pair arguments in any order asName1,Value1,...,NameN,ValueN.

Example:'useParallel','yes'

Option to specify parallel calculations, specified as'yes'or'no'.

  • 'no'– Calculations occur on normal MATLAB thread. This is the default'useParallel'setting.

  • 'yes'– Calculations occur on parallel workers if a parallel pool is open. Otherwise calculations occur on the normal MATLAB®thread.

Option to specify GPU calculations, specified as'yes','no', or'only'.

  • 'no'– Calculations occur on the CPU. This is the default'useGPU'setting.

  • 'yes'– Calculations occur on the currentgpuDeviceif it is a supported GPU (See Parallel Computing Toolbox for GPU requirements.) If the currentgpuDeviceis not supported, calculations remain on the CPU. If'useParallel'is also'yes'and a parallel pool is open, then each worker with a unique GPU uses that GPU, other workers run calculations on their respective CPU cores.

  • 'only'– If no parallel pool is open, then this setting is the same as'yes'. If a parallel pool is open then only workers with unique GPUs are used. However, if a parallel pool is open, but no supported GPUs are available, then calculations revert to performing on all worker CPUs.

Option to show resources, specified as'yes'or'no'.

  • 'no'– Do not display computing resources used at the command line. This is the default setting.

  • 'yes'– Show at the command line a summary of the computing resources actually used. The actual resources may differ from the requested resources, if parallel or GPU computing is requested but a parallel pool is not open or a supported GPU is not available. When parallel workers are used, each worker’s computation mode is described, including workers in the pool that are not used.

Memory reduction, specified as a positive integer.

For most neural networks, the default CPU training computation mode is a compiled MEX algorithm. However, for large networks the calculations might occur with a MATLAB calculation mode. This can be confirmed using'showResources'. If MATLAB is being used and memory is an issue, setting the reduction option to a value N greater than 1, reduces much of the temporary storage required to train by a factor of N, in exchange for longer training times.

Checkpoint file, specified as a character vector.

The value for'CheckpointFile'can be set to a filename to save in the current working folder, to a file path in another folder, or to an empty string to disable checkpoint saves (the default value).

Checkpoint delay, specified as a nonnegative integer.

The optional parameter'CheckpointDelay'limits how often saves happen. Limiting the frequency of checkpoints can improve efficiency by keeping the amount of time saving checkpoints low compared to the time spent in calculations. It has a default value of 60, which means that checkpoint saves do not happen more than once per minute. Set the value of'CheckpointDelay'to 0 if you want checkpoint saves to occur only once every epoch.

Output Arguments

collapse all

Trained network, returned as anetworkobject.

Training record (epochandperf), returned as a structure whose fields depend on the network training function (net.NET.trainFcn)。It can include fields such as:

  • Training, data division, and performance functions and parameters

  • Data division indices for training, validation and test sets

  • Data division masks for training validation and test sets

  • Number of epochs (num_epochs) and the best epoch (best_epoch)

  • A list of training state names (states)

  • Fields for each state name recording its value throughout training

  • Best performances of the network, evaluated at each epoch: best performance on the training set (best_perf), best performance on the validation set (best_vperf), and best performance on the test set (best_tperf)

Algorithms

traincalls the function indicated bynet.trainFcn, using the training parameter values indicated bynet.trainParam.

Typically one epoch of training is defined as a single presentation of all input vectors to the network. The network is then updated according to the results of all those presentations.

Training occurs until a maximum number of epochs occurs, the performance goal is met, or any other stopping condition of the functionnet.trainFcnoccurs.

Some training functions depart from this norm by presenting only one input vector (or sequence) each epoch. An input vector (or sequence) is chosen randomly for each epoch from concurrent input vectors (or sequences).competlayerreturns networks that usetrainru, a training function that does this.

See Also

|||

Introduced before R2006a

Deep Learning Toolbox Documentation

金宝app

Introducing Deep Learning with MATLAB

Introducing Deep Learning with MATLAB

Download ebook