rmspropupdate

Update parameters using root mean squared propagation (RMSProp)

Since R2019b

Syntax

``[netUpdated,averageSqGrad] = rmspropupdate(net,grad,averageSqGrad)``
``[params,averageSqGrad] = rmspropupdate(params,grad,averageSqGrad)``
``[___] = rmspropupdate(___learnRate,sqGradDecay,epsilon)``

Description

Update the network learnable parameters in a custom training loop using the root mean squared propagation (RMSProp) algorithm.

Note

This function applies the RMSProp optimization algorithm to update network parameters in custom training loops. To train a neural network using the `trainnet` function using the RMSProp solver, use the `trainingOptions` function and set the solver to `"rmsprop"`.

example

````[netUpdated,averageSqGrad] = rmspropupdate(net,grad,averageSqGrad)` updates the learnable parameters of the network `net` using the RMSProp algorithm. Use this syntax in a training loop to iteratively update a network defined as a `dlnetwork` object.```

example

````[params,averageSqGrad] = rmspropupdate(params,grad,averageSqGrad)` updates the learnable parameters in `params` using the RMSProp algorithm. Use this syntax in a training loop to iteratively update the learnable parameters of a network defined using functions. ```

example

````[___] = rmspropupdate(___learnRate,sqGradDecay,epsilon)` also specifies values to use for the global learning rate, square gradient decay, and small constant epsilon, in addition to the input arguments in previous syntaxes. ```

Examples

collapse all

Perform a single root mean squared propagation update step with a global learning rate of `0.05` and squared gradient decay factor of `0.95`.

Create the parameters and parameter gradients as numeric arrays.

```params = rand(3,3,4); grad = ones(3,3,4);```

Initialize the average squared gradient for the first iteration.

`averageSqGrad = [];`

Specify custom values for the global learning rate and squared gradient decay factor.

```learnRate = 0.05; sqGradDecay = 0.95;```

Update the learnable parameters using `rmspropupdate`.

`[params,averageSqGrad] = rmspropupdate(params,grad,averageSqGrad,learnRate,sqGradDecay);`

Use `rmspropupdate` to train a network using the root mean squared propagation (RMSProp) algorithm.

```[XTrain,TTrain] = digitTrain4DArrayData; classes = categories(TTrain); numClasses = numel(classes);```

Define the Network

Define the network architecture and specify the average image value using the `Mean` option in the image input layer.

```layers = [ imageInputLayer([28 28 1],'Mean',mean(XTrain,4)) convolution2dLayer(5,20) reluLayer convolution2dLayer(3,20,'Padding',1) reluLayer convolution2dLayer(3,20,'Padding',1) reluLayer fullyConnectedLayer(numClasses) softmaxLayer];```

Create a `dlnetwork` object from the layer array.

`net = dlnetwork(layers);`

Define Model Loss Function

Create the helper function `modelLoss`, listed at the end of the example. The function takes a `dlnetwork` object and a mini-batch of input data with corresponding labels, and returns the loss and the gradients of the loss with respect to the learnable parameters.

Specify Training Options

Specify the options to use during training.

```miniBatchSize = 128; numEpochs = 20; numObservations = numel(TTrain); numIterationsPerEpoch = floor(numObservations./miniBatchSize);```

Train Network

`averageSqGrad = [];`

Calculate the total number of iterations for the training progress monitor.

`numIterations = numEpochs * numIterationsPerEpoch;`

Initialize the `TrainingProgressMonitor` object. Because the timer starts when you create the monitor object, make sure that you create the object close to the training loop.

`monitor = trainingProgressMonitor(Metrics="Loss",Info="Epoch",XLabel="Iteration");`

Train the model using a custom training loop. For each epoch, shuffle the data and loop over mini-batches of data. Update the network parameters using the `rmspropupdate` function. At the end of each iteration, display the training progress.

Train on a GPU, if one is available. Using a GPU requires Parallel Computing Toolbox™ and a supported GPU device. For information on supported devices, see GPU Computing Requirements (Parallel Computing Toolbox).

Train the network.

```iteration = 0; epoch = 0; while epoch < numEpochs && ~monitor.Stop epoch = epoch + 1; % Shuffle data. idx = randperm(numel(TTrain)); XTrain = XTrain(:,:,:,idx); TTrain = TTrain(idx); i = 0; while i < numIterationsPerEpoch && ~monitor.Stop i = i + 1; iteration = iteration + 1; % Read mini-batch of data and convert the labels to dummy % variables. idx = (i-1)*miniBatchSize+1:i*miniBatchSize; X = XTrain(:,:,:,idx); T = zeros(numClasses,miniBatchSize,"single"); for c = 1:numClasses T(c,TTrain(idx)==classes(c)) = 1; end % Convert mini-batch of data to a dlarray. X = dlarray(single(X),"SSCB"); % If training on a GPU, then convert data to a gpuArray. if canUseGPU X = gpuArray(X); end % Evaluate the model loss and gradients using dlfeval and the % modelLoss function. [loss,gradients] = dlfeval(@modelLoss,net,X,T); % Update the network parameters using the RMSProp optimizer. [net,averageSqGrad] = rmspropupdate(net,gradients,averageSqGrad); % Update the training progress monitor. recordMetrics(monitor,iteration,Loss=loss); updateInfo(monitor,Epoch=epoch + " of " + numEpochs); monitor.Progress = 100 * iteration/numIterations; end end```

Test the Network

Test the classification accuracy of the model by comparing the predictions on a test set with the true labels.

`[XTest,TTest] = digitTest4DArrayData;`

Convert the data to a `dlarray` with dimension format `"SSCB"`. For GPU prediction, also convert the data to a `gpuArray`.

```XTest = dlarray(XTest,"SSCB"); if canUseGPU XTest = gpuArray(XTest); end```

To classify images using a `dlnetwork` object, use the `predict` function and find the classes with the highest scores.

```YTest = predict(net,XTest); [~,idx] = max(extractdata(YTest),[],1); YTest = classes(idx);```

Evaluate the classification accuracy.

`accuracy = mean(YTest==TTest)`
```accuracy = 0.9926 ```

Model Loss Function

The helper function `modelLoss` takes a `dlnetwork` object `net` and a mini-batch of input data `X` with corresponding labels `T`, and returns the loss and the gradients of the loss with respect to the learnable parameters in `net`. To compute the gradients automatically, use the `dlgradient` function.

```function [loss,gradients] = modelLoss(net,X,T) Y = forward(net,X); loss = crossentropy(Y,T); gradients = dlgradient(loss,net.Learnables); end```

Input Arguments

collapse all

Network, specified as a `dlnetwork` object.

The function updates the `Learnables` property of the `dlnetwork` object. `net.Learnables` is a table with three variables:

• `Layer` — Layer name, specified as a string scalar.

• `Parameter` — Parameter name, specified as a string scalar.

• `Value` — Value of parameter, specified as a cell array containing a `dlarray`.

The input argument `grad` must be a table of the same form as `net.Learnables`.

Network learnable parameters, specified as a `dlarray`, a numeric array, a cell array, a structure, or a table.

If you specify `params` as a table, it must contain the following three variables.

• `Layer` — Layer name, specified as a string scalar.

• `Parameter` — Parameter name, specified as a string scalar.

• `Value` — Value of parameter, specified as a cell array containing a `dlarray`.

You can specify `params` as a container of learnable parameters for your network using a cell array, structure, or table, or nested cell arrays or structures. The learnable parameters inside the cell array, structure, or table must be `dlarray` or numeric values of data type `double` or `single`.

The input argument `grad` must be provided with exactly the same data type, ordering, and fields (for structures) or variables (for tables) as `params`.

The learnables can be complex-valued. (since R2024a) Ensure that the corresponding operations support complex-valued learnables.

Before R2024a: The learnables must not be complex-valued. If your model involves complex learnables, then convert the learnables to real values before calculating the gradients.

Gradients of the loss, specified as a `dlarray`, a numeric array, a cell array, a structure, or a table.

The exact form of `grad` depends on the input network or learnable parameters. The following table shows the required format for `grad` for possible inputs to `rmspropupdate`.

`net`Table `net.Learnables` containing `Layer`, `Parameter`, and `Value` variables. The `Value` variable consists of cell arrays that contain each learnable parameter as a `dlarray`. Table with the same data type, variables, and ordering as `net.Learnables`. `grad` must have a `Value` variable consisting of cell arrays that contain the gradient of each learnable parameter.
`params``dlarray``dlarray` with the same data type and ordering as `params`
Numeric arrayNumeric array with the same data type and ordering as `params`
Cell arrayCell array with the same data types, structure, and ordering as `params`
StructureStructure with the same data types, fields, and ordering as `params`
Table with `Layer`, `Parameter`, and `Value` variables. The `Value` variable must consist of cell arrays that contain each learnable parameter as a `dlarray`.Table with the same data types, variables, and ordering as `params`. `grad` must have a `Value` variable consisting of cell arrays that contain the gradient of each learnable parameter.

You can obtain `grad` from a call to `dlfeval` that evaluates a function that contains a call to `dlgradient`. For more information, see Use Automatic Differentiation In Deep Learning Toolbox.

The gradients can be complex-valued. (since R2024a) Using complex valued gradients can lead to complex-valued learnable parameters. Ensure that the corresponding operations support complex-valued learnables.

Before R2024a: The gradients must not be complex-valued. If your model involves complex numbers, then convert all outputs to real values before calculating the gradients.

Moving average of squared parameter gradients, specified as an empty array, a `dlarray`, a numeric array, a cell array, a structure, or a table.

The exact form of `averageSqGrad` depends on the input network or learnable parameters. The following table shows the required format for `averageSqGrad` for possible inputs to `rmspropupdate`.

`net`Table `net.Learnables` containing `Layer`, `Parameter`, and `Value` variables. The `Value` variable consists of cell arrays that contain each learnable parameter as a `dlarray`. Table with the same data type, variables, and ordering as `net.Learnables`. `averageSqGrad` must have a `Value` variable consisting of cell arrays that contain the average squared gradient of each learnable parameter.
`params``dlarray``dlarray` with the same data type and ordering as `params`
Numeric arrayNumeric array with the same data type and ordering as `params`
Cell arrayCell array with the same data types, structure, and ordering as `params`
StructureStructure with the same data types, fields, and ordering as `params`
Table with `Layer`, `Parameter`, and `Value` variables. The `Value` variable must consist of cell arrays that contain each learnable parameter as a `dlarray`.Table with the same data types, variables, and ordering as `params`. `averageSqGrad` must have a `Value` variable consisting of cell arrays that contain the average squared gradient of each learnable parameter.

If you specify `averageSqGrad` as an empty array, the function assumes no previous gradients and runs in the same way as for the first update in a series of iterations. To update the learnable parameters iteratively, use the `averageSqGrad` output of a previous call to `rmspropupdate` as the `averageSqGrad` input.

The gradients can be complex-valued. (since R2024a) Using complex valued gradients can lead to complex-valued learnable parameters. Ensure that the corresponding operations support complex-valued learnables.

Before R2024a: The gradients must not be complex-valued. If your model involves complex numbers, then convert all outputs to real values before calculating the gradients.

Global learning rate, specified as a positive scalar. The default value of `learnRate` is `0.001`.

If you specify the network parameters as a `dlnetwork`, the learning rate for each parameter is the global learning rate multiplied by the corresponding learning rate factor property defined in the network layers.

Squared gradient decay factor, specified as a positive scalar between `0` and `1`. The default value of `sqGradDecay` is `0.9`.

Small constant for preventing divide-by-zero errors, specified as a positive scalar. The default value of `epsilon` is `1e-8`.

Output Arguments

collapse all

Updated network, returned as a `dlnetwork` object.

The function updates the `Learnables` property of the `dlnetwork` object.

Updated network learnable parameters, returned as a `dlarray`, a numeric array, a cell array, a structure, or a table with a `Value` variable containing the updated learnable parameters of the network.

The learnables can be complex-valued. (since R2024a) Ensure that the corresponding operations support complex-valued learnables.

Before R2024a: The learnables must not be complex-valued. If your model involves complex learnables, then convert the learnables to real values before calculating the gradients.

Updated moving average of squared parameter gradients, returned as a `dlarray`, a numeric array, a cell array, a structure, or a table.

The gradients can be complex-valued. (since R2024a) Using complex valued gradients can lead to complex-valued learnable parameters. Ensure that the corresponding operations support complex-valued learnables.

Before R2024a: The gradients must not be complex-valued. If your model involves complex numbers, then convert all outputs to real values before calculating the gradients.

Algorithms

collapse all

Root Mean Square Propagation

Stochastic gradient descent with momentum uses a single learning rate for all the parameters. Other optimization algorithms seek to improve network training by using learning rates that differ by parameter and can automatically adapt to the loss function being optimized. Root mean square propagation (RMSProp) is one such algorithm. It keeps a moving average of the element-wise squares of the parameter gradients,

`${v}_{\ell }={\beta }_{2}{v}_{\ell -1}+\left(1-{\beta }_{2}\right){\left[\nabla E\left({\theta }_{\ell }\right)\right]}^{2}$`

β2 is the squared gradient decay factor of the moving average. Common values of the decay rate are 0.9, 0.99, and 0.999. The corresponding averaging lengths of the squared gradients equal 1/(1-β2), that is, 10, 100, and 1000 parameter updates, respectively. The RMSProp algorithm uses this moving average to normalize the updates of each parameter individually,

`${\theta }_{\ell +1}={\theta }_{\ell }-\frac{\alpha \nabla E\left({\theta }_{\ell }\right)}{\sqrt{{v}_{\ell }}+ϵ}$`

where the division is performed element-wise. Using RMSProp effectively decreases the learning rates of parameters with large gradients and increases the learning rates of parameters with small gradients. ɛ is a small constant added to avoid division by zero.

Version History

Introduced in R2019b

expand all