MATLAB: Evaluating all NeuralNetworks in a cell array simultanously

cell arraysMATLABneural network

Hi,

i have cell array of neural networks, which are all trained.

I now want to feed one inpuct vector into all of those NN (it's the same input values for all NNs), but it needs to be done as quickly as possible as I am working on a realtime application. Does anyone have an idea about how to do that without looping through the single networks? Or possibly a different approach than saving the networks in a cell array?

Thanks in advance!

Best Answer

Hi,

You can make use of the parfor to speed up the process.

The links given below will give in detailed explanation on how to make best use of parfor

https://www.mathworks.com/help/deeplearning/examples/use-parfor-to-train-multiple-deep-learning-networks.html

https://www.mathworks.com/help/parallel-computing/examples/train-deep-learning-networks-in-parallel.html

Even though the given examples are for training. You can use the case just for validatation.

Hope this helps!

Related Solutions

MATLAB: In Neural Network Toolbox, how can I can change the values of training Parameters

You cannot customize a lot with App. If you want to train not with default values, change values/parameters on code.

After the training on Neural Pattern Recognition App, click Next until getting to the Save Results page.

Click "Simple Script."

When you want to use the training function that uses learning rate and momentum, use traingdx. (If it is only learning rate, use traingda; if it is only momentum, use traingdm)

In the generated script, there is a line defining the training function such as:

>> trainFcn = 'trainscg';

Change this to, for example:

>> trainFcn = 'traingdx';

If you want to change the parameter of learning rate to 0.1 for example, add

>> net.trainParam.lr = 0.1;

after making the default network, which is the line include PATTERNNET as well as before TRAIN. You can also change the momentum by changing net.trainParam.mc.

MATLAB: Neural Network in Matlab App Designer

Yes, Neural Network (both shallow and deep neural networks) works with applications created by AppDesigner both for training and predict. Could you specify your use case, if possible?

Best Answer

Related Solutions

MATLAB: In Neural Network Toolbox, how can I can change the values of training Parameters

MATLAB: Neural Network in Matlab App Designer

Related Question