How can I use gensim neural network generated block for online training the network in simulink?

Hi,

I want to deploy online system identification using NN in Simulink using the NARX model, but I do not know how to train a network online in Simulink. By the way, I think the NN block, which can be created using the gensim function, is just a pretrained network and can not be trained online. How can I make NN that can be trained online in Simulink?

Answer 1

[Ayush Aniket]

There are three ways in which you can train a neural network online in Simulink for system identification using the NARX model:

1. MATLAB's System Identification Toolbox allows online training of nonlinear models, including NARX networks. You can use the Nonlinear ARX model with adaptive learning to update parameters dynamically. Refer the following documentation: https://www.mathworks.com/help/ident/nonlinear-model-identification.html
2. Simulink provides adaptive learning blocks that allow online training. You can use Neural State-Space Models or Adaptive Neuro-Fuzzy Inference Systems (ANFIS) for real-time learning. You can read more about it here: https://www.mathworks.com/help/deeplearning/ug/design-time-series-narx-feedback-neural-networks.html
3. Finally, you can implement an online learning algorithm using MATLAB Function blocks inside Simulink. This requires manually updating weights using backpropagation or reinforcement learning techniques.