I am working on a recurrent neural network (LSTM) to predict a time series. since the training takes time, I have some concerns about the real-world situation when the model is going to implement in a hardware (a chip), it should predict the next state based on the input, but since the environment changes rapidly, the model must retrain (frequently) based on the environment. how should I take care of this re-trainig process? I also want it to train very fast, I am mostly concern about the strategies which I can use for it, like taining with less epochs or less layers, but since I am not an expert in Neural Networks, I have many confusion about it.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.