Reputation: 57
Use Feed Forward Neural Networks instead of LSTM?
Can a LSTM problem be expressed as FFNN one?
LSTM neural networks simply look in the past. But I can also take some (or many) past values and use them as input features of a FFNN.
In this way, could FFNN replace LSTM Networks? Why should I prefer LSTM over FFNN if I can take past values and use them as input features?
Upvotes: 1
Views: 965
Answers (1)
Reputation: 1461
LSTM is also a feed forward neural network with Memory Cell and recurrent connection. LSTM is an optimized NN algorithm since it can handle the problem of vanishing and exploring gradients and it can handle the long term dependencies. Obviously, you can use a FFNN by customizing the input layer information with a valid Neural Network architecture, this is not a replacement of LSTM.
Upvotes: 1
Related Questions
- LSTM with classification
- Is it possible to use LSTM predictions as inputs for next time steps?
- LSTM/RNN many to one
- Using Keras to structure LSTM model
- LSTM RNN Backpropagation
- Is it okay to use STATEFUL Recurrent NN (LSTM) for classification
- Multiple Layer of LSTM for Prediction using Tensorflow
- lstm for prediction of future time series values with Keras
- Feed Forward - Neural Networks Keras
- LSTM NN: forward propagation