What is the best neural network model for temporal data?
Answers
I'm specifically interested in deep learning methods such as RBM, sparse autoencoders and so on.
Most methods I encountered consider only one dimension of the data, or maybe a 2D "block" in the data (usually images).
I couldn't find a paper on how to take into consideration the temporal aspect and also the multivariate aspect. For example if I'm recording audio from multiple channels, then I know that the channels are probably correlated to some degree. Also, since it's an evolving temporal signal, there is also some correlation of each sample to the previous samples.
Is there some way to incorporate these multivariate temporal constraints into a network?
I'm looking for specific papers on methods for multivariate temporal where the multi-channel structure is used.
The best neural network model for temporal data is Recurrent Neural Network.
Temporal Data can basically be defined as a special type of data which is not consistent over time and varies with the dimension of time.
Recurrent Neural Networks are the special types of neural networks which are much well suited for dealing with the temporal data sets as input data.
Recurrent Neural Networks have been defined by Wikipedia as- "A recurrent neural network (RNN) is a class of artificial neural network where connections between nodes form a designed graph with a low lasting flow."
It enables it to show temporal dynamic behavior. The process continuation of inputs can use feed forward neural networks in their internal state. This is making them they should do tasks such as connected handwriting recognition, unsegmented or speech recognition.