Question

Prediction accuracy of a neural network depends on

Answer 1

I'm looking for a way to model and extract features from multivariate temporal data (e.g., multi-channel audio recordings).

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.

Answer 2

The prediction accuracy of a neural network mainly depends on the following two factors:

1. Type of training data set used

 2. Type of neural forecasting model used

  To understand the above two points, you need to understand what neural networks are and for what they’re used. Neural networks are basically a layered network composed of several artificial neurons and are generally used for predicting certain things which are otherwise unobvious.  

  A neuron is basically a virtual software element which takes input values and fires up based on the value produced by the activation function. Training data set is the data which is used to train a neural network.  

  For instance, a neural network has to be trained to identify the images with a dog in it, then it is trained by giving it a training data set which only has images of dogs in it.