The tag has no usage guidance.

learn more… | top users | synonyms

2
votes
0answers
53 views

What parallelization methods can make neural nets train faster?

A fairly straightforward way (on a theoretical level, at least) of parallelizing artifical neural networks (ANNs) would be to divy up the batches of training examples during every epoch so that ...
1
vote
0answers
45 views

How to evaluate a recurrent connection in an artificial neural network?

I just can't understand how should I compute the output of a neural network, which contains a recurrent connection. So here is an example: (i_1,2 are the input values, w_1,2,3,r are the ...
1
vote
0answers
89 views

Neural network converges to 0.5 for XoR

I'm coding a neural network in C for an OCR project. Before testing with character recognition, I'm making it learn the XoR operation. Although, the results I'n getting always converges to 0.5 instead ...
0
votes
0answers
33 views

How do errors make sense for hidden layers in artificial neural networks?

Its pretty clear for the output layer, since what we do is we compare the output with our prototype and calculate the error. But how does error make sense for hidden layers, What is considered to be ...
0
votes
0answers
24 views

Distributed versus Sparse encoding for Neural Network Input

This is not a theoretical question, but an actual question which will reflect my implementation in C++ of a Knowledge Representation classifier. The intended ANN is in fact a binary RBM. My data, is ...