| Neural Network Toolbox | |
Create concurrent bias vectors
Syntax
Description
B - S x 1 bias vector (or Nl x 1 cell array of vectors).
Q - Concurrent size.
Returns an S x B matrix of copies of B (or Nl x 1 cell array of matrices).
Examples
Here concur creates three copies of a bias vector.
b = [1; 3; 2; -1]; concur(b,3)
Network Use
To calculate a layer's net input, the layer's weighted inputs must be combined with its biases. The following expression calculates the net input for a layer with the netsum net input function, two input weights, and a bias:
n = netsum(z1,z2,b)
The above expression works if Z1, Z2, and B are all S x 1 vectors. However, if the network is being simulated by sim (or adapt or train) in response to Q concurrent vectors, then Z1 and Z2 will be S x Q matrices. Before B can be combined with Z1 and Z2, we must make Q copies of it.
n = netsum(z1,z2,concur(b,q))
See Also
netsum, netprod, sim, seq2con, con2seq
| | con2seq | ddotprod | |