bttderiv

(To be removed) Backpropagation through time derivative function

bttderiv will be removed in a future release. For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.

For advice on updating your code, see Version History.

Syntax

bttderiv('dperf_dwb',net,X,T,Xi,Ai,EW)
bttderiv('de_dwb',net,X,T,Xi,Ai,EW)

Description

This function calculates derivatives using the chain rule from a network’s performance back through the network, and in the case of dynamic networks, back through time.

bttderiv('dperf_dwb',net,X,T,Xi,Ai,EW) takes these arguments,

net

Neural network

X

Inputs, an RxQ matrix (or NxTS cell array of RixQ matrices)

T

Targets, an SxQ matrix (or MxTS cell array of SixQ matrices)

Xi

Initial input delay states (optional)

Ai

Initial layer delay states (optional)

EW

Error weights (optional)

and returns the gradient of performance with respect to the network’s weights and biases, where R and S are the number of input and output elements and Q is the number of samples (and N and M are the number of input and output signals, Ri and Si are the number of each input and outputs elements, and TS is the number of timesteps).

bttderiv('de_dwb',net,X,T,Xi,Ai,EW) returns the Jacobian of errors with respect to the network’s weights and biases.

Examples

Here a feedforward network is trained and both the gradient and Jacobian are calculated.

[x,t] = simplefit_dataset;
net = feedforwardnet(20);
net = train(net,x,t);
y = net(x);
perf = perform(net,t,y);
gwb = bttderiv('dperf_dwb',net,x,t)
jwb = bttderiv('de_dwb',net,x,t)

Version History

Introduced in R2010b

collapse all

See Also

| (Statistics and Machine Learning Toolbox) | (Statistics and Machine Learning Toolbox) | | |

Topics