= Backpropagation through time
{title2=$\partial h_t/\partial h_{t-1}$}
= BPTT
{c}
{synonym}
Apply the chain rule to a recurrent network unrolled over its input sequence, adding contributions to parameters reused at multiple time steps. Products of state Jacobians convey effects from earlier states to later losses. This can compute exact <gradients> for the chosen finite unrolling, while physiological availability of the same history and error signals is a separate question.
Back to article page
