NeuroSolutions is the only Windows simulation environment to fully support backpropagation through time (BPTT). Instead of mapping a static input to a static output, BPTT maps a series of inputs to a series of outputs. This provides the ability to solve temporal problems by extracting how data changes over time. Examples of temporal problems are digital signal processing, speech recognition, and time-series prediction.
In backpropagation through time, the goal is to compute the gradient over the trajectory. Since the gradient decomposes over time, this can be achieved by computing the instantaneous gradients and summing the effect over time. During BPTT the activation is sent through the network and each processing element stores its activation locally for the entire length of the trajectory. At each step the network output is also computed and stored. At the end of the trajectory, the errors are generated at the output and a vector of errors is used to update the network weights.