< Back to Article

Constructing functional models from biophysically-detailed neurons

Fig 8

Network architecture for recurrent networks.

Orange components indicate the feedforward computation of , and purple components indicate the recurrent computation of ; together they implement Eq 6. While this network is used at test-time, an “unrolled” version similar to Fig 5 is used during training. As such, we remove reference to “tar”, and to the decoders and encoders composing w, in this figure.

doi: https://doi.org/10.1371/journal.pcbi.1010461.g008