Lower Bounds for the Computational Power of Networks of Spiking

摘要

We investigate the computational power of a formal model for networks ofspiking neurons. It is shown that simple operations on phase-differencesbetween spike-trains provide a very powerful computational tool that canin principle be used to carry out highly complex computations on a smallnetwork of spiking neurons. We construct networks of spiking neurons thatsimulate arbitrary threshold circuits, Turing machines, and a certain typeof random access machines with real valued inputs. We also show thatrelatively weak basic assumptions about the response- and threshold-functions of the spiking neurons are sufficient in order to employ themfor such computations.