Neural network solution to the neuromagnetic imaging problem
Hisashi Tsuruoka · Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society · 1992
The application of neural networks is considered in solving the inverse problem in producing naps of neuron current densities, resulting from brain activity, with magnetic field data measured by superconducting quantum interference device (SQUID)sensors. The reconstruction ability of two neural network types, Hopfield network and Boltzmann machine, is evaluated by computer.