1. (1) J. J. Hopfield, “Neurons with graded response have collective computational properties like those of two-state neurons,” Proc. Natl. Sci. USA, vol.81, no.10, pp.3088–3092, 1984.
2. (2) G. E. Hinton and T. J. Sejnowski, “Learning and relearning in Boltzmann machines,” Parallel distributed processing, 1, D. E. Rumelhart and J. L. McClelland eds., pp.282–317, MIT Press, 1986.
3. (3) D. E. Rumelhart, G. E. Hinton, and Y. R. J. Williams, “Learning representations by back-propagating errors,” Nature, vol.323, pp.533–536, 1986.
4. (4) K. Nakajima and Y. Hayakawa, “Characteristics of inverse delayed model for neural computation,” Proc. NOLTA, pp.861–864, 2002.
5. (5) K. Nakajima and S. Suenaga, “Bursting characteristics of a neuron model based on a concept of potential with active areas,” CHAOS, vol.18, 023120, pp.1–12, 2008.