H Gutfreund and Y Stein 1990 J. Phys. A: Math. Gen. 23 2613 doi:10.1088/0305-4470/23/12/036
H Gutfreund and Y Stein
Show affiliationsThe authors study the optimal storage capacity of neural networks with discrete local constraints on the synaptic couplings Jij. Models with such constraints include those with binary couplings Jij=+or-1 or Jij=0, 1, quantised couplings with larger synaptic range, e.g. Jij=+or-1/L, +or-2/L, . . ., +or-1 and, in the limit, continuous couplings confined to the hypercube mod Jij mod <or=1 ('box confinement'). They find that the optimal storage capacity alpha ( kappa ) is best determined by the vanishing of a suitably defined 'entropy' as calculated in the replica symmetric approximation. They also extend their results to cases with biased memories and make contact with sparse coding models.
05.50.+q Lattice theory and statistics (Ising, Potts, etc.)
82C32 Neural nets (See also 68T05, 91E40, 92B20)
82C20 Dynamic lattice systems (kinetic Ising, etc.) and systems on graphs
Issue 12 (21 June 1990)
H Gutfreund and Y Stein 1990 J. Phys. A: Math. Gen. 23 2613
Elika Saïdi et al 2009 Nanotechnology 20 115703
Yasemin Caglar et al 2009 J. Phys. D: Appl. Phys. 42 065421
Christiane Höppener and Lukas Novotny 2008 Nanotechnology 19 384012
Jared H Cole and Lloyd C L Hollenberg 2009 Nanotechnology 20 495401
L Ruan et al 2009 J. Phys. G: Nucl. Part. Phys. 36 095001
Alexander L Fetter and Anatoly A Svidzinsky 2001 J. Phys.: Condens. Matter 13 R135
V Matveev and R Shrock 1995 J. Phys. A: Math. Gen. 28 L533
V Matveev and R Shrock 1995 J. Phys. A: Math. Gen. 28 5235
V Matveev and R Shrock 1995 J. Phys. A: Math. Gen. 28 4859