Skip to main content
. 2007 Jun 20;104(26):11079–11084. doi: 10.1073/pnas.0700324104

Fig. 3.

Fig. 3.

Performance of various algorithms with hard-bounded hidden variables. Triangles, BPI; squares, CP; circles, SP; crosses, cascade model. (A–C) Critical capacity vs. N, with fixed number of internal states K. (D) Convergence time vs. α at N = 1,415, K = 40, averaged over 100 samples. Figures for different number of states and synapses are qualitatively similar.