Optical implementations of the alternating projection neural network

An analysis of the alternating projection neural network (APNN) along with results from an electronic and two optical implementations are presented in this thesis. After an introduction the APNN is explored both analytically and geometrically. Characteristics such as the speed of convergence are realized through matrix equations and linear algebra. If convergence of the APNN is visualized as a geometrical process based on projection, complementary principles are established, such as how the convergence rate changes as new data is stored in the network. Finally, experimental results from two optical architectures are discussed; both configurations use optical matrix-vector multipliers with feedback, but different spatial light modulators are used.