A new polarization-encoding scheme for a bipolar kth-order neural netw
ork based on inner-product representation is proposed. Bipolar data mu
ltiplication is achieved as the rotation of linearly polarized light.
A compact architecture of the bipolar kth-order neural network is sugg
ested. In the architecture, no subtractions are needed, and the thresh
old levels for the neurons are fixed. Also, we show that a liquid-crys
tal device such as a liquid-crystal television is acceptable as a pola
rization modulator in the proposed architecture by computer simulation
.