NUMERICAL SIMULATION OF NEURAL NETWORKS WITH TRANSLATION AND ROTATION INVARIANT PATTERN RECOGNITION
Maria Cristina Antonucci, Brunello Tirozzi, N.D. YARUNIN, Vladimir Dotsenko · International Journal of Modern Physics B · 1994
A Hopfield-like network modified for translation and rotation invariant pattern recognition is studied on a computer. The neural firing thresholds θ are used as additional degrees of freedom. The phase diagram in the space of parameters (T, θ) is obtained both for the translation and the rotation.