Abstract—Pseudo inverse learning rule and hyperbolic activation function performance will be evaluated and compared with the sign constraint method and Hebb rule. Comparisons are made between these rules to see which rule is better or outperformed other rules in the aspects of computation time, memory and complexity. From the computer simulation that has been carried out, the hyperbolic activation function performs better than the other learning methods.

Index Terms—Pseudo inverse, hebb rule, hyperbolic activation function, capacity

Saratha Sathasivam is with the School of Mathematical Sciences, Universiti Sains Malaysia, 11800 USM, Penang (Email:saratha@cs.usm.my)

Cite: Saratha Sathasivam, "Learning Rules Comparison in Neuro-Symbolic Integration," International Journal of Applied Physics and Mathematics  vol. 1, no. 2, pp. 129-132, 2011.