By designing a new family of expedient learning machines, the author proves the counterintuitive fact that arbitrarily increasing the memory of a learning automaton does not necessarily increase its learning capability. This complements the results of M. E. Hellman and T. M. Cover (1970), who proved that it is impossible to obtain an arbitrarily accurate learning machine which possesses only finite memory.

Additional Metadata
Conference Second Conference on Artificial Intelligence Applications: The Engineering of Knowledge-Based Systems.
Citation
Oommen, J. (1985). ON THE FUTILITY OF ARBITRARILY INCREASING MEMORY CAPABILITIES OF STOCHASTIC LEARNING AUTOMATA. In Second Conference on Artificial Intelligence Applications: The Engineering of Knowledge-Based Systems. (pp. 308–312).