Proceedings to The Twenty-Ninth International FLAIRS Conference
Episodic memory systems for artificially intelligent agents must cope with an ever-growing episodic memory store. This paper presents an approach for minimizing the size of the store by using specialized hash functions to convert each memory into a relatively short binary code. A set of desiderata for such hash functions are presented including locale sensitivity and reversibility. The paper then introduces multiple approaches for such functions and compares their effectiveness.
Artificial intelligence; Episodic memory
Citation: Pilot Scholars Version (Modified MLA Style)
Vanderwerf, Emilia; Stiles, Robert; Warlen, Alexandra; Siebert, Allison; Bastien, Kevin; Meyer, Andrew; Nuxoll, Andrew M.; and Wallace, Scott A., "Hash Functions for Episodic Recognition and Retrieval" (2016). Engineering Faculty Publications and Presentations. 35.