Proceedings of the Annual Meeting of the Cognitive Science Society

We present a neural network model of how events are storedin and retrieved from episodic long-term memory (LTM). Themodel is novel in giving an explicit account of the workingmemory (WM) medium mediating access to episodic mem-ory: it makes a specific proposal about how representations ofevents and situations in WM interface with representations ofevents and situations in episodic memory. It also provides theframework for an account of how operations accessing tempo-rally remote situations are reported in language.