One system for learning and remembering episodes and rules
Joshua T. S. Hewson, Sabina J. Sloman, Marina Dubova

TL;DR
This paper demonstrates that a single, high-capacity learning system can effectively learn and retain both individual episodes and generalizable rules, challenging the traditional view of separate systems for these processes.
Contribution
It introduces a unified learning system capable of handling both episodic and rule-based knowledge, countering the idea of separate, competing systems.
Findings
A single system with excess capacity learns episodes and rules
The system retains both types of knowledge over time
Challenges the view of separate learning systems in cognition
Abstract
Humans can learn individual episodes and generalizable rules and also successfully retain both kinds of acquired knowledge over time. In the cognitive science literature, (1) learning individual episodes and rules and (2) learning and remembering are often both conceptualized as competing processes that necessitate separate, complementary learning systems. Inspired by recent research in statistical learning, we challenge these trade-offs, hypothesizing that they arise from capacity limitations rather than from the inherent incompatibility of the underlying cognitive processes. Using an associative learning task, we show that one system with excess representational capacity can learn and remember both episodes and rules.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNeural Networks and Applications
