Report de Recerca IIIA 93-2 Gener 1993
Reflection, Memory and Learning
Enric Plaza & Josep-Lluís Arcos
IIIA - Institut d'Investigació en
Intel.ligència Artificial,
CSIC - Spanish Scientific Research Council,
Campus Universitat Autonòma de Barcelona,
08193 Bellaterra, Catalonia, Spain.
Voice: +34 3 5809570;
Fax: +34 3 5809661;
Email: {plaza | arcos}@iiia.csic.es
WWW: http://www.iiia.csic.es
In this paper we will discuss the significance of memory and reflection in
integrated learning architectures. The Massive Memory Architecture, a uniform
architecture based on episodic memory a case-based reasoning, is described. Its
reflective capabilities are described and we put forth the hypothesis that
learning methods are inference methods with reflective capabilities, i.e.
methods requiring a self-model of the system. Self-models and method
implementation are based on conceptual, knowledge-level descriptions of
inference. We show how the MMA reflective capabilities can be used for
representing and implementing learning methods.