TY - JOUR A1 - Schillaci, Guido A1 - Schmidt, Uwe A1 - Miranda, Luis T1 - Prediction Error-Driven Memory Consolidation for Continual Learning: On the Case of Adaptive Greenhouse Models T2 - KI - Künstliche Intelligenz N2 - This work presents an adaptive architecture that performs online learning and faces catastrophic forgetting issues by means of an episodic memory system and of prediction-error driven memory consolidation. In line with evidence from brain sciences, memories are retained depending on their congruence with the prior knowledge stored in the system. In this work, congruence is estimated in terms of prediction error resulting from a deep neural model. The proposed AI system is transferred onto an innovative application in the horticulture industry: the learning and transfer of greenhouse models. This work presents models trained on data recorded from research facilities and transferred to a production greenhouse. KW - Adaptive models KW - Deep neural networks KW - Episodic memory KW - Memory consolidation KW - Greenhouse Y1 - 2022 UR - https://opus4.kobv.de/opus4-hnee/frontdoor/index/index/docId/251 UR - https://nbn-resolving.org/urn:nbn:de:kobv:eb1-opus-2510 SN - 1610-1987 VL - 35 SP - 71 EP - 80 PB - Springer ER -