Skip to Main content Skip to Navigation
Journal articles

Prediction Error-Driven Memory Consolidation for Continual Learning: On the Case of Adaptive Greenhouse Models

Abstract : 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.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03344240
Contributor : Schillaci Guido <>
Submitted on : Tuesday, September 14, 2021 - 5:50:31 PM
Last modification on : Tuesday, September 14, 2021 - 6:00:33 PM

File

Schillaci2021_Article_Predicti...
Publication funded by an institution

Identifiers

Citation

Guido Schillaci, Uwe Schmidt, Luis Miranda. Prediction Error-Driven Memory Consolidation for Continual Learning: On the Case of Adaptive Greenhouse Models. KI - Künstliche Intelligenz, Springer Nature, 2021, Developmental Robotics, 35 (1), pp.71 - 80. ⟨10.1007/s13218-020-00700-8⟩. ⟨hal-03344240⟩

Share

Metrics

Record views

70

Files downloads

45