Living beings are able to adapt their behaviour repertoire to environmental constraints. Among the capabilities needed for such improvement, the ability to store and retrieve temporal sequences is of particular importance. This chapter focuses on the description of an architecture based on spiking neurons, able to learn and autonomously generate a sequence of generic objects or events. The neural architecture is inspired by the insect mushroom bodies already taken into account in the previous chapters as a crucial centre for multimodal sensory integration and behaviour modulation in insects. Sequence learning is only one among a variety of functionalities that coexist within the insect brain computational model. We will propose a series of implementations that can be adopted to obtain these objectives and report the simulation results obtained. We will embed these mechanisms also in roving robots thereby proposing forward-thinking experiments.
|Titolo:||Learning spatio-temporal behavioural sequences|
PATANE', LUCA (Corresponding)
|Data di pubblicazione:||2018|
|Appare nelle tipologie:||2.1 Contributo in volume (Capitolo o Saggio)|