LIDA
LIDA (Learning IDA) adds various mode of human-like learning to the
IDA architecture (see IDA description below), including perceptual, episodic,
procedural and attentional learning.
Integrated LIDA: Parameter Tuning
forthcoming
Integrated LIDA: Tyrell's World
forthcoming
LIDA Working Memory
This project aims to develop a more detailed and comprehensive computational model of working memory in LIDA. Roughly speaking, working memory in LIDA is implemented via the workspace, perceptual, episodic, and declarative memory buffers, and relational and structure-building codelets. Part of the project is to flesh out a new component of the workspace called the Model which contains the agent's representational model of its current situation. Some of the questions involved in this research are how to model the memory buffers, how to update the model with new percepts and cued memory, and how to implement top-down processes to build relations in the workspace based on lower-level perceptual information. In short, the LIDA Working Memory Project aims to design, implement, and test mechanisms that give LIDA an understanding of its current situation.
|