Considering Memory Networks in the LTM Structure of the Multilevel Darwinist Brain

被引：4

作者：

Duro, Richard J. ^{[1
]}

Antonio Becerra, Jose ^{[1
]}

Monroy, Juan ^{[1
]}

Caamano, Pilar ^{[2
]}

机构：

[1] Univ A Coruna, GII, La Coruna, Spain

[2] NATO STO CMRE, La Spezia, Italy

来源：

PROCEEDINGS OF THE 2016 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE (GECCO'16 COMPANION) | 2016年

关键词：

Long term memory; cognition; Multilevel Darwinist Brain; network memory;

D O I：

10.1145/2908961.2931674

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

In this paper, we present an initial implementation of the concept of memory network within the long term memory (LTM) structure of the Multilevel Darwinist Brain (MDB). The purpose is to address the problem of determining what, out of all the knowledge stored in the LTM, is relevant for the current context that a robot finds itself in, without having to resort to complex and time consuming search processes. Additionally, this type of structure allows for a very elegant way of hierarchically relating previously learnt knowledge with solutions to new situations. A very simple example is presented in order to help to understand how the system operates and its possibilities.

引用

页码：1057 / 1060

页数：4

共 11 条

[1]

Anderson J.R., 1993, PRODUCTION SYSTEMS A

[2] Multilevel Darwinist Brain (MDB): Artificial Evolution in a Cognitive Architecture for Real Robots [J].