Skip to content
You are here: Home » Documents » Deliverables » Deliverable WP4
Personal tools

Deliverable WP4

Up one level
WP4 related deliverables
Deliverable WP4 D4.1: Critical Comparison of Mechanisms based on Analogy, Proactive and Goal Directed
This document classifies and differentiates all systems relevant to WP4: Goal-directed behavior, pro-activity, and analogy. The workpackage is mainly concerned with anticipatory (goaldirected)action decision making and action control that is controlled by predictions and analogical reasoning. Essentially, the document assesses the potential of each relevant model to predict the future, potentially including and incorporating own future actions, motivations, and emotions. The document examines and compares the relevant models with respect to their predictive and anticipatory capabilities. We assess weaknesses and strengths of the architectures in generating predictions and using those predictions for the generation of anticipatory cognitive functions. Solutions are suggested that will enable agents to predict at different time scales and at different levels of abstraction. Moreover, solutions are suggested how to enable effective top-down cognitive influence resulting in goal-directed behavior mechanisms and pro-activity. It is shown that the different system capabilities cover the whole spectrum of the mechanisms necessary to generate the desired anticipatory, cognitive embodied systems. However, it is also shown that without effective collaboration and knowledge exchange between the partners, the capabilities are expected to stay limited. Although one part of the work relevant to workpackage four and the whole MindRACES project consists in the further development and evaluation of the predictive and anticipatory capabilities of each system in separation, the biggest challenge will be to combine the different capabilities, such as, for example, context processing capabilities with long term dependency learning capabilities and grammar learning capabilities, to induce maximally effective predictive environmental representations that are most suitable for the goal-directed behavior mechanisms, expected to be generated by the means of the predictive representations. The scenarios developed in WP2 are expected to help stimulate the interaction of the partners further as well as to identify potential collaborations amongst them. However, this document suggests many potential collaborations and system combinations between the partners and may serve as the guidebook for the generation of competent anticipatory cognitive embodied systems that learn and exhibit effective anticipatory, goal-directed behavior exploiting their emergent predictive representations most effectively.
Deliverable WP4 D4.2

Powered by Plone

Anticipatory Cognitive Science is a research field that ensembles artificial intelligence, biology, psychology, neurology, engineering and philosophy in order to build anticipatory cognitive systems that are able to face human tasks with the same anticipatory capabilities and performance. In deep: Cognitive science is the interdisciplinary study of mind and intelligence, embracing philosophy, psychology, artificial intelligence, neuroscience, linguistics, and anthropology. Its intellectual origins are in the mid-1950s when researchers in several fields began to develop theories of mind based on complex representations and computational procedures. Its organizational origins are in the mid-1970s when the Cognitive Science Society was formed and the journal Cognitive Science began. Since then, more than sixty universities in North America, Europe, Asia, and Australia have established cognitive science programs, and many others have instituted courses in cognitive science.