Integration of Symbolic and Connectionist Learning to ease Robot Programming and Control
نویسنده
چکیده
This paper presents an overview on the advantages an integrated symbolic connectionist approach can ooer for robot programming and control. It describes the functional dependency of symbolic and con-nectionist modules being parts of an hierarchical robot control system as well as their descriptive and methodological integration. Moreover, it is shown how both symbolic and connectionist learning techniques can be used to make robot programming easier, namely by means of employing a new technique called "Robot Programming by Demonstration" on several levels of the robot control system.
منابع مشابه
Boards Relation Boards Object Boards Planning Boards Sensor Board Actuator Board User Demo Trace Object Agent Classification & Formation of Generic Objects Sensor Agent Preprocessing Extraction of Primitives Experiment
This paper presents an overview on the advantages an integrated symbolic connectionist approach can ooer for robot programming and control. It describes the functional dependency of symbolic and con-nectionist modules being parts of an hierarchical robot control system as well as their descriptive and methodological integration. Moreover, it is shown how both symbolic and connectionist learning...
متن کاملNeural-symbolic integration
The field of neural-symbolic integration has received much attention recently. While with propositional paradigms, the integration of symbolic knowledge and connectionist systems (also called artificial neural networks) has already resulted in applicable systems, the theoretical foundations for the first-order case are currently being laid and first perspectives for real implementations are eme...
متن کاملDynamical Insight into Structure 1 Running head: DYNAMICAL INSIGHT INTO STRUCTURE IN CONNECTIONIST MODELS Dynamical Insight into Structure in Connectionist Models
I discuss a connectionist model, based on Elman’s (1990, 1991) Simple Recurrent Network, of the acquisition of complex syntactic structure. While not intended as a detailed model of the process children go through in acquiring natural languages, the model helps clarify concepts that may be useful for understanding the development of complex abilities. It provides evidence that connectionist lea...
متن کاملTowards Learning Semantics of Spontaneous Dialog Utterances in a Hybrid Framework
In contrast to text processing, spontaneous language contains many discontinuities caused by unusual order, false starts, repairs, repetitions, pauses, etc. Data-driven connectionist learning methods and their inherent fault tolerance can consider this form of \sequential noise". We describe a new hybrid approach for a at semantic interpretation of sentences in spontaneous dialogs using symboli...
متن کاملHybrid Connectionist-Symbolic Modules: A Report from the IJCAI-95 Workshop on Connectionist-Symbolic Integration
need for such models has been growing slowly but steadily over the past five years. Some new, important approaches have been proposed and developed, some of which were presented at the workshop. In sum, the participants felt that it was definitely worthwhile to further pursue research in this area because it might generate important new ideas and significant new applications in the near future....
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1994