Integrating Subsymbolic and Symbolic Processing in Artificial Vision
نویسندگان
چکیده
We approach the integration between symbolic and subsymbolic processing within a hybrid model of visual perception, intended for an autonomous intelligent system. No hypotheses are made about the adequacy of this model as a model of human vision: the proposed model is currently under development for a robot system. We propose an associative mapping mechanism, that relates the constructs of the symbolic representation to a geometric representation of the observed scene. The symbolic representation is expressed in terms of a formalism provided with compositional structure. The geometric representation is obtained by making use of a geometric modelling system based on superquadrics. We describe a possible realization of the mapping mechanism by means of a feed-forward neural network architecture based on the backpropagation rule, presenting some results of a partial implementation.
منابع مشابه
Symbolic and Subsymbolic Learning for Vision: Some Possibilities
Robust, flexible and sufficiently general vision systems such as those for recognition and description of complex 3dimensional objects require an adequate armamentarium of representations and learning mechanisms. This paper briefly analyzes the strengths and weaknesses of different learning paradigms such as symbol processing systems, connectionist networks, and statistical and syntactic patter...
متن کاملRule Induction through Integrated Symbolic and Subsymbolic Processing
We describe a neural network, called RufeNet, that learns explicit, symbolic condition-action rules in a formal string manipulation domain. RuleNet discovers functional categories over elements of the domain, and, at various points during learning, extracts rules that operate on these categories. The rules are then injected back into RuleNet and training continues, in a process called iterative...
متن کاملPerception Processing for General Intelligence: Bridging the Symbolic/Subsymbolic Gap
Bridging the gap between symbolic and subsymbolic representations is a – perhaps the – key obstacle along the path from the present state of AI achievement to human-level artificial general intelligence. One approach to bridging this gap is hybridization – for instance, incorporation of a subsymbolic system and a symbolic system into a integrative cognitive architecture. Here we present a detai...
متن کاملSubsymbolic planning of behavior in a four-arm-maze
Method Introduction By now, many successful attempts have been made to implement sensory processing in subsymbolic systems, but planning of complex behavior is still a domain of symbolic systems. Inspired by a biological example, here we try to design and implement a system handling both aspects in a homogeneous architecture (1), integrating sensory processing, action execution and decision mak...
متن کاملLearning in an active hybrid vision system
This paper focuses on learning of object models for an active robot vision system. One of its main attributes is the generation of hybrid models of 3D objects, integrating implicit representations by neural networks and explicit descriptions by semantic networks. On both levels of the vision system, subsymbolic neural learning as well as symbolic semantic learning can be done completely unsuper...
متن کامل