Symbolic Module Connectionist Module
نویسندگان
چکیده
This paper describes the system SYNHESYS, which is a shell for developing expert systems composed of both a connectionist module and a symbolic module. The shell allows for several types of interactions between the two modules, and for several degrees of coupling. SYNHESYS aims at facilitating the process of knowledge acquisition and at improving the performance of the symbolic module. We present results showing that the symbolic backward chaining performs better when coupled with the connectionist module. Our experiments with SYNHESYS have also shown that several issues have to be taken into account when building hybrid systems, and we nally discuss them.
منابع مشابه
Parallelization of Connectionist Models Based on a Symbolic Formalism
In this paper we study the parallelization of the inference process for connectionist models. We use a symbolic formalism for the representation of the connectionist models. With this translation, the training mechanism is local in the elements of the network, the computing power is improved in the network nodes and a local hybridization with symbolic parts is achieved. The inference in the nal...
متن کاملA Hybrid Intelligent Architecture and Its Application to Water Reservoir Control
Measured inputs in control domains are often continuous. A discretization function is needed to map continuous inputs into multiple intervals or ranges of input values, so that they can be used as symbolic inputs to a rule-based system. The discretization parameters used to determine each interval play a critical role in the overall eeectiveness of a rule-based system. This paper introduces a H...
متن کاملNetNeg: A Hybrid Interactive Architecture for Composing Polyphonic Music in Real Time
There are musical activities in which we are faced with symbolic and sub-symbolic processes. This research focuses on the question whether there is any advantage in integrating a neural network together with a distributed artiicial intelligence approach in the musical domain. In this work, we present a new approach for composing and analyzing polyphonic music. As a case study, we began experime...
متن کاملNetNeg: A Hybrid System Architecture for Composing Polyphonic Music
There are musical activities in which we are faced with symbolic and sub-symbolic processes. This research focuses on the question whether integrating a neural network together with a distributed artiicial intelligence approach has any advantages in the music domain. In this work, we present a new approach for composing and analyzing poliphonic music. As a case study, we began experimenting wit...
متن کاملIntegrating connectionist, statistical and symbolic approaches for continuous spoken Korean processing
This paper presents a multi-strategic and hybrid approach for large-scale integrated speech and natural language processing, employing connectionist, statistical and symbolic techniques. The developed spoken Korean processing engine (SKOPE) integrates connectionist TDNN-based phoneme recognition technique with statistical Viterbi-based lexical decoding and symbolic morphological/phonological an...
متن کامل