A Competitive Modular Connectionist Architecture
نویسندگان
چکیده
We describe a multi-network, or modular, connectionist architecture that captures that fact that many tasks have structure at a level of granularity intermediate to that assumed by local and global function approximation schemes. The main innovation of the architecture is that it combines associative and competitive learning in order to learn task decompositions. A task decomposition is discovered by forcing the networks comprising the architecture to compete to learn the training patterns. As a result of the competition, different networks learn different training patterns and, thus, learn to partition the input space. The performance of the architecture on a "what" and "where" vision task and on a multi-payload robotics task are presented.
منابع مشابه
Using Multiple Models to Imitate the YMCA
Learning by imitation enables people to program robots simply by showing them what to do, instead of having to specify the motor commands of the robot. To achieve imitative behaviour in a simulated robot, a modular connectionist architecture for motor learning and control was implemented. The architecture was used to imitate human dance movements. The architecture self-organizes the decompositi...
متن کاملA connectionist method for pattern classification with diverse features
A novel connectionist method is proposed to simultaneously use diverse features in an optimal way for pattern classification. Unlike methods of combining multiple classifiers, a modular neural network architecture is proposed through use of soft competition among diverse features. Parameter estimation in the proposed architecture is treated as a maximum Ž . likelihood problem, and an Expectatio...
متن کاملTask decomposition through competition in a modular connectionist architecture: The what and where vision tasks
A novel modular connectionist architecture is presented in which the networks composing the architecture compete to learn the training patterns. An outcome of the competition is that di erent networks learn di erent training patterns and, thus, learn to compute di erent functions. The architecture performs task decomposition in the sense that it learns to partition a task into two or more funct...
متن کاملTask Decompostiion Through Competition in a Modular Connectionist Architecture: The What and Where Vision Tasks
A novel modular connectionist architecture is presented in which the networks composing the architecture compete to learn the training potterns. An outcome of the competition is that different networks learn different training patterns and, thus, learn to compute different functions. The architecture performs task decomposition in the sense that it learns to partition a task into two or more fu...
متن کاملIncremental Parsing by Modular Recurrent Connectionist Networks
We present a novel, modular, recurrent connectionist network architecture which learns to robustly perform incremental parsing of complex sentences. From sequential input, one word at a time, our networks learn to do semantic role assignment, noun phrase attachment, and clause structure recognition for sentences with passive constructions and center embedded clauses. The networks make syntactic...
متن کامل