Task 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 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 functionally independent tasks and allocates distinct networks to learn each task. In addition, the architecture tends to allocate to each task the network whose topology is most appropriate to that task. The architecture's performance on “what” and “where” vision tasks is presented and compared with the performance of two multilayer networks. Finally, it is noted that function decomposition is an underconstrained problem, and, thus, different modular architectures may decompose a function in different ways. A desirable decomposition can be achieved if the architecture is suitably restricted in the types of functions that it can compute. Finding appropriate restrictions is possible through the application of domain knowledge. A strength of the modular architecture is that its structure is well suited for incorporating domain knowledge.     

A Computational Theory of Learning Causal Relationships

I present a cognitive model of the human ability to acquire causal relationships. I report on experimental evidence demonstrating that human learners acquire accurate causal relationships more rapidly when training examples are consistent with a general theory of causality. This article describes a learning process that uses a general theory of causality as background knowledge. The learning process, which I call theory-driven learning (TDL), hypothesizes causal relationships consistent both with observed data and the general theory of causality. TDL accounts for data on both the rate at which human learners acquire causal relationships, and the types of causal relationships they acquire. Experiments with TDL demonstrate the advantage of TDL for acquiring causal relationships over similarity-based approaches to learning: Fewer examples are required to learn an accurate relationship.     

Default Probability

A probability may be called “default” if it is neither derived from preestablished probabilities nor based on considerations of frequency or symmetry. Default probabilities presumably arise through reasoning based on causality and similarity. This article advances a model of default probability based on a featural approach to similarity. The accuracy of the model is assessed by comparing its predictions to the probabilities provided by undergraduates asked to reason about mammals.