Daniel T. Halstead

Learn More
It is notoriously difficult to simultaneously deal with both probabilistic and structural representations in A.I., particularly because probability necessitates a uniform representation of the training examples. In this paper, we show how to build fully-specified probabilistic models from arbitrary propositional case descriptions about terrorist activities.(More)
Learning spatial prepositions is an important problem in spatial cognition. We describe a model for learning how to classify visual scenes according to what spatial preposition they depict. We use SEQL, an existing model of analogical generalization, to construct relational descriptions from stimuli input as hand-drawn sketches. We show that this model can(More)
A key issue in artificial intelligence lies in finding the amount of input detail needed to do successful learning. Too much detail causes overhead and makes learning prone to over-fitting. Too little detail and it may not be possible to learn anything at all. The issue is particularly relevant when the inputs are relational case descriptions, and a very(More)
  • 1