The concept of PNL (Precisiated Natural Language) has been proposed by Zadeh for computation with perceptions and some problems described in natural language. We describe a design for restricted domain question answering systems enhanced by PNL-based reasoning. For a subset of a knowledge corpus (e.g. critical or frequently-asked topics) where fuzzy set definitions of vague terms are provided, more precise answers can be computed via protoformal deduction. Nested structure in the system design also enables processing of natural language statements that are not PNL protoforms using phrase-based deduction and concept matching to generate the most relevant facts for a query. If deduction results yield low confidence factor, standard search engine provides a baseline response (relevant paragraphs based on keyword matches). Our design principles aim for flexible, domain independent capability and minimize human input to provision of semantic clues and background knowledge during design or application set-up.

Interim results of a study on pattern recognition of robotic tactile impressions using connectionist models are described. The training data consists of gray-scale force gradient profiles that accurately reflect the tactile domain; the focus is on extracting these features with artificial neural systems (ANSs). A description is given of an architecture in which a two-layer back-error-propagation network performs feature extraction of gray-scale gradients, and a second BEP network classifies the surface profiles. Imposition of constraints on the training set is critical to ensure that meaningful features are selected. In domains where information content of the input vectors are dense and very similar, receptive field neurons encode useful data across unit activations, while fully connected schemes shroud information among the link weights