Current artificial neural network or connectionist models of music cognition embody feature-extraction and feature-weighting principles. This paper reports two experiments which seek evidence for similar processes mediating recognition of short musical compositions by musically trained and untrained listeners. The experiments are cast within a pattern recognition framework based on the vision-audition analogue wherein music is considered an auditory pattern consisting of local and global features. Local features such as inter-note interval, and global features such as melodic contour, are derived from (...) a two-dimensional matrix in which music is represented as a series of frequencies plotted over time.Manipulation of inter-note interval affected accuracy and reaction time measures in a discrimination task, whereas the same variables were affected by manipulation of melodic contour in a classification task. Musical training is thought of as a form of practice in musical pattern recognition and, as predicted, accuracy and reaction time measures of musically trained subjects were significantly better than those of untrained subjects. Given the evidence for feature-extraction and weighting processes in music recognition tasks, two connectionist models are discussed. The first is a single-layer perceptron which has been trained to discriminate between compositions according to inter-note interval. A second network, using the back-propagation algorithm and sequential input of patterns, is also discussed. (shrink)

Pylyshyn makes a convincing case that early visual processing is cognitively impenetrable, and although I question the utility of binary oppositions such as penetrable/impenetrable, for the most part I am in agreement. The author does not provide explicit designations or denotations for the terms penetrable and impenetrable, which appear quite arbitrary. Furthermore, the use of focal attention smacks of an homunculus, and the account appears to slip too easily between the perceptual, the cognitive, and the neurophysiological.

Models of saccade generation and visual selective attention must explain how and why particular targets are selected. Findlay & Walker do an excellent job of explaining the how of visual selection, but not the why. For a salience map to be more than a description of the relative importance of potential targets, there must be some account of the learning and inheritance that fashion its peaks and troughs. Point of gaze is not necessarily region of attention, and it may be (...) premature to downgrade the role of covert attention in models of visual selection. (shrink)

Schyns, Goldstone & Thibaut oppose the notion of fixed feature analysis, suggesting the possibility of flexible feature creation in object recognition and categorisation. Such proposals cannot be assessed until clear definitions of the objects in question and their decompositions are formulated. Flexibility may come from the decompositions of objects rather than from feature creation.

The Chorus scheme could be an important step in the search for solutions to the symbol grounding problem (Harnad 1990), but Edelman does not address the potential difficulties inherent in downgrading differences in favor of similarities in a categorization device. Isomorphism rather than representation is a more coherent way of thinking about Chorus whose modules are probably analytic rather than holistic.