This paper explores the possibility that the formation of color blobs in primate striate cortex can be partly explained through the process of activity-based self-organization. We present a simulation of a highly simplified model of visual processing along the parvocellular pathway, that combines precortical color processing, excitatory and inhibitory cortical interactions, and Hebbian learning. The model self-organizes in response to natural color images and develops islands of unoriented, color-selective cells within a sea of contrast-sensitive, orientation-selective cells. By way of understanding this topography, a principal component analysis of the color inputs presented to the network reveals that the optimal linear coding of these inputs keeps color information and contrast information separate.

The effect of different kinds of weight normalization on the outcome of a simple competitive learning rule is analyzed. It is shown that there are important differences in the representation formed depending on whether the constraint is enforced by dividing each weight by the same amount (“divisive enforcement”) or subtracting a fixed amount from each weight (“subtractive enforcement”). For the divisive cases weight vectors spread out over the space so as to evenly represent “typical” inputs, whereas for the subtractive cases the weight vectors tend to the axes of the space, so as to represent “extreme” inputs. The consequences of these differences are examined.

Integrated systems have become prominent in the research programmes of a number of artificial intelligence laboratories. The Edinburgh machine intelligence group here defines its research and development philosophy in reply to questions put by Japanese robot engineers.