|
Abstract : |
This paper sketches several aspects of a hypothetical cortical architecture for visual object recognition, based on a recent computational model. The scheme relies on modules for learning from examples, such as Hyperbf-like networks, as its basic components. Such models are not intended to be precise theories of the biological circuitry but rather to capture a class of explanations we call Memory-Based Models (MBM) that contains sparse population coding, memory-based recognition and codebooks of prototypes. Unlike the sigmoidal units of some arti cial neural networks, the units of MBMs are consistent with the usual description of cortical neurons as tuned to multidimensional optimal stimuli. We will describe how an example of MBM may be realized in terms of cortical circuitry and biophysical mechanisms, consistent with psychophysical and physiological data. A number of predictions, testable with physiological techniques, are made., |
