Artificial neural networks have weaknesses as models of cognition. A conventional neural network has limitations of computational power. The localist representation is at least equal to its competition. We contend that locally connected neural networks are perfectly capable of storing and retrieving the individual features, but the process of reconstruction must be otherwise explained. We support the localist position but propose a “hybrid” model that can begin to explain cognition in anatomically plausible terms.

Somatosensory processing for action guidance can be dissociated from perception and memory processing. The dorsal system has a global bias and the ventral system has a local processing bias. Autistics illustrate the point, showing a bias for part over wholes. Lateralized differences have also been noted in these modalities. The multi-modal dysfunction observed may suggest more an issue of interhemispheric communication.