Categorization in neural networks and prosopagnosia

• Published in: Physics reports 1989-12, Vol.184 (2), p.301-306
• Main Author: Virasoro, M.A
• Format: Article
• Language: English
• Subjects: Exact sciences and technology; Fluctuation phenomena, random processes, noise, and brownian motion; Physics; Statistical physics, thermodynamics, and nonlinear dynamical systems
• ISSN: 0370-1573; 1873-6270
• DOI: 10.1016/0370-1573(89)90050-1

Prosopagnosia is a syndrome characterized by a generalized difficulty to visually recognize individual patterns among those that are similar, and can therefore be said to belong to the same category. I suggest that the existence of this disfunction may be an important clue for understanding the categorization process in the brain. In this direction the performance of neural networks under random destruction of synapses is analysed. It is found that in almost every network that stores correlated patterns the coding of the discriminating details between individuals inside a class is more sensitive to noise or to random destruction than the coding that distinguishes between classes. It follows that a process of death and/or deterioration at an intermediate level of intensity, even if it acts randomly on the network may lead to a malfunctioning of the network that resembles prosopagnosia.