Open AccessRemoving uncertainty in neural networks
Author(s) -
Arturo Tozzi,
James F. Peters
Publication year - 2020
Publication title -
cognitive neurodynamics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.83
H-Index - 41
eISSN - 1871-4099
pISSN - 1871-4080
DOI - 10.1007/s11571-020-09574-w
Subject(s) - computer science , morphing , manifold (fluid mechanics) , reciprocal , artificial neural network , artificial intelligence , euclidean geometry , topology (electrical circuits) , mathematics , mechanical engineering , linguistics , philosophy , geometry , combinatorics , engineering
Neuroscientists draw lines of separation among structures and functions that they judge different, arbitrarily excluding or including issues in our description, to achieve positive demarcations that permits a pragmatic treatment of the nervous activity based on regularity and uniformity. However, uncertainty due to disconnectedness, lack of information and absence of objects' sharp boundaries is a troubling issue that prevents these scientists to select the required proper sets/subsets during their experimental assessment of natural and artificial neural networks. Starting from the detection of metamorphoses of shapes inside a Euclidean manifold, we propose a technique to detect the topological changes that occur during their reciprocal interactions and shape morphing. This method, that allows the detection of topological holes development and disappearance, makes it possible to solve the problem of uncertainty in the assessment of countless dynamical phenomena, such as cognitive processes, protein homeostasis deterioration, fire propagation, wireless sensor networks, migration flows, and cosmic bodies analysis.