Artificial Intelligence

   

A Novel Pandemonium Architecture Based on Visual Topological Invariants and Mental Matching Descriptions

Authors: Arturo Tozzi, James F Peters

A novel daemon-based architecture is introduced to elucidate some brain functions, such as pattern recognition during human perception and mental interpretation of visual scenes. By taking into account the concepts of invariance and persistence in topology, we introduce a Selfridge pandemonium variant of brain activity that takes into account a novel feature, namely, extended feature daemons that, in addition to the usual recognition of short straight as well as curved lines, recognize topological features of visual scene shapes, such as shape interior, density and texture. A series of transformations can be gradually applied to a pattern, in particular to the shape of an object, without affecting its invariant properties, such as its boundedness and connectedness of the parts of a visual scene. We also introduce another Pandemonium implementation: low-level representations of objects can be mapped to higher-level views (our mental interpretations), making it possible to construct a symbolic multidimensional representation of the environment. The representations can be projected continuously to an object that we have seen and continue to see, thanks to the mapping from shapes in our memory to shapes in Euclidean space. A multidimensional vista detectable by the brain (brainscapes) results from the presence of daemons (mind channels) that detect not only ordinary views of the shapes in visual scenes, but also the features of the shapes. Although perceived shapes are 3-dimensional (3+1 dimensional, if we include time), shape features (volume, colour, contour, closeness, texture, and so on) lead to n-dimensional brainscapes, We arrive at 5 as a minimum shape feature space, since every visual shape has at least a contour in space-time. We discuss the advantages of our parallel, hierarchical model in pattern recognition, computer vision and biological nervous system’s evolution.

Comments: 13 Pages.

Download: PDF

Submission history

[v1] 2017-05-15 03:07:04

Unique-IP document downloads: 26 times

Vixra.org is a pre-print repository rather than a journal. Articles hosted may not yet have been verified by peer-review and should be treated as preliminary. In particular, anything that appears to include financial or legal advice or proposed medical treatments should be treated with due caution. Vixra.org will not be responsible for any consequences of actions that result from any form of use of any documents on this website.

Add your own feedback and questions here:
You are equally welcome to be positive or negative about any paper but please be polite. If you are being critical you must mention at least one specific error, otherwise your comment will be deleted as unhelpful.

comments powered by Disqus