A neural network structure specified for representing and storing logical relations
- PDF / 2,560,114 Bytes
- 19 Pages / 595.276 x 790.866 pts Page_size
- 55 Downloads / 175 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL ARTICLE
A neural network structure specified for representing and storing logical relations Gang Wang1 Received: 23 July 2019 / Accepted: 14 March 2020 Ó Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Logical representation and reasoning is an important aspect of intelligence. Current ANN models are good at perceptual intelligence while they are not good at cognitive intelligence such as logical representation, so researchers have tried to design novel models so as to represent and store logical relations into the neural network structures, called the type of Knowledge-Based Neural Network. However, there is an ambiguous problem that the same neural network structure represents multiple logical relations. It causes the corresponding logical relations not to be read out from these neural network structures which are constructed according to them. To let logical relations stored in the format of neural network and read out from it, this paper studies the direct mapping method between logical relations and neural network structures and proposes a novel model called Probabilistic Logical Generative Neural Network, which is specified for logical relation representation by redesigning the neurons and links. It can make neurons solely for representing things while making links solely for representing logical relations between things, and thus no extra logical neurons and layers are needed. Moreover, the related construction and adjustment methods of the neural network structure are also designed making the neural network structure dynamically constructed and adjusted according to logical relations. Keywords Logical representation and storage Generative neural network structure Logical artificial neural network Adaptivity Connection structure Inhibitory link
1 Introduction With computer technology widely used for a few decades, it greatly increases the informatization and automation in every aspect of human activities and brings the big convenience for human. As computer technology is further applied, the matters to be solved by computers become more and more complex such as advanced medical diagnosis or driverless vehicles. For these complex matters, there are a considerable amount of various conditions contained, and new conditions may appear at any time. For example, in the medical diagnosis, various symptoms may appear on a patient, such as various physical or mental features, and new symptoms may appear later for chronic or worsening diseases. People eagerly expect the coming of & Gang Wang [email protected]; [email protected] 1
Department of Computer Science and Technology, Taiyuan University of Technology, Taiyuan, China
advanced diagnosis computer systems matching for the skill of doctors. To solve the complex matters in medical and other fields, more and more complex computer systems need building in order to respectively process considerable conditions in the complex matters which are represented as the set of if-then rul
Data Loading...
