Dr. Zakhira Nugayeva,
Herriot-Watt University Aktobe Campus, Kazakhstan
THEORETICAL INVESTIGATION OF IMPULSIVE HOPFIELD NEURAL NETWORKS DYNAMICS IN SOCIAL SCIENCE RESEARCH
The advent of artificial intelligence and machine learning has brought transformative changes across various fields of study. Neural networks, a critical component of this technological revolution, have been at the forefront of these developments. The networks, inspired by the human brain’s architecture, have demonstrated remarkable capabilities in tasks ranging from image recognition and natural language processing to predictive analytics.
While neural networks are widely recognized for their applications in processing and interpreting large datasets, their potential for advancing theoretical and applied research in the social sciences is still underexplored. Social scientists are increasingly faced with complex systems that are difficult to model using traditional statistical methods. This is particularly true in areas where the dynamics of human behavior, social interactions, and societal changes involve non-linear relationships, feedback loops, and unpredictable influences [1]. As such, there is a growing need to explore how advanced neural network models, particularly those that accommodate more inmtricate and less predictable dynamics, can be integrated into social science research.
This research aims to contribute to this field by studying the dynamics of Hopfield neural networks with impulsive effects [2], focusing on Poisson stable rates, synaptic connections, and unpredictable external inputs. The specific focus of this research is on the dynamic behaviors of Hopfield neural networks when subject to impulsive effects—sudden, discontinuous changes that can significantly alter the state of the network. The impulsive effects can be thought of as analogous to sudden shocks or disruptions in social systems, such as economic crises, social upheavals. By examining the effects of these impulses on the stability and behavior of the network, this study seeks to extend the theoretical understanding of how such networks can model complex social phenomena.
References
1. Garson, G.D. Neural Networks: An Introductory Guide for Social Scientists. Sage Publications. London 1998.
2. Hopfield, J.J. Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. USA 1982, 79, 2554–2558.
