Integration of Neural Network Technologies into the Methodology of Teaching Sensory Analysis for Food Technology Students

Abstract

The article examines the implementation of neural network technologies in the educational process for training food technology specialists, with the aim of modeling sensory evaluations, optimizing practical classes, and developing students’ critical thinking and professional skills. The purpose of the article is to investigate and substantiate the opportunities for integrating neural network technologies into the methodology of teaching sensory analysis for the training of food technology specialists, as well as to identify effective approaches to the use of artificial intelligence to improve the quality of the educational process and to build the professional competencies of future food industry professionals.

Methods. A comprehensive methodological approach was applied that integrates pedagogical, experimental, and information technology research methods. The pedagogical component includes analysis of curricula, development of didactic materials, and evaluation of teaching effectiveness using intelligent systems. The experimental component was implemented through the modeling of controlled experiments to assess the impact of neural networks on the development of students’ sensory competencies. The information technology component supports the use of machine learning and deep learning algorithms for processing sensory data and creating personalized learning platforms. This approach makes it possible to assess the potential of artificial intelligence in education and to formulate recommendations for the optimal implementation of relevant tools.

Results. The use of neural network technologies in the educational process was found to enhance the effectiveness of mastering complex sensory characteristics of food products, optimize the development of professional skills, and enable the modeling of individualized learning trajectories. Artificial intelligence algorithms enable automated analysis of students’ responses to different sensory stimuli, prediction of assessment accuracy, and real-time adjustment of methodological approaches. This increases the interactivity of classes, stimulates active cognitive engagement, and supports a deeper understanding of the mechanisms underlying the perception of taste, aroma, and texture attributes of products.

Conclusions. It is substantiated that the introduction of neural network technologies into the teaching of sensory analysis significantly improves the effectiveness of training students in the Food Technology specialty. This approach promotes a deeper understanding of the relationship between the physicochemical properties of a product and its organoleptic characteristics, which is essential for the professional preparation of future technologists. The application of artificial neural networks makes it possible to model and predict the sensory properties of products based on a comprehensive analysis of large datasets, providing students with practical skills in working with digital tools and forming competencies required for the implementation of innovative technologies in the food industry. The use of interactive educational models incorporating elements of neural network analysis increases student motivation, stimulates cognitive activity, and supports the development of analytical thinking needed for evidence-based technological decision-making in food production. Effective implementation of neural network technologies requires a systematic approach that includes the development of appropriate methodological support, adaptation of software, and advanced training for instructors. Promising directions for further research include optimizing neural network models for predicting the sensory characteristics of products and developing adaptive learning platforms to individualize the educational process and improve the quality of training for food technology specialists.