Sensory-biased autoencoder enables prediction of texture perception from food rheology

Abstract

Understanding how the physical properties of food affect sensory perception remains a critical challenge for food design. Here, we present an innovative machine learning strategy to decode the complex relationships between non-Newtonian rheological attributes of liquid foods and their perceived texture. A unique and key aspect of our approach is the implementation of an autoencoder neural network that incorporates sensory scores as a decoder bias during training. This enables the autoencoder to effectively identify non-linear, non-injective relationships between shear-thinning properties and perceived thickness, even when trained on a small dataset. This strategy offers a promising approach for advancing food product development by aiding the design of carefully tailored sensory experiences.