Skip to Main content Skip to Navigation
Book sections

Interactive machine learning for applications in food Science

Abstract : The apparent simplicity of food processes often hides complex systems, where physical, chemical and living organisms' processes co-exist and interact to create the final product. Data can be plagued by uncertainty; heterogeneity of available information is likely; qualitative and quantitative data may also coexist in the same process, from expert perception of food quality to nano-properties of ingredients. In order to obtain reliable models, it then becomes necessary to acquire additional information from external sources. Experts of a domain can provide invaluable insight in products and processes, but this precious knowledge is often available only in the form of intuition and implicit expertise. Including expert insight in a model can be tackled by having humans interacting with a machine learning process, through visualization or via specialists in encoding implicit domain knowledge. In this chapter, three selected case studies in food science portray different success stories of combining machine learning and expert interaction. We show that expert knowledge can be integrated at different stages of the modelling process, either online or offline, to initialize, enrich or guide this process.
Keywords : knowledge resistance
Complete list of metadata
Contributor : Migration ProdInra Connect in order to contact the contributor
Submitted on : Friday, June 5, 2020 - 7:28:08 AM
Last modification on : Friday, August 5, 2022 - 2:38:10 PM



Alberto Tonda, Nadia Boukhelifa, Thomas Chabin, Marc Barnabe, Benoit Génot, et al.. Interactive machine learning for applications in food Science. Human and Machine Learning, SPRINGER, pp.19, 2018, Human-Computer Interaction Series, 978-3-319-90403-0; 978-3-319-90402-3. ⟨10.1007/978-3-319-90403-0_22⟩. ⟨hal-02791245⟩



Record views