Olfaction Prediction With Topology‐Aware Machine Learning - Wang - Flavour and Fragrance Journal - Wiley Online Library

AbstractData science seems to be everywhere these days. This talk will discuss examples of data science being applied to music and meal planning, as well as introducing publicly available resources for exploring culturally motivated data. This talk will delve deeply into the multidisciplinary field of Music Information Retrieval (MIR) motivated by the comparisons that we, as humans, make about music and the various contexts of these comparisons. Specifically, we discuss the aligned hierarchies, which is a structure-based representation that can be used for comparing songs, and new extensions of aligned hierarchies that leverage ideas from topological data analysis. The talk will then pivot to how we can think about meal planning as “playlists of recipes” and the data-based challenges associated with building a database of meal plans. BioKatherine M. Kinnaird is a computational researcher working at the intersection of machine learning, mathematics and cultural analytics. Currently she is an Associate Professor of Computer Science and Statistical & Data Sciences at Smith College as well as Chair of the CS Department.