Machine Learning for Flavor Development
dc.contributor.advisor | Calmon, Flavio du Pin | |
dc.contributor.author | Xu, David | |
dc.date.accessioned | 2019-11-26T15:55:46Z | |
dc.date.submitted | 2019-04 | |
dc.identifier.citation | Xu, David. 2019. Machine Learning for Flavor Development. Bachelor's thesis, Harvard College. | |
dc.identifier.uri | http://nrs.harvard.edu/urn-3:HUL.InstRepos:41940965 | * |
dc.description.abstract | Currently, most flavor development is performed by chemists who experimentally iterate many times to find flavors that best fit specified requirements. In this study, three potential algorithms for automating and accelerating this process are examined and implemented, and the results are analyzed. The apriori algorithm, which generates probabilistic association rules, fails because it only predicts the coexistence of high-frequency features. The generative adversarial network (GAN) fails because the generator only exploits a small part of the solution space. However, the variational autoencoder (VAE) successfully recovers purposely omitted features 95.6% of the time, making it the most promising algorithm. | en_US |
dc.language.iso | en_US | en_US |
dash.license | LAA | |
dc.title | Machine Learning for Flavor Development | en_US |
dc.type | Thesis or Dissertation | en_US |
dc.date.available | 2019-11-26T15:55:46Z | |
thesis.degree.date | 2019 | en_US |
thesis.degree.discipline | Electrical Engineering | en_US |
thesis.degree.grantor | Harvard College | en_US |
thesis.degree.level | UNDERGRADUATE | en_US |
thesis.degree.name | Bachelor of Science | en_US |
Files in this item
This item appears in the following Collection(s)
-
FAS Theses and Dissertations [6136]