Application of Curriculum Learning for de novo design of small molecules

dc.contributor.authorArango, Juan Diego
dc.contributor.departmentChalmers tekniska högskola / Institutionen för fysiksv
dc.contributor.examinerGranath, Mats
dc.date.accessioned2021-06-28T05:40:20Z
dc.date.available2021-06-28T05:40:20Z
dc.date.issued2021sv
dc.date.submitted2020
dc.description.abstractIn recent years, Deep Learning has given new energy to the field of de novo design. This field is the generation of novel chemical compound ideas, which can be used for new applications. AstraZeneca has developed software for this task called REINVENT. The software uses Reinforcement Learning and a user-defined scoring function to create new compound ideas. The objective of this work is to implement, within REINVENT, the technique of Curriculum Learning. Here, the scoring function during the training phase is actively modified. Besides the implementation, this work explores how this approach improves performance compared to the classical Reinforcement Learning approach.sv
dc.identifier.coursecodeTIFX05sv
dc.identifier.urihttps://hdl.handle.net/20.500.12380/302731
dc.language.isoengsv
dc.setspec.uppsokPhysicsChemistryMaths
dc.titleApplication of Curriculum Learning for de novo design of small moleculessv
dc.type.degreeExamensarbete för masterexamensv
dc.type.uppsokH
Ladda ner
Original bundle
Visar 1 - 1 av 1
Hämtar...
Bild (thumbnail)
Namn:
Master_thesis_Juan_Diego_Arango.pdf
Storlek:
1.66 MB
Format:
Adobe Portable Document Format
Beskrivning:
License bundle
Visar 1 - 1 av 1
Hämtar...
Bild (thumbnail)
Namn:
license.txt
Storlek:
1.51 KB
Format:
Item-specific license agreed upon to submission
Beskrivning: