Application of Curriculum Learning for de novo design of small molecules
| dc.contributor.author | Arango, Juan Diego | |
| dc.contributor.department | Chalmers tekniska högskola / Institutionen för fysik | sv |
| dc.contributor.examiner | Granath, Mats | |
| dc.date.accessioned | 2021-06-28T05:40:20Z | |
| dc.date.available | 2021-06-28T05:40:20Z | |
| dc.date.issued | 2021 | sv |
| dc.date.submitted | 2020 | |
| dc.description.abstract | In 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.coursecode | TIFX05 | sv |
| dc.identifier.uri | https://hdl.handle.net/20.500.12380/302731 | |
| dc.language.iso | eng | sv |
| dc.setspec.uppsok | PhysicsChemistryMaths | |
| dc.title | Application of Curriculum Learning for de novo design of small molecules | sv |
| dc.type.degree | Examensarbete för masterexamen | sv |
| dc.type.uppsok | H |