Differentiable Neural Computers for in silico molecular design: Benchmarks of architectures in generative modeling of molecules

Visa enkel post
dc.contributor.authorPRYKHODKO, OLEKSII
dc.contributor.authorJOHANSSON, SIMON
dc.contributor.departmentChalmers tekniska högskola / Institutionen för data och informationstekniksv
dc.contributor.examinerSchliep, Alexander
dc.contributor.supervisorKemp, Graham
dc.contributor.supervisorChen, Hongming
dc.date.accessioned2019-10-08T10:28:03Z
dc.date.available2019-10-08T10:28:03Z
dc.date.issued2019sv
dc.date.submitted2019
dc.description.abstractIn the area of in silico drug discovery, deep learning has grown immensely as a field of research. Recurrent neural networks (RNN) is one of the most common approaches used for generative modeling, but recently the differentiable neural computer (DNC) has been shown to give considerable improvement over the RNN for modeling of sequential data. In this thesis, a DNC has been implemented as an extension to REINVENT, an RNN based model that has already been successfully shown to generate molecules with high validity. The model was benchmarked on its capacity to learn the SMILES language on the GDB-13 and ChEMBL datasets. The DNC shows some improvement on all tests conducted at the cost of greatly increased computational time and memory consumption, which puts its practical use into question. This project also gives some insight into the effect of the DNC hyperparameters for the task of generative modeling of molecules.sv
dc.identifier.coursecodeDATX05sv
dc.identifier.urihttps://hdl.handle.net/20.500.12380/300419
dc.language.isoengsv
dc.setspec.uppsokTechnology
dc.subjectComputer sciencesv
dc.subjectmachine learningsv
dc.subjectrecurrent neural networkssv
dc.subjectGRUsv
dc.subjectLSTMsv
dc.subjectdifferentiable neural computersv
dc.subjectengineeringsv
dc.subjectprojectsv
dc.subjectthesissv
dc.titleDifferentiable Neural Computers for in silico molecular design: Benchmarks of architectures in generative modeling of moleculessv
dc.type.degreeExamensarbete för masterexamensv
dc.type.uppsokH
Ladda ner
Original bundle
Visar 1 - 1 av 1
Bild (thumbnail)
Namn:
CSE 19-94 ODR Prykhodko Johansson.pdf
Storlek:
4.05 MB
Format:
Adobe Portable Document Format
Beskrivning:
Differentiable Neural Computers for in silico molecular design: Benchmarks of architectures in generative modeling of molecules
Ladda ner
License bundle
Visar 1 - 1 av 1
Bild (thumbnail)
Namn:
license.txt
Storlek:
1.14 KB
Format:
Item-specific license agreed upon to submission
Beskrivning:
Ladda ner
Samling
Examensarbeten för masterexamen