dc.rights.license | CC-BY-NC-ND | |
dc.contributor.advisor | van Ommen, M. (Thijs) | |
dc.contributor.author | Bolwerk, C.J. | |
dc.date.accessioned | 2021-08-09T18:00:31Z | |
dc.date.available | 2021-08-09T18:00:31Z | |
dc.date.issued | 2021 | |
dc.identifier.uri | https://studenttheses.uu.nl/handle/20.500.12932/40695 | |
dc.description.abstract | This research focuses on adapting an early-pruning algorithm called SynFlow to prune after pre-training. Adapting in this way was inspired by work around the Lottery Ticket Hypothesis by Frankle et al. We show that the instability analysis is a way to determine the stability of a network at an iteration k, after which post-training a subnetwork will result in it matching a full network’s accuracy. While this still reduces complexity and training time during training as the original SynFlow, it also improves accuracy significantly. In the current training setup, a full ResNet-20 network is able to achieve accuracies as high as 90.14%. SynFlow on average gets up to a 80% accuracy, sometimes reaching the low 80 percentages. This research presents AdSynFlow, where we consistently achieve higher accuracies than SynFlow, with a high of 85.27%. Though not yet matching the full network, AdSynFlow promises a bright future for early pruning methods. | |
dc.description.sponsorship | Utrecht University | |
dc.format.extent | 604297 | |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | |
dc.title | How can the knowledge of lottery tickets be used to adapt SynFlow to early pruning after pre-training? | |
dc.type.content | Bachelor Thesis | |
dc.rights.accessrights | Open Access | |
dc.subject.keywords | pruning, lottery tickets, pre-training, SynFlow | |
dc.subject.courseuu | Kunstmatige Intelligentie | |