dc.contributor.author | Yang, Yongxin | |
dc.date.accessioned | 2017-09-28T13:49:08Z | |
dc.date.available | 2017-09-28T13:49:08Z | |
dc.date.issued | 2017-08-14 | |
dc.date.submitted | 2017-09-28T14:16:03.446Z | |
dc.identifier.citation | Yang, Y. 2017. Knowledge sharing: From atomic to parametrised context and shallow to deep models. Queen Mary University of London | en_US |
dc.identifier.uri | http://qmro.qmul.ac.uk/xmlui/handle/123456789/25988 | |
dc.description | PhD | en_US |
dc.description.abstract | Key to achieving more effective machine intelligence is the capability to generalise knowledge
across different contexts. In this thesis, we develop a new and very general perspective
on knowledge sharing that unifi es and generalises many existing methodologies,
while being practically effective, simple to implement, and opening up new problem settings.
Knowledge sharing across tasks and domains has conventionally been studied disparately.
We fi rst introduce the concept of a semantic descriptor and a
flexible neural network approach to knowledge sharing that together unify multi-task/multi-domain
learning, and encompass various classic and recent multi-domain learning (MDL) and
multi-task learning (MTL) algorithms as special cases.
We next generalise this framework from single-output to multi-output problems and
from shallow to deep models. To achieve this, we establish the equivalence between
classic tensor decomposition methods, and specifi c neural network architectures. This
makes it possible to implement our framework within modern deep learning stacks. We
present both explicit low-rank, and trace norm regularisation solutions.
From a practical perspective, we also explore a new problem setting of zero-shot
domain adaptation (ZSDA) where a model can be calibrated solely based on some
abstract information of a new domain, e.g., some metadata like the capture device of
photos, without collecting or labelling the data. | en_US |
dc.language.iso | en | en_US |
dc.publisher | Queen Mary University of London | en_US |
dc.rights | The copyright of this thesis rests with the author and no quotation from it or information derived from it may be published without the prior written consent of the author | |
dc.subject | Electronic Engineering and Computer Science | en_US |
dc.subject | Machine learning | en_US |
dc.subject | knowledge sharing | en_US |
dc.title | Knowledge sharing: From atomic to parametrised context and shallow to deep models | en_US |
dc.type | Thesis | en_US |