Cognitively motivated machine learning for dimensionality reduction and domain adaptation of speech and language models in resource-constrained settings
Abstract
In the recent years, a dominant strategy has arised in machine learning, i.e., scaling-up model capacity and training data, with impressive results. However, the development of techniques for resource-limited settings can have a great economic, environmental, and research impact, especially for digitally under-represented communities. In this thesis, which is split into two major parts, we draw motivation from insights in the fields of cognitive sciences and neurosciences to design efficient and effective machine learning algorithms for data representation and model adaptation. First, we propose a novel algorithm for dimensionality reduction via multi-dimensional scaling based on the global geometry of the input data. The proposed algorithm, Pattern Search MDS is based on derivative-free direct search, and is able to capture the geometry of complex “pseudo”-metric spaces. Reduction of the algorithm to the General Pattern Search algorithmic family provides theoretical convergence guaran ...
show more
![]() | Download full text in PDF format (9.76 MB)
(Available only to registered users)
|
All items in National Archive of Phd theses are protected by copyright.
|
Usage statistics
VIEWS
Concern the unique Ph.D. Thesis' views for the period 07/2018 - 07/2023.
Source: Google Analytics.
Source: Google Analytics.
ONLINE READER
Concern the online reader's opening for the period 07/2018 - 07/2023.
Source: Google Analytics.
Source: Google Analytics.
DOWNLOADS
Concern all downloads of this Ph.D. Thesis' digital file.
Source: National Archive of Ph.D. Theses.
Source: National Archive of Ph.D. Theses.
USERS
Concern all registered users of National Archive of Ph.D. Theses who have interacted with this Ph.D. Thesis. Mostly, it concerns downloads.
Source: National Archive of Ph.D. Theses.
Source: National Archive of Ph.D. Theses.






