Thesis
From matrix factorisation to signal propagation in deep learning: algorithms and guarantees
- Abstract:
-
Many problems in data science amount to computing an appropriate representation of the data for the task at hand: two examples related to this thesis are 1) reducing memory, sensing or transmission costs by computing a sparse representation of the data and 2) performing classification by transforming the data into a representation in which the members of different classes are linearly separable. The unifying theme of this thesis is the design and analysis of algorithms which are guaranteed...
Expand abstract
Actions
Access Document
- Files:
-
-
(Preview, Dissemination version, Version of record, pdf, 2.8MB, Terms of use)
-
+ The Alan Turing Institute
More from this funder
- Grant:
- EP/N510129/1
- Programme:
- The Alan Turing Institute Studentship Program
- DOI:
- Type of award:
- DPhil
- Level of award:
- Doctoral
- Awarding institution:
- University of Oxford
- Language:
-
English
- Keywords:
- Subjects:
- Deposit date:
-
2021-06-20
Terms of use
- Copyright holder:
- Murray, M
- Copyright date:
- 2021
If you are the owner of this record, you can report an update to it here: Report update to this record