PhD on Neural Network Architecture Optimisation
Neural Networks are a powerful machine learning model that can reach outstanding performance in many problems, such as classification and regression. In this PhD project, we want to investigate novel solutions for the generalisation problem affecting deep networks. Transfer learning and domain adaptation techniques are widely used to solve the generalisation problem. However, those algorithms focus on adapting the parameters of a single model. In the context of federated learning, where a set of distributed machines aims to train a model (typically avoiding data sharing), federal domain adaptation is still underexplored. Therefore, we want to study and investigate how pre-trained deep neural network architectures can be fine-tuned using transfer learning techniques on multiple distributed models at the same time, under the federated learning training paradigm.
The successful applicant will be enrolled in the School of Computing at the Edinburgh Napier University as a PostGrad student and they will be able to shape their PhD with the support and guidance of the student’s supervisors.
Academic qualifications:
A first degree (at least a 2.1) ideally in computer science, or maths, with a good fundamental knowledge of neural networks and graph theory.
English language requirement:
IELTS score must be at least 6.5 (with not less than 6.0 in each of the four components). Other, equivalent qualifications will be accepted. Full details of the University’s policy are available online.
Essential attributes:
Experience of fundamental neural networks.
• Competent in graph theory.
• Knowledge of Python and at least one neural network framework (e.g., Keras, tensorflow, pytorch).
• Good written and oral communication skills.
• Strong motivation, with evidence of independent research skills relevant to the project.
• Good time management.
Desirable attributes:
The applicants should motivate their willingness to obtain a PhD degree, attaching a research proposal (max 1 A4 page), describing their ideas and how these align with the scholarships aims and objectives
Funding Notes
This PhD call is fully-funded for 3 years and covers the tuition fees of UK/UE applicants.
Informal Enquires: Dr Valerio Giuffrida (check email address at the footer of the website)
—————
PhD on Domain Adaptation in Federated Learning
Neural Networks are a powerful machine learning model that can reach outstanding performance in many problems, such as classification and regression. Since the rise of deep neural networks, especially used in computer vision, there are several open questions on what the optimal network architecture should be. Most of the state-of-the-art deep architectures are not optimised and typically result in over-parametrized models, as was recently demonstrated in several works.
We want to investigate how deep neural network architectures can be optimised, by reducing the number of layers – and thus the number of parameters to be optimized – and their interconnections. In particular, we want to study neural network optimsation using graph and network theories.
Academic qualifications:
A first degree (at least a 2.1) ideally in computer science, or maths, with a good fundamental knowledge of neural networks and graph theory.
English language requirement:
IELTS score must be at least 6.5 (with not less than 6.0 in each of the four components). Other, equivalent qualifications will be accepted. Full details of the University’s policy are available online.
Essential attributes:
Experience of fundamental neural networks.
• Competent in graph theory.
• Knowledge of Python and at least one neural network framework (e.g., Keras, tensorflow, pytorch).
• Good written and oral communication skills.
• Strong motivation, with evidence of independent research skills relevant to the project.
• Good time management.
Desirable attributes:
The applicants should motivate their willingness to obtain a PhD degree, attaching a research proposal (max 1 A4 page), describing their ideas and how these align with the scholarships aims and objectives
Funding Notes
This PhD call is fully-funded for 3 years and covers the tuition fees of UK/UE applicants.
Informal Enquires: Dr Valerio Giuffrida (check email address at the footer of the website)