Tips on how to manage your PhD stipend FIND OUT MORE
Martin Luther University of Halle-Wittenberg Featured PhD Programmes
University of West London Featured PhD Programmes
Queen’s University Belfast Featured PhD Programmes

Biologically-plausible neural network models of movement control algorithms


Department of Computer Science

About the Project

A number of neural network implementations of control theory algorithms have been proposed, especially with the recent rise of machine learning. However, most current implementations are biologically unrealistic either in their mechanisms or in their learning algorithms. Considering mechanism, spiking neural network implementations of control algorithms have the potential of being deployed in neuromorphic hardware and neuro-robotics for energy-efficient portable robotics, as well as suggesting neural circuits for biological movement control. Considering the issue of learning, backpropagation of error (derived from gradient descent) is the key technique for deep learning in artificial neural networks. Even though artificial neural networks are inspired by the brain, it is unclear if learning in the brain utilises (an approximation of) backpropagation of error. Learning in the brain happens via synaptic plasticity, which being a physical process and not an algorithm, has to depend on quantities available physically near the synapse at the current time, i.e. the learning rule has to be local in space and time. However, standard backpropagation does not fulfill this criterion.

In this PhD project, we will distill the benefits of various control theory approaches into a spiking neural network model, that is biologically plausible in mechanism, architecture and learning, and possibly outperforms similar current approaches. We will benchmark these control networks on biological limb and prosthetic models. We will compare these networks with experimental data and port them to neuromorphic hardware as well.

A background in Control theory, Physics and/or Computational neuroscience, with good coding skills, is desirable.

If English is not your first language, you must have an IELTS score of 6.5 overall, with no less than 6.0 in each component. More details regarding English Language Qualifications can be found here - https://www.sheffield.ac.uk/postgraduate/english-language

To apply for the project, applicants need to apply directly to the University of Sheffield using the online application system. Complete an application for admission to the standard Computer Science PhD programme
http://www.sheffield.ac.uk/postgraduate/research/apply

Please name Dr Aditya Gilra as your proposed supervisor in your application.

Applications should include a research proposal, transcripts and two references.
The research proposal (up to 4 A4 pages, including references) should outline your reasons for applying for this project and how you would approach the researching, including details of your skills and experience.

Funding Notes

Currently, only students with their own funding can be considered.

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here

The information you submit to University of Sheffield will only be used by them or their data partners to deal with your enquiry, according to their privacy notice. For more information on how we use and store your data, please read our privacy statement.

* required field

Your enquiry has been emailed successfully



Search Suggestions

Search Suggestions

Based on your current searches we recommend the following search filters.



FindAPhD. Copyright 2005-2021
All rights reserved.