Don't miss our weekly PhD newsletter | Sign up now Don't miss our weekly PhD newsletter | Sign up now

  Next-Generation Spiking Neural Networks Architectures and Machine Learning Algorithms

   School of Engineering

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  Prof Daniel Coca  Applications accepted all year round  Self-Funded PhD Students Only

About the Project

Spiking Neural Networks (SNNs) represent the so called ‘third generation’ of artificial neural network models, that bridge the gap between neuroscience and artificial intelligence by relying on biologically realistic models of neurons and network architectures to carry out computations. Specifically, Information transfer between the neurons in the spiking neural network is via the precise timing of spikes generated by the individual neurons.  

SNNs exploit temporal encoding and asynchronous processing to perform complex information processing and learning tasks in a fast and efficient manner. This makes SNNs suitable for real-time applications that that exploit energy-efficient neuromorphic hardware platforms rather than conventional microprocessor-based systems. 

SNNs have been shown to be as computationally powerful as conventional artificial neural networks (ANNs). However, SNNs have not quite reached the same accuracy levels of ANNs in traditional machine learning tasks largely because of the lack of adequate training algorithms for deep SNNs. The non-differentiable nature of spike events precludes the direct application of gradient descent methods that are by far the most widely used algorithms for training deep neural networks.  

The problem of synthesizing sparse, energy-efficient spiking neural circuits that perform desired computations from individual spiking neurons as well as simple, previously characterised neural circuits is still an open question.  

This project aims to advance the theoretical foundations of spiking neural networks and develop new spike-based methodologies for synthesizing and training spiking neural networks that perform conventional machine learning tasks, implement optimal control policies or provide biologically realistic models of neural computations.  

Numerical simulations will be carried out in MATLAB, C/C++, Python. Optional, depending on interest and experience, simulations could be implemented on neuromorphic hardware such as Intel’s Loihi neuromorphic chip. 

Entry Requirements  

To be considered for the project, candidates must be highly motivated and should possess a 1st Class honours undergraduate degree or MSc Distinction (or international equivalent) in Engineering, Computer Science, Mathematics, Physics, or a closely related subject. Outstanding candidates with an upper 2nd Class degree may also be considered. Good programming skills and experience with Python and/or Matlab is essential. 

Newcastle University is committed to being a fully inclusive Global University which actively recruits, supports and retains colleagues from all sectors of society.  We value diversity as well as celebrate, support and thrive on the contributions of all our employees and the communities they represent.  We are proud to be an equal opportunities employer and encourage applications from everybody, regardless of race, sex, ethnicity, religion, nationality, sexual orientation, age, disability, gender identity, marital status/civil partnership, pregnancy and maternity, as well as being open to flexible working practices. 

Application enquiries: 

Daniel Coca, [Email Address Removed], 

Computer Science (8) Engineering (12)
Search Suggestions
Search suggestions

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

 About the Project