Connectionists: [jobs] PhD opportunity on ANNs for reinforcement learning, Plymouth, UK

[Torbjorn Dahl]

We are looking for a PhD student on ANNs for reinforcement learning (Topic 2: Learning and Planning with Emergent Hierarchical Representations and Decaying Short-Term Memory) at the Centre for Robotics and Neural Systems at the University of Plymouth, UK.

A brief description of the project is included below.
The application deadline is May 29th, 12noon, UK time.
The project starts October 1st.

Further details on the project, funding and the application procedure can be found at:
https://www.plymouth.ac.uk/student-life/your-studies/the-graduate-school/phd-studentship-at-the-centre-for-robotics-and-neural-systems

Interested candidates are invited to contact the director of studies for an informal consultation.

Best regards,
Torbjorn Dahl
____________________________________________________
Torbjørn S. DAHL, MEng, ACGI, PhD
Lecturer in Software Engineering
Centre for Robotics and Neural Systems
School of Computing and Mathematics, Plymouth University
Drake Circus, Plymouth PL4 8AA, UK
____________________________________________________

Abstract

This project will develop a new generation of artificial neural networks for reinforcement learning (RL), significantly increasing the applicability of RL in areas such as robotics.  The new algorithms will make use of two central features of biological memory to limit their space and time requirements; emergent hierarchical representations and decaying short-term memory (STM). The algorithms developed will use hierarchical memory structures that grow according to a given RL problem.  The hierarchical structures will be made from multiple Kohonen networks and will provide the algorithms’ long-term memory (LTM) capabilities.  The Kohonen networks will be augmented with decaying node activation values providing explicit STM capabilities within a connectionist framework.  The main encoding mechanism in the new algorithms uses the decaying activation values (STM) of one network layer as input to update the weights (LTM) of other layers.  This architecture has allowed us to develop new, more efficient, mechanisms for key RL functions including hidden state identification and future reward estimation.  We have already demonstrated some of these mechanisms using analytical methods and lossless memory encoding (Pierris and Dahl, 2014).  This project will build on those results to produce true connectionist algorithms that can be parallelised, e.g., using Cuda technology.  The work will consider traditional RL benchmarks as well as robot learning problems and will use the University of Plymouth’s Nao or iCub humanoid robots.

Related reference

Pierris G. and Dahl T. S., Humanoid Tactile Gesture Production using a Hierarchical SOM-based Encoding. IEEE Transactions on Autonomous Mental Development, 6(2):153-167, 2014.

________________________________
[http://www.plymouth.ac.uk/images/email_footer.gif]<http://www.plymouth.ac.uk/worldclass>

This email and any files with it are confidential and intended solely for the use of the recipient to whom it is addressed. If you are not the intended recipient then copying, distribution or other use of the information contained is strictly prohibited and you should not rely on it. If you have received this email in error please let the sender know immediately and delete it from your system(s). Internet emails are not necessarily secure. While we take every care, Plymouth University accepts no responsibility for viruses and it is your responsibility to scan emails and their attachments. Plymouth University does not accept responsibility for any changes made after it was sent. Nothing in this email or its attachments constitutes an order for goods or services unless accompanied by an official order form.