Skip to main content

Research Repository

Advanced Search

All Outputs (10)

Dynamic Facial Models for Video-Based Dimensional Affect Estimation (2019)
Conference Proceeding
Song, S., Sánchez-Lozano, E., Kumar Tellamekala, M., Shen, L., Johnston, A., & Valstar, M. (2019). Dynamic Facial Models for Video-Based Dimensional Affect Estimation. In Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) (1608-1617). https://doi.org/10.1109/ICCVW.2019.00200

Dimensional affect estimation from a face video is a challenging task, mainly due to the large number of possible facial displays made up of a set of behaviour primitives including facial muscle actions. The displays vary not only in composition but... Read More about Dynamic Facial Models for Video-Based Dimensional Affect Estimation.

Exploring the capabilities of Projection Augmented Relief Models (PARM) (2017)
Conference Proceeding
Priestnall, G., Goulding, J., Smith, A., & Arss, N. (2017). Exploring the capabilities of Projection Augmented Relief Models (PARM).

This paper explores the broad capabilities of physical landscape models when augmented by projection, termed Projection Augmented Relief Models (PARM). This includes experiences of developing PARM displays in public settings such as museums and visit... Read More about Exploring the capabilities of Projection Augmented Relief Models (PARM).

Interactions with Projected Augmented Relief Models (PARM) (2017)
Conference Proceeding
Arss, N., Smith, A. D., & Priestnall, G. (2017). Interactions with Projected Augmented Relief Models (PARM).

Techniques for enhancing physical landscape models with dynamic maps and imagery, termed Projected Augmented Relief Models (PARM), are part of a revival of interest in the power of relief models as tools for geographic visualization. This method enab... Read More about Interactions with Projected Augmented Relief Models (PARM).

An Introduction to Delay-Coupled Reservoir Computing (2014)
Conference Proceeding
Schumacher, J., Toutounji, H., & Pipa, G. (2014). An Introduction to Delay-Coupled Reservoir Computing. In Artificial Neural Networks: Methods and Applications in Bio-/Neuroinformatics (63-90). https://doi.org/10.1007/978-3-319-09903-3_4

Reservoir computing has been successfully applied in difficult time series prediction tasks by injecting an input signal into a spatially extended reservoir of nonlinear subunits to perform history-dependent nonlinear computation. Recently, the netwo... Read More about An Introduction to Delay-Coupled Reservoir Computing.

Optimized Temporal Multiplexing for Reservoir Computing with a Single Delay-Coupled Node (2014)
Conference Proceeding
TOUTOUNJI, H., Schumacher, J., & Pipa, G. (2014). Optimized Temporal Multiplexing for Reservoir Computing with a Single Delay-Coupled Node. https://doi.org/10.15248/proc.1.519

The computational performance of reservoir computers based on a single delay-coupled node is critically dependent on the temporal multiplexing of input to the reservoir. Here we present an optimization of the temporal multiplexing by means of optimiz... Read More about Optimized Temporal Multiplexing for Reservoir Computing with a Single Delay-Coupled Node.

An Analytical Approach to Single Node Delay-Coupled Reservoir Computing (2013)
Conference Proceeding
Schumacher, J., Toutounji, H., & Pipa, G. (2013). An Analytical Approach to Single Node Delay-Coupled Reservoir Computing. In Artificial Neural Networks and Machine Learning – ICANN 2013 23rd International Conference on Artificial Neural Networks Sofia, Bulgaria, September 10-13, 2013. Proceedings (26-33). https://doi.org/10.1007/978-3-642-40728-4_4

Reservoir computing has been successfully applied in difficult time series prediction tasks by injecting an input signal into a spatially extended reservoir of nonlinear subunits to perform history-dependent nonlinear computation. Recently, the netwo... Read More about An Analytical Approach to Single Node Delay-Coupled Reservoir Computing.

Scalable reinforcement learning through hierarchical decompositions for weakly-coupled problems (2011)
Conference Proceeding
Toutounji, H., Rothkopf, C. A., & Triesch, J. (2011). Scalable reinforcement learning through hierarchical decompositions for weakly-coupled problems. In 2011 IEEE International Conference on Development and Learning (ICDL). https://doi.org/10.1109/devlrn.2011.6037351

Reinforcement Learning, or Reward-Dependent Learning, has been very successful at describing how animals and humans adjust their actions so as to increase their gains and reduce their losses in a wide variety of tasks. Empirical studies have furtherm... Read More about Scalable reinforcement learning through hierarchical decompositions for weakly-coupled problems.

On Randomness and the Genetic Behavior of Cellular Automata (2008)
Conference Proceeding
Toutounji, H., & Aljundi, A. C. (2008). On Randomness and the Genetic Behavior of Cellular Automata. In 2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications. https://doi.org/10.1109/ICTTA.2008.4530320

We investigate a new approach in utilizing a given classification to cellular automata to search for a particular behavior cellular automaton with a genetic algorithm. This investigation leads to the formation of two new concepts. The first is creati... Read More about On Randomness and the Genetic Behavior of Cellular Automata.

Is Experts' Knowledge Modular? (2001)
Conference Proceeding
Gobet, F. (2001). Is Experts' Knowledge Modular?.

This paper explores, both with empirical data and with computer simulations, the extent to which modularity characterises experts' knowledge. We discuss a replication of Chase and Simon's (1973) classic method of identifying 'chunks', i.e., perceptua... Read More about Is Experts' Knowledge Modular?.