- UHRA Home
- Browsing by Author
Browsing by Author "Glackin, Cornelius"
Now showing items 1-12 of 12
-
Approximation of empowerment in the continuous domain
Salge, Christoph; Glackin, Cornelius; Polani, D. (2012)The empowerment formalism offers a goal-independent utility function fully derived from an agent's embodiment. It produces intrinsic motivations which can be used to generate self-organizing behaviours in agents. One ... -
Changing the Environment Based on Empowerment as Intrinsic Motivation
Salge, Christoph; Glackin, Cornelius; Polani, D. (2014-05-21)One aspect of intelligence is the ability to restructure your own environment so that the world you live in becomes more beneficial to you. In this paper we investigate how the information-theoretic measure of agent ... -
A Comparison Between Convolutional and Transformer Architectures for Speech Emotion Recognition
Iyer, Shreyah; Glackin, Cornelius; Cannings, Nigel; Veneziano, Vito; Sun, Yi (Institute of Electrical and Electronics Engineers (IEEE), 2022-09-30)Creating speech emotion recognition models com-parable to the capability of how humans recognise emotions is a long-standing challenge in the field of speech technology with many potential commercial applications. As ... -
CORBYS cognitive control architecture for robotic follower
Leu, Adrian; Ristic-Durrant, Danijela; Slavnic, Sinisa; Glackin, Cornelius; Salge, Christoph; Polani, D.; Badii, Atta; Khan, Ali; Raval, Rajkumar (Institute of Electrical and Electronics Engineers (IEEE), 2013-12)In this paper the novel generic cognitive robot control architecture CORBYS is presented. The objective of the CORBYS architecture is the integration of high-level cognitive modules to support robot functioning in dynamic ... -
Empowerment : An Introduction
Salge, Christoph; Glackin, Cornelius; Polani, D. (Springer Nature, 2014)This book chapter is an introduction to and an overview of the information-theoretic, task independent utility function "Empowerment", which is defined as the channel capacity between an agent's actions and an agent's ... -
Empowerment and State-dependent Noise : An Intrinsic Motivation for Avoiding Unpredictable Agents
Salge, Christoph; Glackin, Cornelius; Polani, D. (MIT Press, 2013)Empowerment is a recently introduced intrinsic motivation algorithm based on the embodiment of an agent and the dynamics of the world the agent is situated in. Computed as the channel capacity from an agent’s actuators to ... -
Gait Trajectory Prediction using Gaussian Process Ensembles
Glackin, Cornelius; Salge, Christoph; Greaves, Martin; Polani, D.; Slavnić, Siniša; Ristić-Durrant, Danijela; Leu, Adrian; Matjačić, Zlatko (Institute of Electrical and Electronics Engineers (IEEE), 2014)The development of robotic devices for the rehabilitation of gait is a growing area of interest in the engineering rehabilitation community. The problem with modelling gait dynamics is that everybody walks differently. The ... -
Information-theoretic measures as a generic approach to human-robot interaction : Application in CORBYS project
Salge, Christoph; Glackin, Cornelius; Ristić-Durrant, Danijela; Greaves, Martin; Polani, D. (ACM Press, 2014)The objective of the CORBYS project is to design and implement a robot control architecture that allows the integration of high-level cognitive control modules, such as a semantically-driven self-awareness module and a ... -
Investigating HuBERT-based Speech Emotion Recognition Generalisation Capability
Li, Letian; Glackin, Cornelius; Cannings, Nigel; Veneziano, Vito; Barker, Jack; Oduola, Olakunle; Woodruff, Chris; Laird, Thea; Laird, James; Sun, Yi (2024-06-20)Transformer-based architectures have made significant progress in speech emotion recognition (SER). However, most published SER research trained and tested models on data from the same corpus, resulting in poor generalisation ... -
Receptive field optimisation and supervision of a fuzzy spiking neural network
Glackin, Cornelius; Maguire, Liam; McDaid, Liam; Sayers, Heather (2011-04)This paper presents a supervised training algorithm that implements fuzzy reasoning on a spiking neural network. Neuron selectivity is facilitated using receptive fields that enable individual neurons to be responsive to ... -
Spiking neural network connectivity and its potential for temporal sensory processing and variable binding
Wall, Julie; Glackin, Cornelius (2013-12-19) -
Synchrony : A spiking-based mechanism for processing sensory stimuli
Glackin, Cornelius; Maguire, Liam; McDaid, Liam; Wade, John (2012)Synchronous behaviour of neurons is both beneficial and detrimental to the neural code. On the one extreme, synchronous firing activity is well known to be a symptom of epileptic seizures, whilst on the other synchrony ...