Nigel Crook | Oxford Brookes University (original) (raw)

Papers by Nigel Crook

Research paper thumbnail of Interaction strategies for an affective conversational agent

Abstract The development of embodied conversational agents (ECA) as companions brings several cha... more Abstract The development of embodied conversational agents (ECA) as companions brings several challenges for both affective and conversational dialogue. These include challenges in generating appropriate affective responses, selecting the overall shape of the dialogue, providing prompt system response times, and handling interruptions. We present an implementation of such a companion showing the development of individual modules that attempt to address these challenges.

Research paper thumbnail of Interaction strategies for an affective conversational agent

Abstract The development of embodied conversational agents (ECA) as companions brings several cha... more Abstract The development of embodied conversational agents (ECA) as companions brings several challenges for both affective and conversational dialogue. These include challenges in generating appropriate affective responses, selecting the overall shape of the dialogue, providing prompt system response times, and handling interruptions. We present an implementation of such a companion showing the development of individual modules that attempt to address these challenges.

Research paper thumbnail of Generating context-sensitive ECA responses to user barge-in interruptions

Abstract We present an Embodied Conversational Agent (ECA) that incorporates a context-sensitive ... more Abstract We present an Embodied Conversational Agent (ECA) that incorporates a context-sensitive mechanism for handling user barge-in. The affective ECA engages the user in social conversation, and is fully implemented. We will use actual examples of system behaviour to illustrate. The ECA is designed to recognise and be empathetic to the emotional state of the user. It is able to detect, react quickly to, and then follow up with considered responses to different kinds of user interruptions.

Research paper thumbnail of Parallel Processing of Interruptions and Feedback in Companions Affective Dialogue System

Research paper thumbnail of Roadmap in Chaotic Neural Networks

Research paper thumbnail of Adaptation in Chaotic Spiking Neural Networks

Research paper thumbnail of Rule extraction from neural networks

Research paper thumbnail of An adaptive chaotic neural network

Abstract The non-linear dynamics of a chaotic attractor offer a number of useful features to the ... more Abstract The non-linear dynamics of a chaotic attractor offer a number of useful features to the developer of neuromorphic systems. Included in these is the ability for efficient memory storage and recall. A chaotic attractor has a potentially infinite number of unstable periodic orbits (UPO) embedded within it. These orbits can be stabilised with the application of delayed feedback inhibition. This research investigates the possibility of using such delayed feedback in a network to stabilise different UPOs in response to disparate input stimuli.

Research paper thumbnail of Simultaneous Human Segmentation, Depth and Pose Estimation via Dual Decomposition

Abstract The tasks of stereo matching, segmentation, and human pose estimation have been popular ... more Abstract The tasks of stereo matching, segmentation, and human pose estimation have been popular in computer vision in recent years, but attempts to combine the three tasks have so far resulted in compromises: either using infra-red cameras, or a greatly simplified body model. We propose a framework for estimating a detailed human skeleton in 3D from a stereo pair of images.

Research paper thumbnail of 'How was your day?': an affective companion ECA prototype

Abstract This paper presents a dialogue system in the form of an ECA that acts as a sociable and ... more Abstract This paper presents a dialogue system in the form of an ECA that acts as a sociable and emotionally intelligent companion for the user. The system dialogue is not task-driven but is social conversation in which the user talks about his/her day at the office. During conversations the system monitors the emotional state of the user and uses that information to inform its dialogue turns. The system is able to respond to spoken interruptions by the user, for example, the user can interrupt to correct the system.

Research paper thumbnail of A chaotic basis for neural coding

Abstract. Recent neurobiological data has demonstrated that some neurons communicate with each ot... more Abstract. Recent neurobiological data has demonstrated that some neurons communicate with each other via the timing of individual spikes. The possibility of a neural code based on time-structured spike trains is a departure from established theories based on rate coding. Precisely how these time-structured spike trains communicate information is still open for debate. In this paper we consider the possibility that these spike trains communicate discrete internal neuronal states that are generated from the stabilised orbits of a chaotic attractor.

Research paper thumbnail of Pattern recognition using chaotic transients

Abstract. This paper proposes a novel nonlinear transient computation device described as the LTC... more Abstract. This paper proposes a novel nonlinear transient computation device described as the LTCM that uses the chaotic attractor provided by the Lorenz system of equations to perform pattern recognition. Previous work on nonlinear transient computation has demonstrated that such devices can process time varying input signals. This paper investigates the ability of the LTCM to correctly classify static, linearly inseperable data sets commonly used as benchmarks in the pattern recognition research community.

Research paper thumbnail of Efficient Discriminative Learning of Parametric Nearest Neighbor Classifiers

Abstract Linear SVMs are efficient in both training and testing, however the data in real applicat... more Abstract Linear SVMs are efficient in both training and testing, however the data in real applications is rarely linearly separable. Non-linear kernel SVMs are too computationally intensive for applications with large-scale data sets. Recently locally linear classifiers have gained popularity due to their efficiency whilst remaining competitive with kernel methods. The vanilla nearest neighbor algorithm is one of the simplest locally linear classifiers, but it lacks robustness due to the noise often present in real-world data.

Research paper thumbnail of Scalable Cascade Inference for Semantic Image Segmentation

Abstract Semantic image segmentation is a problem of simultaneous segmentation and recognition of... more Abstract Semantic image segmentation is a problem of simultaneous segmentation and recognition of an input image into regions and their associated categorical labels, such as person, car or cow. A popular way to achieve this goal is to assign a label to every pixel in the input image and impose simple structural constraints on the output label space.

Research paper thumbnail of Generating context-sensitive ECA responses to user barge-in interruptions

We present an Embodied Conversational Agent (ECA) that incorporates a context-sensitive mechanism... more We present an Embodied Conversational Agent (ECA) that incorporates a context-sensitive mechanism for handling user barge-in. The affective ECA engages the user in social
conversation, and is fully implemented. We will use actual examples of system behaviour to illustrate. The ECA is designed to recognise and be empathetic to the emotional state of the user. It is able to detect, react quickly to, and then follow up with considered responses to different kinds of user interruptions. The
design of the rules which enable the ECA to respond intelligently to different types of interruptions was informed by manually
analysed real data from human--human dialogue. The rules represent recoveries from interruptions as two-part structures: an address followed by a resumption. The system is robust enough to manage long, multi-utterance turns by both user and system, which creates good opportunities for the user to interrupt while the ECA is speaking.

Research paper thumbnail of Using Input Parameter Influences to Support the Decisions of Feedforward Neural Networks

Neurocomputing, Jan 1, 1999

Whilst rules extracted from neural networks assist the explanation process, in isolation they do ... more Whilst rules extracted from neural networks assist the explanation process, in isolation they do not illustrate the relative importance of each input parameter nor how sensitive the network's output is to these parameters. In this paper we discuss three related measures of input parameter influence which can be used to support explanation facilities for neural networks. An algorithm for generating rules from real-valued networks based on the influence measures is also presented.

Research paper thumbnail of Self-Organised Dynamic Recognition States for Chaotic Neural Networks

Information Sciences, Jan 1, 2003

Research paper thumbnail of The Nonlinear Dynamic State Neuron

Research paper thumbnail of A Novel Chaotic Neural Network Architecture

Research paper thumbnail of Nonlinear Transient Computation

Neurocomputing, Jan 1, 2007

Research paper thumbnail of Interaction strategies for an affective conversational agent

Abstract The development of embodied conversational agents (ECA) as companions brings several cha... more Abstract The development of embodied conversational agents (ECA) as companions brings several challenges for both affective and conversational dialogue. These include challenges in generating appropriate affective responses, selecting the overall shape of the dialogue, providing prompt system response times, and handling interruptions. We present an implementation of such a companion showing the development of individual modules that attempt to address these challenges.

Research paper thumbnail of Interaction strategies for an affective conversational agent

Abstract The development of embodied conversational agents (ECA) as companions brings several cha... more Abstract The development of embodied conversational agents (ECA) as companions brings several challenges for both affective and conversational dialogue. These include challenges in generating appropriate affective responses, selecting the overall shape of the dialogue, providing prompt system response times, and handling interruptions. We present an implementation of such a companion showing the development of individual modules that attempt to address these challenges.

Research paper thumbnail of Generating context-sensitive ECA responses to user barge-in interruptions

Abstract We present an Embodied Conversational Agent (ECA) that incorporates a context-sensitive ... more Abstract We present an Embodied Conversational Agent (ECA) that incorporates a context-sensitive mechanism for handling user barge-in. The affective ECA engages the user in social conversation, and is fully implemented. We will use actual examples of system behaviour to illustrate. The ECA is designed to recognise and be empathetic to the emotional state of the user. It is able to detect, react quickly to, and then follow up with considered responses to different kinds of user interruptions.

Research paper thumbnail of Parallel Processing of Interruptions and Feedback in Companions Affective Dialogue System

Research paper thumbnail of Roadmap in Chaotic Neural Networks

Research paper thumbnail of Adaptation in Chaotic Spiking Neural Networks

Research paper thumbnail of Rule extraction from neural networks

Research paper thumbnail of An adaptive chaotic neural network

Abstract The non-linear dynamics of a chaotic attractor offer a number of useful features to the ... more Abstract The non-linear dynamics of a chaotic attractor offer a number of useful features to the developer of neuromorphic systems. Included in these is the ability for efficient memory storage and recall. A chaotic attractor has a potentially infinite number of unstable periodic orbits (UPO) embedded within it. These orbits can be stabilised with the application of delayed feedback inhibition. This research investigates the possibility of using such delayed feedback in a network to stabilise different UPOs in response to disparate input stimuli.

Research paper thumbnail of Simultaneous Human Segmentation, Depth and Pose Estimation via Dual Decomposition

Abstract The tasks of stereo matching, segmentation, and human pose estimation have been popular ... more Abstract The tasks of stereo matching, segmentation, and human pose estimation have been popular in computer vision in recent years, but attempts to combine the three tasks have so far resulted in compromises: either using infra-red cameras, or a greatly simplified body model. We propose a framework for estimating a detailed human skeleton in 3D from a stereo pair of images.

Research paper thumbnail of 'How was your day?': an affective companion ECA prototype

Abstract This paper presents a dialogue system in the form of an ECA that acts as a sociable and ... more Abstract This paper presents a dialogue system in the form of an ECA that acts as a sociable and emotionally intelligent companion for the user. The system dialogue is not task-driven but is social conversation in which the user talks about his/her day at the office. During conversations the system monitors the emotional state of the user and uses that information to inform its dialogue turns. The system is able to respond to spoken interruptions by the user, for example, the user can interrupt to correct the system.

Research paper thumbnail of A chaotic basis for neural coding

Abstract. Recent neurobiological data has demonstrated that some neurons communicate with each ot... more Abstract. Recent neurobiological data has demonstrated that some neurons communicate with each other via the timing of individual spikes. The possibility of a neural code based on time-structured spike trains is a departure from established theories based on rate coding. Precisely how these time-structured spike trains communicate information is still open for debate. In this paper we consider the possibility that these spike trains communicate discrete internal neuronal states that are generated from the stabilised orbits of a chaotic attractor.

Research paper thumbnail of Pattern recognition using chaotic transients

Abstract. This paper proposes a novel nonlinear transient computation device described as the LTC... more Abstract. This paper proposes a novel nonlinear transient computation device described as the LTCM that uses the chaotic attractor provided by the Lorenz system of equations to perform pattern recognition. Previous work on nonlinear transient computation has demonstrated that such devices can process time varying input signals. This paper investigates the ability of the LTCM to correctly classify static, linearly inseperable data sets commonly used as benchmarks in the pattern recognition research community.

Research paper thumbnail of Efficient Discriminative Learning of Parametric Nearest Neighbor Classifiers

Abstract Linear SVMs are efficient in both training and testing, however the data in real applicat... more Abstract Linear SVMs are efficient in both training and testing, however the data in real applications is rarely linearly separable. Non-linear kernel SVMs are too computationally intensive for applications with large-scale data sets. Recently locally linear classifiers have gained popularity due to their efficiency whilst remaining competitive with kernel methods. The vanilla nearest neighbor algorithm is one of the simplest locally linear classifiers, but it lacks robustness due to the noise often present in real-world data.

Research paper thumbnail of Scalable Cascade Inference for Semantic Image Segmentation

Abstract Semantic image segmentation is a problem of simultaneous segmentation and recognition of... more Abstract Semantic image segmentation is a problem of simultaneous segmentation and recognition of an input image into regions and their associated categorical labels, such as person, car or cow. A popular way to achieve this goal is to assign a label to every pixel in the input image and impose simple structural constraints on the output label space.

Research paper thumbnail of Generating context-sensitive ECA responses to user barge-in interruptions

We present an Embodied Conversational Agent (ECA) that incorporates a context-sensitive mechanism... more We present an Embodied Conversational Agent (ECA) that incorporates a context-sensitive mechanism for handling user barge-in. The affective ECA engages the user in social
conversation, and is fully implemented. We will use actual examples of system behaviour to illustrate. The ECA is designed to recognise and be empathetic to the emotional state of the user. It is able to detect, react quickly to, and then follow up with considered responses to different kinds of user interruptions. The
design of the rules which enable the ECA to respond intelligently to different types of interruptions was informed by manually
analysed real data from human--human dialogue. The rules represent recoveries from interruptions as two-part structures: an address followed by a resumption. The system is robust enough to manage long, multi-utterance turns by both user and system, which creates good opportunities for the user to interrupt while the ECA is speaking.

Research paper thumbnail of Using Input Parameter Influences to Support the Decisions of Feedforward Neural Networks

Neurocomputing, Jan 1, 1999

Whilst rules extracted from neural networks assist the explanation process, in isolation they do ... more Whilst rules extracted from neural networks assist the explanation process, in isolation they do not illustrate the relative importance of each input parameter nor how sensitive the network's output is to these parameters. In this paper we discuss three related measures of input parameter influence which can be used to support explanation facilities for neural networks. An algorithm for generating rules from real-valued networks based on the influence measures is also presented.

Research paper thumbnail of Self-Organised Dynamic Recognition States for Chaotic Neural Networks

Information Sciences, Jan 1, 2003

Research paper thumbnail of The Nonlinear Dynamic State Neuron

Research paper thumbnail of A Novel Chaotic Neural Network Architecture

Research paper thumbnail of Nonlinear Transient Computation

Neurocomputing, Jan 1, 2007