Search

Your search keyword '"Elshaw, Mark"' showing total 120 results
Start Over Author "Elshaw, Mark"
120 results on '"Elshaw, Mark"'

1. A Multimodal Hierarchial Approach to Robot Learning by Imitation

Author

Weber, Cornelius, Elshaw, Mark, Zochios, Alex, Wermter, Stefan, Berthouze, Luc, Kozima, Hideki, Prince, Christopher G., Sandini, Giulio, Stojanov, Georgi, Metta, Giorgio, and Balkenius, Christian

Subjects
Computer Science: Machine Learning, Computer Science: Neural Nets, Computer Science: Robotics, Machine Learning, Neural Nets, Robotics
Abstract

In this paper we propose an approach to robot learning by imitation that uses the multimodal inputs of language, vision and motor. In our approach a student robot learns from a teacher robot how to perform three separate behaviours based on these inputs. We considered two neural architectures for performing this robot learning. First, a one-step hierarchial architecture trained with two different learning approaches either based on Kohonen's self-organising map or based on the Helmholtz machine turns out to be inefficient or not capable of performing differentiated behavior. In response we produced a hierarchial architecture that combines both learning approaches to overcome these problems. In doing so the proposed robot system models specific aspects of learning using concepts of the mirror neuron system (Rizzolatti and Arbib, 1998) with regards to demonstration learning.

Published
2004

2. Generative Adversarial Stacked Autoencoders for Facial Pose Normalization and Emotion Recognition

Author

Ruiz-Garcia, Ariel, Palade, Vasile, Elshaw, Mark, and Awad, Mariette

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning
Abstract

In this work, we propose a novel Generative Adversarial Stacked Autoencoder that learns to map facial expressions, with up to plus or minus 60 degrees, to an illumination invariant facial representation of 0 degrees. We accomplish this by using a novel convolutional layer that exploits both local and global spatial information, and a convolutional layer with a reduced number of parameters that exploits facial symmetry. Furthermore, we introduce a generative adversarial gradual greedy layer-wise learning algorithm designed to train Adversarial Autoencoders in an efficient and incremental manner. We demonstrate the efficiency of our method and report state-of-the-art performance on several facial emotion recognition corpora, including one collected in the wild., Comment: Accepted at IJCNN 2020

Published
2020

3. Visual and Thermal Data for Pedestrian and Cyclist Detection

Author

Ahmed, Sarfraz, Huda, M. Nazmul, Rajbhandari, Sujan, Saha, Chitta, Elshaw, Mark, Kanarachos, Stratis, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Althoefer, Kaspar, editor, Konstantinova, Jelizaveta, editor, and Zhang, Ketao, editor

Published
2019
Full Text
View/download PDF

4. Deep Learning for Real Time Facial Expression Recognition in Social Robots

Author

Ruiz-Garcia, Ariel, Webb, Nicola, Palade, Vasile, Eastwood, Mark, Elshaw, Mark, Hutchison, David, Series Editor, Kanade, Takeo, Series Editor, Kittler, Josef, Series Editor, Kleinberg, Jon M., Series Editor, Mattern, Friedemann, Series Editor, Mitchell, John C., Series Editor, Naor, Moni, Series Editor, Pandu Rangan, C., Series Editor, Steffen, Bernhard, Series Editor, Terzopoulos, Demetri, Series Editor, Tygar, Doug, Series Editor, Weikum, Gerhard, Series Editor, Cheng, Long, editor, Leung, Andrew Chi Sing, editor, and Ozawa, Seiichi, editor

Published
2018
Full Text
View/download PDF

6. Emotion Recognition Using Facial Expression Images for a Robotic Companion

Author

Ruiz-Garcia, Ariel, Elshaw, Mark, Altahhan, Abdulrahman, Palade, Vasile, Diniz Junqueira Barbosa, Simone, Series editor, Chen, Phoebe, Series editor, Du, Xiaoyong, Series editor, Filipe, Joaquim, Series editor, Kara, Orhun, Series editor, Kotenko, Igor, Series editor, Liu, Ting, Series editor, Sivalingam, Krishna M., Series editor, Washio, Takashi, Series editor, Jayne, Chrisina, editor, and Iliadis, Lazaros, editor

Published
2016
Full Text
View/download PDF

7. Deep Learning for Emotion Recognition in Faces

Author

Ruiz-Garcia, Ariel, Elshaw, Mark, Altahhan, Abdulrahman, Palade, Vasile, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Villa, Alessandro E.P., editor, Masulli, Paolo, editor, and Pons Rivero, Antonio Javier, editor

Published
2016
Full Text
View/download PDF

12. Grounding Neural Robot Language in Action

Author

Wermter, Stefan, Weber, Cornelius, Elshaw, Mark, Gallese, Vittorio, Pulvermüller, Friedemann, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Carbonell, Jaime G., editor, Siekmann, Jörg, editor, Wermter, Stefan, editor, Palm, Günther, editor, and Elshaw, Mark, editor

Published
2005
Full Text
View/download PDF

13. Towards Biomimetic Neural Learning for Intelligent Robots

Author

Wermter, Stefan, Palm, Günther, Weber, Cornelius, Elshaw, Mark, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Carbonell, Jaime G., editor, Siekmann, Jörg, editor, Wermter, Stefan, editor, Palm, Günther, editor, and Elshaw, Mark, editor

Published
2005
Full Text
View/download PDF

18. Reinforcement Learning in MirrorBot

Author

Weber, Cornelius, Muse, David, Elshaw, Mark, Wermter, Stefan, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Duch, Włodzisław, editor, Kacprzyk, Janusz, editor, Oja, Erkki, editor, and Zadrożny, Sławomir, editor

Published
2005
Full Text
View/download PDF

20. Towards Novel Neuroscience-Inspired Computing

Author

Wermter, Stefan, Elshaw, Mark, Austin, Jim, Willshaw, David, Goos, G., editor, Hartmanis, J., editor, van Leeuwen, J., editor, Carbonell, J. G., editor, Siekmann, J., editor, Wermter, Stefan, editor, Austin, Jim, editor, and Willshaw, David, editor

Published
2001
Full Text
View/download PDF

39. Is one business and management school better than another? A clustering perspective across UK national HE league tables.

Author

Slaich, Amritpal, Yu-Lun Liu, Elshaw, Mark, and Tsun Wai Yuen

Subjects
BUSINESS schools, INDUSTRIAL management, HIGHER education, RANKING, STAKEHOLDERS
Abstract

Higher education (HE) league table rankings have been widely adopted and used by stakeholders such as students and HE institution managers. Nevertheless, criticisms have been raised by researchers. The present study proposes that rather than using league table indicators to make a single, standardised ranking list, indicators of the existing three UK national league tables indicators could be used to form clusters based on the homogeneity of the characteristics of each business and management school. Six groups of business and management schools were extracted and characterised. The approach has removed the notion of saying that one business and management school is better than another (single ranking). Findings offer stakeholders a clearer view of business and management school by identifying groups that best represent the UK business and management school focus. [ABSTRACT FROM AUTHOR]

Published
2018

47. A Camera-Direction Dependent Visual-Motor Coordinate Transformation for a Visually Guided Neural Robot.

Author

Macintosh, Ann, Ellis, Richard, Allen, Tony, Weber, Cornelius, Muse, David, Elshaw, Mark, and Wermter, Stefan

Abstract

Objects of interest are represented in the brain simultaneously in different frames of reference. Knowing the positions of one's head and eyes, for example, one can compute the body-centred position of an object from its perceived coordinates on the retinae. We propose a simple and fully trained attractor network which computes head-centred coordinates given eye position and a perceived retinal object position. We demonstrate this system on artificial data and then apply it within a fully neurally implemented control system which visually guides a simulated robot to a table for grasping an object. The integrated system has as input a primitive visual system with a what-where pathway which localises the target object in the visual field. The coordinate transform network considers the visually perceived object position and the camera pan-tilt angle and computes the target position in a body-centred frame of reference. This position is used by a reinforcement-trained network to dock a simulated PeopleBot robot at a table for reaching the object. Hence, neurally computing coordinate transformations by an attractor network has biological relevance and technical use for this important class of computations. [ABSTRACT FROM AUTHOR]

Published
2006
Full Text
View/download PDF

48. A Scale Invariant Local Image Descriptor for Visual Homing.

Author

Wermter, Stefan, Palm, Günther, Elshaw, Mark, Vardy, Andrew, and Oppacher, Franz

Abstract

A descriptor is presented for characterizing local image patches in a scale invariant manner. The descriptor is biologically-plausible in that the necessary computations are simple and local. Two different methods for robot visual homing based on this descriptor are also presented and tested. The first method utilizes the common technique of corresponding descriptors between images. The second method determines a home vector more directly by finding the stationary local image patch most similar between the two images. We find that the first method exceeds the performance of Franz et. al’s warping method. No statistically significant difference was found between the second method and the warping method. [ABSTRACT FROM AUTHOR]

Published
2005
Full Text
View/download PDF

49. Neural Robot Detection in RoboCup.

Author

Wermter, Stefan, Elshaw, Mark, Mayer, Gerd, Kaufmann, Ulrich, Kraetzschmar, Gerhard, and Palm, Günther

Abstract

Improving the game play in RoboCup middle size league requires a very robust visual opponent and teammate detection system. Because RoboCup games are highly dynamic, the detection system also has to be very fast. That both conditions are not necessarily contradictory is shown in this paper. The described multilevel approach documents, that the combination of a simple color based attention control and a subsequent neural object classification can be applied successfully in real world scenarios. The presented results indicate a very good overall performance regarding robustness, flexibility and computational needs. [ABSTRACT FROM AUTHOR]

Published
2005
Full Text
View/download PDF

50. Modular Learning Schemes for Visual Robot Control.

Author

Wermter, Stefan, Palm, Günther, Elshaw, Mark, Hermann, Gilles, Wira, Patrice, and Urban, Jean-Philippe

Abstract

This chapter explores modular learning in artificial neural networks for intelligent robotics. Mainly inspired from neurobiological aspects, the modularity concept can be used to design artificial neural networks. The main theme of this chapter is to explore the organization, the complexity and the learning of modular artificial neural networks. A robust modular neural architecture is then developed for the position/orientation control of a robot manipulator with visual feedback. Simulations prove that the modular learning enhances the artificial neural networks capabilities to learn and approximate complex problems. The proposed bidirectional modular learning architecture avoids the neural networks well-known limitations. Simulation results on a 7 degrees of freedom robot-vision system are reported to show the performances of the modular approach to learn a high-dimensional nonlinear problem. Modular learning is thus an appropriate solution to robot learning complexity due to limitations on the amount of available training data, the real-time constraint, and the real-world environment. [ABSTRACT FROM AUTHOR]

Published
2005
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results