The Experts below are selected from a list of 123 Experts worldwide ranked by ideXlab platform
Tara J. Hamilton - One of the best experts on this subject based on the ideXlab platform.
-
The ripple pond: enabling spiking networks to see.
Frontiers in Neuroscience, 2013Co-Authors: Salim Afshar, Torsten Lehmann, Jonathan Tapson, Gregory Cohen, Runchun Wang, André Van Schaik, Tara J. HamiltonAbstract:We present the biologically inspired Ripple Pond Network (RPN), a simply connected spiking neural network which performs a transformation converting two dimensional images to one dimensional temporal patterns suitable for recognition by temporal coding learning and memory networks. The RPN has been developed as a hardware solution linking previously implemented neuromorphic vision and memory structures such as frameless vision sensors and neuromorphic temporal coding spiking neural networks. Working together such systems are potentially capable of delivering end-to-end high-speed, low-power and low-resolution recognition for mobile and autonomous applications where slow, highly sophisticated and power hungry signal processing solutions are ineffective. Key aspects in the proposed approach include utilising the spatial properties of physically embedded neural networks and propagating waves of activity therein for Information processing, using dimensional collapse of imagery Information into amenable temporal patterns and the use of asynchronous frames for Information Binding.
-
The Ripple Pond: Enabling Spiking Networks to See
arXiv: Neural and Evolutionary Computing, 2013Co-Authors: Salim Afshar, Torsten Lehmann, Jonathan Tapson, Gregory Cohen, Runchun Wang, André Van Schaik, Tara J. HamiltonAbstract:In this paper we present the biologically inspired Ripple Pond Network (RPN), a simply connected spiking neural network that, operating together with recently proposed PolyChronous Networks (PCN), enables rapid, unsupervised, scale and rotation invariant object recognition using efficient spatio-temporal spike coding. The RPN has been developed as a hardware solution linking previously implemented neuromorphic vision and memory structures capable of delivering end-to-end high-speed, low-power and low-resolution recognition for mobile and autonomous applications where slow, highly sophisticated and power hungry signal processing solutions are ineffective. Key aspects in the proposed approach include utilising the spatial properties of physically embedded neural networks and propagating waves of activity therein for Information processing, using dimensional collapse of imagery Information into amenable temporal patterns and the use of asynchronous frames for Information Binding.
-
The ripple pond: Enabling spiking networks to see
Frontiers in Neuroscience, 2013Co-Authors: Salim Afshar, Runchun M. Wang, Antoinette Van Schaik, Gregory K. Cohen, Torsten Lehmann, Jonathan Tapson, Tara J. HamiltonAbstract:We present the biologically inspired Ripple Pond Network (RPN), a simply connected spiking neural network which performs a transformation converting two dimensional images to one dimensional temporal patterns (TP) suitable for recognition by temporal coding learning and memory networks. The RPN has been developed as a hardware solution linking previously implemented neuromorphic vision and memory structures such as frameless vision sensors and neuromorphic temporal coding spiking neural networks. Working together such systems are potentially capable of delivering end-to-end high-speed, low-power and low-resolution recognition for mobile and autonomous applications where slow, highly sophisticated and power hungry signal processing solutions are ineffective. Key aspects in the proposed approach include utilizing the spatial properties of physically embedded neural networks and propagating waves of activity therein for Information processing, using dimensional collapse of imagery Information into amenable TP and the use of asynchronous frames for Information Binding.
Luís Garcia Dominguez - One of the best experts on this subject based on the ideXlab platform.
-
Phase synchronization measurements using electroencephalographic recordings
Neuroinformatics, 2005Co-Authors: Ramón Guevara, José Luis Pérez Velazquez, Vera Nenadovic, Richard Wennberg, Goran Senjanović, Luís Garcia DominguezAbstract:Phase synchrony analysis is a relatively new concept that is being increasingly used on neurophysiological data obtained through different methodologies. It is currently believed that phase synchrony is an important signature of Information Binding between distant sites of the brain, especially during cognitive tasks. Electroencephalographic (EEG) recordings are the most widely used recording technique for recording brain signals and assessing phase synchrony patterns. In this study, we address the suitability of phase synchrony analysis in EEG recordings. Using geometrical arguments and numerical examples, employing EEG and magnetoencephalographic data, we show that the presence of a common reference signal in the case of EEG recordings results in a distortion of the synchrony values observed, in that the amplitudes of the signals influence the synchrony measured, and in general destroys the intended physical interpretation of phase synchrony.
-
Phase synchronization measurements using electroencephalographic recordings: what can we really say about neuronal synchrony?
Neuroinformatics, 2005Co-Authors: Ramón Guevara, José Luis Pérez Velazquez, Vera Nenadovic, Richard Wennberg, Goran Senjanović, Luís Garcia DominguezAbstract:Phase synchrony analysis is a relatively new concept that is being increasingly used on neurophysiological data obtained through different methodologies. It is currently believed that phase synchrony is an important signature of Information Binding between distant sites of the brain, especially during cognitive tasks. Electroencephalographic (EEG) recordings are the most widely used recording technique for recording brain signals and assessing phase synchrony patterns. In this study, we address the suitability of phase synchrony analysis in EEG recordings. Using geometrical arguments and numerical examples, employing EEG and magnetoencephalographic data, we show that the presence of a common reference signal in the case of EEG recordings results in a distortion of the synchrony values observed, in that the amplitudes of the signals influence the synchrony measured, and in general destroys the intended physical interpretation of phase synchrony.
Salim Afshar - One of the best experts on this subject based on the ideXlab platform.
-
The ripple pond: enabling spiking networks to see.
Frontiers in Neuroscience, 2013Co-Authors: Salim Afshar, Torsten Lehmann, Jonathan Tapson, Gregory Cohen, Runchun Wang, André Van Schaik, Tara J. HamiltonAbstract:We present the biologically inspired Ripple Pond Network (RPN), a simply connected spiking neural network which performs a transformation converting two dimensional images to one dimensional temporal patterns suitable for recognition by temporal coding learning and memory networks. The RPN has been developed as a hardware solution linking previously implemented neuromorphic vision and memory structures such as frameless vision sensors and neuromorphic temporal coding spiking neural networks. Working together such systems are potentially capable of delivering end-to-end high-speed, low-power and low-resolution recognition for mobile and autonomous applications where slow, highly sophisticated and power hungry signal processing solutions are ineffective. Key aspects in the proposed approach include utilising the spatial properties of physically embedded neural networks and propagating waves of activity therein for Information processing, using dimensional collapse of imagery Information into amenable temporal patterns and the use of asynchronous frames for Information Binding.
-
The Ripple Pond: Enabling Spiking Networks to See
arXiv: Neural and Evolutionary Computing, 2013Co-Authors: Salim Afshar, Torsten Lehmann, Jonathan Tapson, Gregory Cohen, Runchun Wang, André Van Schaik, Tara J. HamiltonAbstract:In this paper we present the biologically inspired Ripple Pond Network (RPN), a simply connected spiking neural network that, operating together with recently proposed PolyChronous Networks (PCN), enables rapid, unsupervised, scale and rotation invariant object recognition using efficient spatio-temporal spike coding. The RPN has been developed as a hardware solution linking previously implemented neuromorphic vision and memory structures capable of delivering end-to-end high-speed, low-power and low-resolution recognition for mobile and autonomous applications where slow, highly sophisticated and power hungry signal processing solutions are ineffective. Key aspects in the proposed approach include utilising the spatial properties of physically embedded neural networks and propagating waves of activity therein for Information processing, using dimensional collapse of imagery Information into amenable temporal patterns and the use of asynchronous frames for Information Binding.
-
The ripple pond: Enabling spiking networks to see
Frontiers in Neuroscience, 2013Co-Authors: Salim Afshar, Runchun M. Wang, Antoinette Van Schaik, Gregory K. Cohen, Torsten Lehmann, Jonathan Tapson, Tara J. HamiltonAbstract:We present the biologically inspired Ripple Pond Network (RPN), a simply connected spiking neural network which performs a transformation converting two dimensional images to one dimensional temporal patterns (TP) suitable for recognition by temporal coding learning and memory networks. The RPN has been developed as a hardware solution linking previously implemented neuromorphic vision and memory structures such as frameless vision sensors and neuromorphic temporal coding spiking neural networks. Working together such systems are potentially capable of delivering end-to-end high-speed, low-power and low-resolution recognition for mobile and autonomous applications where slow, highly sophisticated and power hungry signal processing solutions are ineffective. Key aspects in the proposed approach include utilizing the spatial properties of physically embedded neural networks and propagating waves of activity therein for Information processing, using dimensional collapse of imagery Information into amenable TP and the use of asynchronous frames for Information Binding.
Torsten Lehmann - One of the best experts on this subject based on the ideXlab platform.
-
The ripple pond: enabling spiking networks to see.
Frontiers in Neuroscience, 2013Co-Authors: Salim Afshar, Torsten Lehmann, Jonathan Tapson, Gregory Cohen, Runchun Wang, André Van Schaik, Tara J. HamiltonAbstract:We present the biologically inspired Ripple Pond Network (RPN), a simply connected spiking neural network which performs a transformation converting two dimensional images to one dimensional temporal patterns suitable for recognition by temporal coding learning and memory networks. The RPN has been developed as a hardware solution linking previously implemented neuromorphic vision and memory structures such as frameless vision sensors and neuromorphic temporal coding spiking neural networks. Working together such systems are potentially capable of delivering end-to-end high-speed, low-power and low-resolution recognition for mobile and autonomous applications where slow, highly sophisticated and power hungry signal processing solutions are ineffective. Key aspects in the proposed approach include utilising the spatial properties of physically embedded neural networks and propagating waves of activity therein for Information processing, using dimensional collapse of imagery Information into amenable temporal patterns and the use of asynchronous frames for Information Binding.
-
The Ripple Pond: Enabling Spiking Networks to See
arXiv: Neural and Evolutionary Computing, 2013Co-Authors: Salim Afshar, Torsten Lehmann, Jonathan Tapson, Gregory Cohen, Runchun Wang, André Van Schaik, Tara J. HamiltonAbstract:In this paper we present the biologically inspired Ripple Pond Network (RPN), a simply connected spiking neural network that, operating together with recently proposed PolyChronous Networks (PCN), enables rapid, unsupervised, scale and rotation invariant object recognition using efficient spatio-temporal spike coding. The RPN has been developed as a hardware solution linking previously implemented neuromorphic vision and memory structures capable of delivering end-to-end high-speed, low-power and low-resolution recognition for mobile and autonomous applications where slow, highly sophisticated and power hungry signal processing solutions are ineffective. Key aspects in the proposed approach include utilising the spatial properties of physically embedded neural networks and propagating waves of activity therein for Information processing, using dimensional collapse of imagery Information into amenable temporal patterns and the use of asynchronous frames for Information Binding.
-
The ripple pond: Enabling spiking networks to see
Frontiers in Neuroscience, 2013Co-Authors: Salim Afshar, Runchun M. Wang, Antoinette Van Schaik, Gregory K. Cohen, Torsten Lehmann, Jonathan Tapson, Tara J. HamiltonAbstract:We present the biologically inspired Ripple Pond Network (RPN), a simply connected spiking neural network which performs a transformation converting two dimensional images to one dimensional temporal patterns (TP) suitable for recognition by temporal coding learning and memory networks. The RPN has been developed as a hardware solution linking previously implemented neuromorphic vision and memory structures such as frameless vision sensors and neuromorphic temporal coding spiking neural networks. Working together such systems are potentially capable of delivering end-to-end high-speed, low-power and low-resolution recognition for mobile and autonomous applications where slow, highly sophisticated and power hungry signal processing solutions are ineffective. Key aspects in the proposed approach include utilizing the spatial properties of physically embedded neural networks and propagating waves of activity therein for Information processing, using dimensional collapse of imagery Information into amenable TP and the use of asynchronous frames for Information Binding.
Jonathan Tapson - One of the best experts on this subject based on the ideXlab platform.
-
The ripple pond: enabling spiking networks to see.
Frontiers in Neuroscience, 2013Co-Authors: Salim Afshar, Torsten Lehmann, Jonathan Tapson, Gregory Cohen, Runchun Wang, André Van Schaik, Tara J. HamiltonAbstract:We present the biologically inspired Ripple Pond Network (RPN), a simply connected spiking neural network which performs a transformation converting two dimensional images to one dimensional temporal patterns suitable for recognition by temporal coding learning and memory networks. The RPN has been developed as a hardware solution linking previously implemented neuromorphic vision and memory structures such as frameless vision sensors and neuromorphic temporal coding spiking neural networks. Working together such systems are potentially capable of delivering end-to-end high-speed, low-power and low-resolution recognition for mobile and autonomous applications where slow, highly sophisticated and power hungry signal processing solutions are ineffective. Key aspects in the proposed approach include utilising the spatial properties of physically embedded neural networks and propagating waves of activity therein for Information processing, using dimensional collapse of imagery Information into amenable temporal patterns and the use of asynchronous frames for Information Binding.
-
The Ripple Pond: Enabling Spiking Networks to See
arXiv: Neural and Evolutionary Computing, 2013Co-Authors: Salim Afshar, Torsten Lehmann, Jonathan Tapson, Gregory Cohen, Runchun Wang, André Van Schaik, Tara J. HamiltonAbstract:In this paper we present the biologically inspired Ripple Pond Network (RPN), a simply connected spiking neural network that, operating together with recently proposed PolyChronous Networks (PCN), enables rapid, unsupervised, scale and rotation invariant object recognition using efficient spatio-temporal spike coding. The RPN has been developed as a hardware solution linking previously implemented neuromorphic vision and memory structures capable of delivering end-to-end high-speed, low-power and low-resolution recognition for mobile and autonomous applications where slow, highly sophisticated and power hungry signal processing solutions are ineffective. Key aspects in the proposed approach include utilising the spatial properties of physically embedded neural networks and propagating waves of activity therein for Information processing, using dimensional collapse of imagery Information into amenable temporal patterns and the use of asynchronous frames for Information Binding.
-
The ripple pond: Enabling spiking networks to see
Frontiers in Neuroscience, 2013Co-Authors: Salim Afshar, Runchun M. Wang, Antoinette Van Schaik, Gregory K. Cohen, Torsten Lehmann, Jonathan Tapson, Tara J. HamiltonAbstract:We present the biologically inspired Ripple Pond Network (RPN), a simply connected spiking neural network which performs a transformation converting two dimensional images to one dimensional temporal patterns (TP) suitable for recognition by temporal coding learning and memory networks. The RPN has been developed as a hardware solution linking previously implemented neuromorphic vision and memory structures such as frameless vision sensors and neuromorphic temporal coding spiking neural networks. Working together such systems are potentially capable of delivering end-to-end high-speed, low-power and low-resolution recognition for mobile and autonomous applications where slow, highly sophisticated and power hungry signal processing solutions are ineffective. Key aspects in the proposed approach include utilizing the spatial properties of physically embedded neural networks and propagating waves of activity therein for Information processing, using dimensional collapse of imagery Information into amenable TP and the use of asynchronous frames for Information Binding.