The Experts below are selected from a list of 9399 Experts worldwide ranked by ideXlab platform
Tm Mcginnity - One of the best experts on this subject based on the ideXlab platform.
-
optimization of Output Spike train encoding for a spiking neuron based on its spatio temporal input pattern
IEEE Transactions on Cognitive and Developmental Systems, 2020Co-Authors: Aboozar Taherkhani, Georgina Cosma, Tm McginnityAbstract:A common learning task for a spiking neuron is to map a spatio–temporal input pattern to a target Output Spike train. There is no prescribed method for selection of the target Output Spike train. However, the precise spiking pattern of the target Output Spike train (Output encoding) can affect the learning performance of the spiking neuron. Therefore, systematic methods of finding the optimum spiking pattern for a target Output Spike train that can be learned by spiking neurons are needed. Here, a method is proposed to adaptively adjust an initial suboptimal Output encoding during different learning epochs to find the optimal Output encoding. A time varying value of a local event called a Spike trace is used to calculate the amount of a required adjustment. The remote supervised method (ReSuMe) learning algorithm is used to train the weights, and the proposed method is used for finding optimized Output encoding (optimized desired Spikes). Experimental results show that optimizing the Output encoding during the learning phase increases the accuracy. The proposed method was applied to find optimized Output encoding in classification tasks and the results revealed improvements up to 16.5% in accuracy compared to when using the non-adapted method. It also increases the accuracy in a classification task from 90% to 100%.
-
Optimization of Output Spike Train Encoding for a Spiking Neuron Based on its Spatio–Temporal Input Pattern
IEEE Transactions on Cognitive and Developmental Systems, 2020Co-Authors: Aboozar Taherkhani, Georgina Cosma, Tm McginnityAbstract:A common learning task for a spiking neuron is to map a spatio–temporal input pattern to a target Output Spike train. There is no prescribed method for selection of the target Output Spike train. However, the precise spiking pattern of the target Output Spike train (Output encoding) can affect the learning performance of the spiking neuron. Therefore, systematic methods of finding the optimum spiking pattern for a target Output Spike train that can be learned by spiking neurons are needed. Here, a method is proposed to adaptively adjust an initial suboptimal Output encoding during different learning epochs to find the optimal Output encoding. A time varying value of a local event called a Spike trace is used to calculate the amount of a required adjustment. The remote supervised method (ReSuMe) learning algorithm is used to train the weights, and the proposed method is used for finding optimized Output encoding (optimized desired Spikes). Experimental results show that optimizing the Output encoding during the learning phase increases the accuracy. The proposed method was applied to find optimized Output encoding in classification tasks and the results revealed improvements up to 16.5% in accuracy compared to when using the non-adapted method. It also increases the accuracy in a classification task from 90% to 100%.
Nikola Kasabov - One of the best experts on this subject based on the ideXlab platform.
-
training spiking neural networks to associate spatio temporal input Output Spike patterns
Neurocomputing, 2013Co-Authors: Ammar Mohemmed, Stefan Schliebs, Satoshi Matsuda, Nikola KasabovAbstract:In a previous work (Mohemmed et al., Method for training a spiking neuron to associate input-Output Spike trains) [1] we have proposed a supervised learning algorithm based on temporal coding to train a spiking neuron to associate input spatiotemporal Spike patterns to desired Output Spike patterns. The algorithm is based on the conversion of Spike trains into analogue signals and the application of the Widrow-Hoff learning rule. In this paper we present a mathematical formulation of the proposed learning rule. Furthermore, we extend the application of the algorithm to train a SNN consisting of multiple spiking neurons to perform spatiotemporal pattern classification and we show that the accuracy of classification is improved significantly over a single spiking neuron. We also investigate a number of possibilities to map the temporal Output of the trained spiking neuron into a class label. Potential applications for motor control in neuro-rehabilitation and neuro-prosthetics are discussed as a future work.
-
IJCNN - Incremental learning algorithm for spatio-temporal Spike pattern classification
The 2012 International Joint Conference on Neural Networks (IJCNN), 2012Co-Authors: Ammar Mohemmed, Nikola KasabovAbstract:In a previous work (Mohemmed et al. [11]), the authors proposed a supervised learning algorithm to train a spiking neuron to associate input/Output Spike patterns. In this paper, the association learning rule is applied in training a single layer of spiking neurons to classify multiclass Spike patterns whereby the neurons are trained to recognize an input Spike pattern by emitting a predetermined Spike train. The training is performed in incremental fashion, i.e. the synaptic weights are adjusted after each presentation of a training pattern. The individual neurons are trained independently from other neurons and on patterns from a single class. A Spike train comparison criterion is used to decode the Output Spike trains into class labels. The results of the simulation experiments on a synthetic dataset of Spike patterns show a high efficiency in solving the considered classification task.
-
Method for Training a Spiking Neuron to Associate Input-Output Spike Trains
2011Co-Authors: Ammar Mohemmed, Stefan Schliebs, Satoshi Matsuda, Nikola KasabovAbstract:We propose a novel supervised learning rule allowing the training of a precise input-Output behavior to a spiking neuron. A single neuron can be trained to associate (map) different Output Spike trains to different multiple input Spike trains. Spike trains are transformed into continuous functions through appropriate kernels and then Delta rule is applied. The main advantage of the method is its algorithmic simplicity promoting its straightforward application to building spiking neural networks (SNN) for engineering problems. We experimentally demonstrate on a synthetic benchmark problem the suitability of the method for spatio-temporal classification. The obtained results show promising efficiency and precision of the proposed method.
-
EANN/AIAI (1) - Method for Training a Spiking Neuron to Associate Input-Output Spike Trains
Engineering Applications of Neural Networks, 2011Co-Authors: Ammar Mohemmed, Stefan Schliebs, Satoshi Matsuda, Nikola KasabovAbstract:We propose a novel supervised learning rule allowing the training of a precise input-Output behavior to a spiking neuron. A single neuron can be trained to associate (map) different Output Spike trains to different multiple input Spike trains. Spike trains are transformed into continuous functions through appropriate kernels and then Delta rule is applied. The main advantage of the method is its algorithmic simplicity promoting its straightforward application to building spiking neural networks (SNN) for engineering problems. We experimentally demonstrate on a synthetic benchmark problem the suitability of the method for spatio-temporal classification. The obtained results show promising efficiency and precision of the proposed method.
-
ICONIP (2) - SPAN: a neuron for precise-time Spike pattern association
Neural Information Processing, 2011Co-Authors: Ammar Mohemmed, Stefan Schliebs, Nikola KasabovAbstract:In this paper we propose SPAN, a LIF spiking neuron that is capable of learning input-Output Spike pattern association using a novel learning algorithm. The main idea of SPAN is transforming the Spike trains into analog signals where computing the error can be done easily. As demonstrated in an experimental analysis, the proposed method is both simple and efficient achieving reliable training results even in the context of noise.
Aboozar Taherkhani - One of the best experts on this subject based on the ideXlab platform.
-
optimization of Output Spike train encoding for a spiking neuron based on its spatio temporal input pattern
IEEE Transactions on Cognitive and Developmental Systems, 2020Co-Authors: Aboozar Taherkhani, Georgina Cosma, Tm McginnityAbstract:A common learning task for a spiking neuron is to map a spatio–temporal input pattern to a target Output Spike train. There is no prescribed method for selection of the target Output Spike train. However, the precise spiking pattern of the target Output Spike train (Output encoding) can affect the learning performance of the spiking neuron. Therefore, systematic methods of finding the optimum spiking pattern for a target Output Spike train that can be learned by spiking neurons are needed. Here, a method is proposed to adaptively adjust an initial suboptimal Output encoding during different learning epochs to find the optimal Output encoding. A time varying value of a local event called a Spike trace is used to calculate the amount of a required adjustment. The remote supervised method (ReSuMe) learning algorithm is used to train the weights, and the proposed method is used for finding optimized Output encoding (optimized desired Spikes). Experimental results show that optimizing the Output encoding during the learning phase increases the accuracy. The proposed method was applied to find optimized Output encoding in classification tasks and the results revealed improvements up to 16.5% in accuracy compared to when using the non-adapted method. It also increases the accuracy in a classification task from 90% to 100%.
-
Optimization of Output Spike Train Encoding for a Spiking Neuron Based on its Spatio–Temporal Input Pattern
IEEE Transactions on Cognitive and Developmental Systems, 2020Co-Authors: Aboozar Taherkhani, Georgina Cosma, Tm McginnityAbstract:A common learning task for a spiking neuron is to map a spatio–temporal input pattern to a target Output Spike train. There is no prescribed method for selection of the target Output Spike train. However, the precise spiking pattern of the target Output Spike train (Output encoding) can affect the learning performance of the spiking neuron. Therefore, systematic methods of finding the optimum spiking pattern for a target Output Spike train that can be learned by spiking neurons are needed. Here, a method is proposed to adaptively adjust an initial suboptimal Output encoding during different learning epochs to find the optimal Output encoding. A time varying value of a local event called a Spike trace is used to calculate the amount of a required adjustment. The remote supervised method (ReSuMe) learning algorithm is used to train the weights, and the proposed method is used for finding optimized Output encoding (optimized desired Spikes). Experimental results show that optimizing the Output encoding during the learning phase increases the accuracy. The proposed method was applied to find optimized Output encoding in classification tasks and the results revealed improvements up to 16.5% in accuracy compared to when using the non-adapted method. It also increases the accuracy in a classification task from 90% to 100%.
Ammar Mohemmed - One of the best experts on this subject based on the ideXlab platform.
-
training spiking neural networks to associate spatio temporal input Output Spike patterns
Neurocomputing, 2013Co-Authors: Ammar Mohemmed, Stefan Schliebs, Satoshi Matsuda, Nikola KasabovAbstract:In a previous work (Mohemmed et al., Method for training a spiking neuron to associate input-Output Spike trains) [1] we have proposed a supervised learning algorithm based on temporal coding to train a spiking neuron to associate input spatiotemporal Spike patterns to desired Output Spike patterns. The algorithm is based on the conversion of Spike trains into analogue signals and the application of the Widrow-Hoff learning rule. In this paper we present a mathematical formulation of the proposed learning rule. Furthermore, we extend the application of the algorithm to train a SNN consisting of multiple spiking neurons to perform spatiotemporal pattern classification and we show that the accuracy of classification is improved significantly over a single spiking neuron. We also investigate a number of possibilities to map the temporal Output of the trained spiking neuron into a class label. Potential applications for motor control in neuro-rehabilitation and neuro-prosthetics are discussed as a future work.
-
IJCNN - Incremental learning algorithm for spatio-temporal Spike pattern classification
The 2012 International Joint Conference on Neural Networks (IJCNN), 2012Co-Authors: Ammar Mohemmed, Nikola KasabovAbstract:In a previous work (Mohemmed et al. [11]), the authors proposed a supervised learning algorithm to train a spiking neuron to associate input/Output Spike patterns. In this paper, the association learning rule is applied in training a single layer of spiking neurons to classify multiclass Spike patterns whereby the neurons are trained to recognize an input Spike pattern by emitting a predetermined Spike train. The training is performed in incremental fashion, i.e. the synaptic weights are adjusted after each presentation of a training pattern. The individual neurons are trained independently from other neurons and on patterns from a single class. A Spike train comparison criterion is used to decode the Output Spike trains into class labels. The results of the simulation experiments on a synthetic dataset of Spike patterns show a high efficiency in solving the considered classification task.
-
Method for Training a Spiking Neuron to Associate Input-Output Spike Trains
2011Co-Authors: Ammar Mohemmed, Stefan Schliebs, Satoshi Matsuda, Nikola KasabovAbstract:We propose a novel supervised learning rule allowing the training of a precise input-Output behavior to a spiking neuron. A single neuron can be trained to associate (map) different Output Spike trains to different multiple input Spike trains. Spike trains are transformed into continuous functions through appropriate kernels and then Delta rule is applied. The main advantage of the method is its algorithmic simplicity promoting its straightforward application to building spiking neural networks (SNN) for engineering problems. We experimentally demonstrate on a synthetic benchmark problem the suitability of the method for spatio-temporal classification. The obtained results show promising efficiency and precision of the proposed method.
-
EANN/AIAI (1) - Method for Training a Spiking Neuron to Associate Input-Output Spike Trains
Engineering Applications of Neural Networks, 2011Co-Authors: Ammar Mohemmed, Stefan Schliebs, Satoshi Matsuda, Nikola KasabovAbstract:We propose a novel supervised learning rule allowing the training of a precise input-Output behavior to a spiking neuron. A single neuron can be trained to associate (map) different Output Spike trains to different multiple input Spike trains. Spike trains are transformed into continuous functions through appropriate kernels and then Delta rule is applied. The main advantage of the method is its algorithmic simplicity promoting its straightforward application to building spiking neural networks (SNN) for engineering problems. We experimentally demonstrate on a synthetic benchmark problem the suitability of the method for spatio-temporal classification. The obtained results show promising efficiency and precision of the proposed method.
-
ICONIP (2) - SPAN: a neuron for precise-time Spike pattern association
Neural Information Processing, 2011Co-Authors: Ammar Mohemmed, Stefan Schliebs, Nikola KasabovAbstract:In this paper we propose SPAN, a LIF spiking neuron that is capable of learning input-Output Spike pattern association using a novel learning algorithm. The main idea of SPAN is transforming the Spike trains into analog signals where computing the error can be done easily. As demonstrated in an experimental analysis, the proposed method is both simple and efficient achieving reliable training results even in the context of noise.
Changsong Zhou - One of the best experts on this subject based on the ideXlab platform.
-
rate synchrony relationship between input and Output of Spike trains in neuronal networks
Physical Review E, 2010Co-Authors: Sentao Wang, Changsong ZhouAbstract:Neuronal networks interact via Spike trains. How the Spike trains are transformed by neuronal networks is critical for understanding the underlying mechanism of information processing in the nervous system. Both the rate and synchrony of the Spikes can affect the transmission, while the relationship between them has not been fully understood. Here we investigate the mapping between input and Output Spike trains of a neuronal network in terms of firing rate and synchrony. With large enough input rate, the working mode of the neurons is gradually changed from temporal integrators into coincidence detectors when the synchrony degree of input Spike trains increases. Since the membrane potentials of the neurons can be depolarized to near the firing threshold by uncorrelated input Spikes, small input synchrony can cause great Output synchrony. On the other hand, the synchrony in the Output may be reduced when the input rate is too small. The case of the feedforward network can be regarded as iterative process of such an input-Output relationship. The activity in deep layers of the feedforward network is in an all-or-none manner depending on the input rate and synchrony.