<abstract xmlns="http://www.w3.org/1999/xhtml"><p>Many recent studies have applied to spike neural networks with spike-timing-dependent plasticity (STDP) to machine learning problems. The learning abilities of dopamine-modulated STDP (DA-STDP) for reward-related synaptic plasticity have also been gathering attention. Following these studies, we hypothesize that a network structure combining self-organized STDP and reward-related DA-STDP can solve the machine learning problem of pattern classification. Therefore, we studied the ability of a network in which recurrent spiking neural networks are combined with STDP for non-supervised learning, with an output layer joined by DA-STDP for supervised learning, to perform pattern classification. We confirmed that this network could perform pattern classification using the STDP effect for emphasizing features of the input spike pattern and DA-STDP supervised learning. Therefore, our proposed spiking neural network may prove to be a useful approach for machine learning problems.</p></abstract>

Many recent studies have applied to spike neural networks with spike-timing-dependent plasticity (STDP) to machine learning problems. The learning abilities of dopamine-modulated STDP (DA-STDP) for reward-related synaptic plasticity have also been gathering attention. Following these studies, we hypothesize that a network structure combining self-organized STDP and reward-related DA-STDP can solve the machine learning problem of pattern classification. Therefore, we studied the ability of a network in which recurrent spiking neural networks are combined with STDP for non-supervised learning, with an output layer joined by DA-STDP for supervised learning, to perform pattern classification. We confirmed that this network could perform pattern classification using the STDP effect for emphasizing features of the input spike pattern and DA-STDP supervised learning. Therefore, our proposed spiking neural network may prove to be a useful approach for machine learning problems.

Pattern Classification by Spiking Neural Networks Combining Self-Organized and Reward-Related Spike-Timing-Dependent Plasticity

Department of Computer Science, Chiba Institute of Technology

Department of Management and Information Sciences

Journal of Artificial Intelligence and Soft Computing Research

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Many recent studies have applied to spike neural networks with spike-timing-dependent plasticity (STDP) to machine learning problems. The learning abilities of...

Pattern Classification by Spiking Neural Networks Combining Self-Organized and Reward-Related Spike-Timing-Dependent Plasticity

Publié en ligne: 30 août 2019

Pages: 283 - 291

Reçu: 16 mars 2019

Accepté: 12 mai 2019

DOI: https://doi.org/10.2478/jaiscr-2019-0009

Mots clés
spiking neural network, spike timing-dependent plasticity, dopamine-modulated spike timing-dependent plasticity, pattern classification

© 2019 Sou Nobukawa et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Pattern Classification by Spiking Neural Networks Combining Self-Organized and Reward-Related Spike-Timing-Dependent Plasticity

Publié en ligne: 30 août 2019

Pages: 283 - 291

Reçu: 16 mars 2019

Accepté: 12 mai 2019

DOI: https://doi.org/10.2478/jaiscr-2019-0009

Mots clésspiking neural network, spike timing-dependent plasticity, dopamine-modulated spike timing-dependent plasticity, pattern classification

© 2019 Sou Nobukawa et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Mots clés
spiking neural network, spike timing-dependent plasticity, dopamine-modulated spike timing-dependent plasticity, pattern classification