Temporal-Sequential Learning With a Brain-Inspired Spiking Neural Network and Its Application to Musical Memory
Sequence learning is a fundamental cognitive function of the brain. However, the ways in which sequential information is represented and memorized are not dealt with satisfactorily by existing models. To overcome this deficiency, this paper introduces a spiking neural network based on psychological...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2020-07-01
|
| Series: | Frontiers in Computational Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fncom.2020.00051/full |
| _version_ | 1811336458901913600 |
|---|---|
| author | Qian Liang Qian Liang Yi Zeng Yi Zeng Yi Zeng Yi Zeng Bo Xu Bo Xu Bo Xu |
| author_facet | Qian Liang Qian Liang Yi Zeng Yi Zeng Yi Zeng Yi Zeng Bo Xu Bo Xu Bo Xu |
| author_sort | Qian Liang |
| collection | DOAJ |
| description | Sequence learning is a fundamental cognitive function of the brain. However, the ways in which sequential information is represented and memorized are not dealt with satisfactorily by existing models. To overcome this deficiency, this paper introduces a spiking neural network based on psychological and neurobiological findings at multiple scales. Compared with existing methods, our model has four novel features: (1) It contains several collaborative subnetworks similar to those in brain regions with different cognitive functions. The individual building blocks of the simulated areas are neural functional minicolumns composed of biologically plausible neurons. Both excitatory and inhibitory connections between neurons are modulated dynamically using a spike-timing-dependent plasticity learning rule. (2) Inspired by the mechanisms of the brain's cortical-striatal loop, a dependent timing module is constructed to encode temporal information, which is essential in sequence learning but has not been processed well by traditional algorithms. (3) Goal-based and episodic retrievals can be achieved at different time scales. (4) Musical memory is used as an application to validate the model. Experiments show that the model can store a huge amount of data on melodies and recall them with high accuracy. In addition, it can remember the entirety of a melody given only an episode or the melody played at different paces. |
| first_indexed | 2024-04-13T17:39:47Z |
| format | Article |
| id | doaj.art-7bae997ef081441a86422cc0f8ed0211 |
| institution | Directory Open Access Journal |
| issn | 1662-5188 |
| language | English |
| last_indexed | 2024-04-13T17:39:47Z |
| publishDate | 2020-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Computational Neuroscience |
| spelling | doaj.art-7bae997ef081441a86422cc0f8ed02112022-12-22T02:37:13ZengFrontiers Media S.A.Frontiers in Computational Neuroscience1662-51882020-07-011410.3389/fncom.2020.00051514012Temporal-Sequential Learning With a Brain-Inspired Spiking Neural Network and Its Application to Musical MemoryQian Liang0Qian Liang1Yi Zeng2Yi Zeng3Yi Zeng4Yi Zeng5Bo Xu6Bo Xu7Bo Xu8Research Center for Brain-Inspired Intelligence, Institute of Automation, Chinese Academy of Sciences, Beijing, ChinaSchool of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, ChinaResearch Center for Brain-Inspired Intelligence, Institute of Automation, Chinese Academy of Sciences, Beijing, ChinaSchool of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, ChinaNational Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, ChinaCenter for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, ChinaResearch Center for Brain-Inspired Intelligence, Institute of Automation, Chinese Academy of Sciences, Beijing, ChinaSchool of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, ChinaCenter for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, ChinaSequence learning is a fundamental cognitive function of the brain. However, the ways in which sequential information is represented and memorized are not dealt with satisfactorily by existing models. To overcome this deficiency, this paper introduces a spiking neural network based on psychological and neurobiological findings at multiple scales. Compared with existing methods, our model has four novel features: (1) It contains several collaborative subnetworks similar to those in brain regions with different cognitive functions. The individual building blocks of the simulated areas are neural functional minicolumns composed of biologically plausible neurons. Both excitatory and inhibitory connections between neurons are modulated dynamically using a spike-timing-dependent plasticity learning rule. (2) Inspired by the mechanisms of the brain's cortical-striatal loop, a dependent timing module is constructed to encode temporal information, which is essential in sequence learning but has not been processed well by traditional algorithms. (3) Goal-based and episodic retrievals can be achieved at different time scales. (4) Musical memory is used as an application to validate the model. Experiments show that the model can store a huge amount of data on melodies and recall them with high accuracy. In addition, it can remember the entirety of a melody given only an episode or the melody played at different paces.https://www.frontiersin.org/article/10.3389/fncom.2020.00051/fullspiking neural networksequential memoryepisodic memoryspike-timing-dependent plasticitytime perceptionmusical learning |
| spellingShingle | Qian Liang Qian Liang Yi Zeng Yi Zeng Yi Zeng Yi Zeng Bo Xu Bo Xu Bo Xu Temporal-Sequential Learning With a Brain-Inspired Spiking Neural Network and Its Application to Musical Memory Frontiers in Computational Neuroscience spiking neural network sequential memory episodic memory spike-timing-dependent plasticity time perception musical learning |
| title | Temporal-Sequential Learning With a Brain-Inspired Spiking Neural Network and Its Application to Musical Memory |
| title_full | Temporal-Sequential Learning With a Brain-Inspired Spiking Neural Network and Its Application to Musical Memory |
| title_fullStr | Temporal-Sequential Learning With a Brain-Inspired Spiking Neural Network and Its Application to Musical Memory |
| title_full_unstemmed | Temporal-Sequential Learning With a Brain-Inspired Spiking Neural Network and Its Application to Musical Memory |
| title_short | Temporal-Sequential Learning With a Brain-Inspired Spiking Neural Network and Its Application to Musical Memory |
| title_sort | temporal sequential learning with a brain inspired spiking neural network and its application to musical memory |
| topic | spiking neural network sequential memory episodic memory spike-timing-dependent plasticity time perception musical learning |
| url | https://www.frontiersin.org/article/10.3389/fncom.2020.00051/full |
| work_keys_str_mv | AT qianliang temporalsequentiallearningwithabraininspiredspikingneuralnetworkanditsapplicationtomusicalmemory AT qianliang temporalsequentiallearningwithabraininspiredspikingneuralnetworkanditsapplicationtomusicalmemory AT yizeng temporalsequentiallearningwithabraininspiredspikingneuralnetworkanditsapplicationtomusicalmemory AT yizeng temporalsequentiallearningwithabraininspiredspikingneuralnetworkanditsapplicationtomusicalmemory AT yizeng temporalsequentiallearningwithabraininspiredspikingneuralnetworkanditsapplicationtomusicalmemory AT yizeng temporalsequentiallearningwithabraininspiredspikingneuralnetworkanditsapplicationtomusicalmemory AT boxu temporalsequentiallearningwithabraininspiredspikingneuralnetworkanditsapplicationtomusicalmemory AT boxu temporalsequentiallearningwithabraininspiredspikingneuralnetworkanditsapplicationtomusicalmemory AT boxu temporalsequentiallearningwithabraininspiredspikingneuralnetworkanditsapplicationtomusicalmemory |