Inhibition of Long-Term Variability in Decoding Forelimb Trajectory Using Evolutionary Neural Networks With Error-Correction Learning
Objective: In brain machine interfaces (BMIs), the functional mapping between neural activities and kinematic parameters varied over time owing to changes in neural recording conditions. The variability in neural recording conditions might result in unstable long-term decoding performance. Relevant...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2020-03-01
|
| Series: | Frontiers in Computational Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fncom.2020.00022/full |
| _version_ | 1818116118569549824 |
|---|---|
| author | Shih-Hung Yang Han-Lin Wang Yu-Chun Lo Hsin-Yi Lai Hsin-Yi Lai Kuan-Yu Chen Yu-Hao Lan Ching-Chia Kao Chin Chou Sheng-Huang Lin Sheng-Huang Lin Jyun-We Huang Ching-Fu Wang Chao-Hung Kuo Chao-Hung Kuo Chao-Hung Kuo You-Yin Chen You-Yin Chen |
| author_facet | Shih-Hung Yang Han-Lin Wang Yu-Chun Lo Hsin-Yi Lai Hsin-Yi Lai Kuan-Yu Chen Yu-Hao Lan Ching-Chia Kao Chin Chou Sheng-Huang Lin Sheng-Huang Lin Jyun-We Huang Ching-Fu Wang Chao-Hung Kuo Chao-Hung Kuo Chao-Hung Kuo You-Yin Chen You-Yin Chen |
| author_sort | Shih-Hung Yang |
| collection | DOAJ |
| description | Objective: In brain machine interfaces (BMIs), the functional mapping between neural activities and kinematic parameters varied over time owing to changes in neural recording conditions. The variability in neural recording conditions might result in unstable long-term decoding performance. Relevant studies trained decoders with several days of training data to make them inherently robust to changes in neural recording conditions. However, these decoders might not be robust to changes in neural recording conditions when only a few days of training data are available. In time-series prediction and feedback control system, an error feedback was commonly adopted to reduce the effects of model uncertainty. This motivated us to introduce an error feedback to a neural decoder for dealing with the variability in neural recording conditions.Approach: We proposed an evolutionary constructive and pruning neural network with error feedback (ECPNN-EF) as a neural decoder. The ECPNN-EF with partially connected topology decoded the instantaneous firing rates of each sorted unit into forelimb movement of a rat. Furthermore, an error feedback was adopted as an additional input to provide kinematic information and thus compensate for changes in functional mapping. The proposed neural decoder was trained on data collected from a water reward-related lever-pressing task for a rat. The first 2 days of data were used to train the decoder, and the subsequent 10 days of data were used to test the decoder.Main Results: The ECPNN-EF under different settings was evaluated to better understand the impact of the error feedback and partially connected topology. The experimental results demonstrated that the ECPNN-EF achieved significantly higher daily decoding performance with smaller daily variability when using the error feedback and partially connected topology.Significance: These results suggested that the ECPNN-EF with partially connected topology could cope with both within- and across-day changes in neural recording conditions. The error feedback in the ECPNN-EF compensated for decreases in decoding performance when neural recording conditions changed. This mechanism made the ECPNN-EF robust against changes in functional mappings and thus improved the long-term decoding stability when only a few days of training data were available. |
| first_indexed | 2024-12-11T04:17:26Z |
| format | Article |
| id | doaj.art-42f994c0a05a4ff0be64d41dbb92178f |
| institution | Directory Open Access Journal |
| issn | 1662-5188 |
| language | English |
| last_indexed | 2024-12-11T04:17:26Z |
| publishDate | 2020-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Computational Neuroscience |
| spelling | doaj.art-42f994c0a05a4ff0be64d41dbb92178f2022-12-22T01:21:13ZengFrontiers Media S.A.Frontiers in Computational Neuroscience1662-51882020-03-011410.3389/fncom.2020.00022513364Inhibition of Long-Term Variability in Decoding Forelimb Trajectory Using Evolutionary Neural Networks With Error-Correction LearningShih-Hung Yang0Han-Lin Wang1Yu-Chun Lo2Hsin-Yi Lai3Hsin-Yi Lai4Kuan-Yu Chen5Yu-Hao Lan6Ching-Chia Kao7Chin Chou8Sheng-Huang Lin9Sheng-Huang Lin10Jyun-We Huang11Ching-Fu Wang12Chao-Hung Kuo13Chao-Hung Kuo14Chao-Hung Kuo15You-Yin Chen16You-Yin Chen17Department of Mechanical Engineering, National Cheng Kung University, Tainan, TaiwanDepartment of Biomedical Engineering, National Yang Ming University, Taipei, TaiwanThe Ph.D. Program for Neural Regenerative Medicine, College of Medical Science and Technology, Taipei Medical University, Taipei, TaiwanKey Laboratory of Medical Neurobiology of Zhejiang Province, Department of Neurology of the Second Affiliated Hospital, Interdisciplinary Institute of Neuroscience and Technology, Zhejiang University School of Medicine, Hangzhou, ChinaKey Laboratory of Biomedical Engineering of Ministry of Education, College of Biomedical Engineering and Instrument Science, Qiushi Academy for Advanced Studies, Zhejiang University, Hangzhou, ChinaDepartment of Biomedical Engineering, National Yang Ming University, Taipei, TaiwanDepartment of Biomedical Engineering, National Yang Ming University, Taipei, TaiwanResearch Center for Information Technology Innovation, Academia Sinica, Taipei, TaiwanDepartment of Regulatory & Quality Sciences, University of Southern California, Los Angeles, CA, United StatesBuddhist Tzu Chi Medical Foundation, Department of Neurology, Hualien Tzu Chi Hospital, Hualien, TaiwanDepartment of Neurology, School of Medicine, Tzu Chi University, Hualien, TaiwanDepartment of Mechanical Engineering, National Cheng Kung University, Tainan, TaiwanDepartment of Biomedical Engineering, National Yang Ming University, Taipei, TaiwanDepartment of Biomedical Engineering, National Yang Ming University, Taipei, Taiwan0Department of Neurosurgery, Neurological Institute, Taipei Veterans General Hospital, Taipei, Taiwan1Department of Neurological Surgery, University of Washington, Seattle, WA, United StatesDepartment of Biomedical Engineering, National Yang Ming University, Taipei, TaiwanThe Ph.D. Program for Neural Regenerative Medicine, College of Medical Science and Technology, Taipei Medical University, Taipei, TaiwanObjective: In brain machine interfaces (BMIs), the functional mapping between neural activities and kinematic parameters varied over time owing to changes in neural recording conditions. The variability in neural recording conditions might result in unstable long-term decoding performance. Relevant studies trained decoders with several days of training data to make them inherently robust to changes in neural recording conditions. However, these decoders might not be robust to changes in neural recording conditions when only a few days of training data are available. In time-series prediction and feedback control system, an error feedback was commonly adopted to reduce the effects of model uncertainty. This motivated us to introduce an error feedback to a neural decoder for dealing with the variability in neural recording conditions.Approach: We proposed an evolutionary constructive and pruning neural network with error feedback (ECPNN-EF) as a neural decoder. The ECPNN-EF with partially connected topology decoded the instantaneous firing rates of each sorted unit into forelimb movement of a rat. Furthermore, an error feedback was adopted as an additional input to provide kinematic information and thus compensate for changes in functional mapping. The proposed neural decoder was trained on data collected from a water reward-related lever-pressing task for a rat. The first 2 days of data were used to train the decoder, and the subsequent 10 days of data were used to test the decoder.Main Results: The ECPNN-EF under different settings was evaluated to better understand the impact of the error feedback and partially connected topology. The experimental results demonstrated that the ECPNN-EF achieved significantly higher daily decoding performance with smaller daily variability when using the error feedback and partially connected topology.Significance: These results suggested that the ECPNN-EF with partially connected topology could cope with both within- and across-day changes in neural recording conditions. The error feedback in the ECPNN-EF compensated for decreases in decoding performance when neural recording conditions changed. This mechanism made the ECPNN-EF robust against changes in functional mappings and thus improved the long-term decoding stability when only a few days of training data were available.https://www.frontiersin.org/article/10.3389/fncom.2020.00022/fullbrain machine interfacesneural decodingerror feedbackevolutionary algorithmrecurrent neural network |
| spellingShingle | Shih-Hung Yang Han-Lin Wang Yu-Chun Lo Hsin-Yi Lai Hsin-Yi Lai Kuan-Yu Chen Yu-Hao Lan Ching-Chia Kao Chin Chou Sheng-Huang Lin Sheng-Huang Lin Jyun-We Huang Ching-Fu Wang Chao-Hung Kuo Chao-Hung Kuo Chao-Hung Kuo You-Yin Chen You-Yin Chen Inhibition of Long-Term Variability in Decoding Forelimb Trajectory Using Evolutionary Neural Networks With Error-Correction Learning Frontiers in Computational Neuroscience brain machine interfaces neural decoding error feedback evolutionary algorithm recurrent neural network |
| title | Inhibition of Long-Term Variability in Decoding Forelimb Trajectory Using Evolutionary Neural Networks With Error-Correction Learning |
| title_full | Inhibition of Long-Term Variability in Decoding Forelimb Trajectory Using Evolutionary Neural Networks With Error-Correction Learning |
| title_fullStr | Inhibition of Long-Term Variability in Decoding Forelimb Trajectory Using Evolutionary Neural Networks With Error-Correction Learning |
| title_full_unstemmed | Inhibition of Long-Term Variability in Decoding Forelimb Trajectory Using Evolutionary Neural Networks With Error-Correction Learning |
| title_short | Inhibition of Long-Term Variability in Decoding Forelimb Trajectory Using Evolutionary Neural Networks With Error-Correction Learning |
| title_sort | inhibition of long term variability in decoding forelimb trajectory using evolutionary neural networks with error correction learning |
| topic | brain machine interfaces neural decoding error feedback evolutionary algorithm recurrent neural network |
| url | https://www.frontiersin.org/article/10.3389/fncom.2020.00022/full |
| work_keys_str_mv | AT shihhungyang inhibitionoflongtermvariabilityindecodingforelimbtrajectoryusingevolutionaryneuralnetworkswitherrorcorrectionlearning AT hanlinwang inhibitionoflongtermvariabilityindecodingforelimbtrajectoryusingevolutionaryneuralnetworkswitherrorcorrectionlearning AT yuchunlo inhibitionoflongtermvariabilityindecodingforelimbtrajectoryusingevolutionaryneuralnetworkswitherrorcorrectionlearning AT hsinyilai inhibitionoflongtermvariabilityindecodingforelimbtrajectoryusingevolutionaryneuralnetworkswitherrorcorrectionlearning AT hsinyilai inhibitionoflongtermvariabilityindecodingforelimbtrajectoryusingevolutionaryneuralnetworkswitherrorcorrectionlearning AT kuanyuchen inhibitionoflongtermvariabilityindecodingforelimbtrajectoryusingevolutionaryneuralnetworkswitherrorcorrectionlearning AT yuhaolan inhibitionoflongtermvariabilityindecodingforelimbtrajectoryusingevolutionaryneuralnetworkswitherrorcorrectionlearning AT chingchiakao inhibitionoflongtermvariabilityindecodingforelimbtrajectoryusingevolutionaryneuralnetworkswitherrorcorrectionlearning AT chinchou inhibitionoflongtermvariabilityindecodingforelimbtrajectoryusingevolutionaryneuralnetworkswitherrorcorrectionlearning AT shenghuanglin inhibitionoflongtermvariabilityindecodingforelimbtrajectoryusingevolutionaryneuralnetworkswitherrorcorrectionlearning AT shenghuanglin inhibitionoflongtermvariabilityindecodingforelimbtrajectoryusingevolutionaryneuralnetworkswitherrorcorrectionlearning AT jyunwehuang inhibitionoflongtermvariabilityindecodingforelimbtrajectoryusingevolutionaryneuralnetworkswitherrorcorrectionlearning AT chingfuwang inhibitionoflongtermvariabilityindecodingforelimbtrajectoryusingevolutionaryneuralnetworkswitherrorcorrectionlearning AT chaohungkuo inhibitionoflongtermvariabilityindecodingforelimbtrajectoryusingevolutionaryneuralnetworkswitherrorcorrectionlearning AT chaohungkuo inhibitionoflongtermvariabilityindecodingforelimbtrajectoryusingevolutionaryneuralnetworkswitherrorcorrectionlearning AT chaohungkuo inhibitionoflongtermvariabilityindecodingforelimbtrajectoryusingevolutionaryneuralnetworkswitherrorcorrectionlearning AT youyinchen inhibitionoflongtermvariabilityindecodingforelimbtrajectoryusingevolutionaryneuralnetworkswitherrorcorrectionlearning AT youyinchen inhibitionoflongtermvariabilityindecodingforelimbtrajectoryusingevolutionaryneuralnetworkswitherrorcorrectionlearning |