{"type":"ScholarlyArticle","title":"Fast and Accurate Classification with a Multi-Spike Learning Algorithm for Spiking Neurons","authors":[{"name":"Rong Xiao","slug":"rong-xiao","given":"Rong","family":"Xiao","affiliation":"College of Computer Science , Sichuan University , China"},{"name":"Qiang Yu","slug":"qiang-yu","given":"Qiang","family":"Yu","affiliation":"College of Intelligence and Computing , Tianjin University , China"},{"name":"Rui Yan","slug":"rui-yan","given":"Rui","family":"Yan","affiliation":"College of Computer Science , Sichuan University , China"},{"name":"Huajin Tang","slug":"huajin-tang","given":"Huajin","family":"Tang","affiliation":"College of Computer Science , Sichuan University , China; College of Computer Science and Technology , Zhejiang University , China"}],"abstract":"The formulation of efficient supervised learning algorithms for spiking neurons is complicated and remains challenging. Most existing learning methods with the precisely firing times of spikes often result in relatively low efficiency and poor robustness to noise. To address these limitations, we propose a simple and effective multi-spike learning rule to train neurons to match their output spike number with a desired one. The proposed method will quickly find a local maximum value (directly related to the embedded feature) as the relevant signal for synaptic updates based on membrane potential trace of a neuron, and constructs an error function defined as the difference between the local maximum membrane potential and the firing threshold. With the presented rule, a single neuron can be trained to learn multi-category tasks, and can successfully mitigate the impact of the input noise and discover embedded features. Experimental results show the proposed algorithm has higher precision, lower computation cost, and better noise robustness than current state-of-the-art learning methods under a wide range of learning tasks.","doi":"10.24963/ijcai.2019/200","url":"https://ijcai.org/proceedings/2019/200","pdf":"https://ijcai.org/proceedings/2019/0200.pdf","markdown":"https://ijcai.org/proceedings/2019/200.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/200","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Humans and AI","track":"Main track","number":200,"pages":{"first":1445,"last":1451},"keywords":["Humans and AI: Cognitive Modeling"],"videos":[],"references":[{"position":1,"raw":"[Bohte et al., 2002] Sander M. Bohte, Joost N. Kok, and Han La Poutre. Error-backpropagation in temporally encod- ed networks of spiking neurons. Neurocomputing, 48(1- 4):17-37, 2002.","title":"Error-backpropagation in temporally encoded networks of spiking neurons","authors":"M Sander, Bohte, N Joost, Han Kok, Poutre La","year":"2002","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Butts et al., 2007] Daniel A. Butts, Chong Weng, Jianzhong Jin, Chun-I Yeh, Nicholas A. Lesica, Jose-Manuel Alon- so, and Garrett B. Stanley. Temporal precision in the neural code and the timescales of natural vision. Nature, 449(7158):92-95, 2007.","title":"Temporal precision in the neural code and the timescales of natural vision","authors":"A Daniel, Chong Butts, Jianzhong Weng, Chun-I Jin, Nicholas A Yeh, Jose-Manuel Lesica, Garrett B Alonso, Stanley","year":"2007","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Fisher, 1936] Ronald A. Fisher. The use of multiple mea- surements in taxonomic problems. Annals of eugenics, 7(2):179-188, 1936.","title":"The use of multiple measurements in taxonomic problems","authors":"Ronald A Fisher","year":"1936","venue":"Annals of eugenics","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Florian, 2012] Rȃzvan V. Florian. The chronotron: a neuron that learns to fire temporally precise spike patterns. PLOS ONE, 7(8):e40233, 2012.","title":"The chronotron: a neuron that learns to fire temporally precise spike patterns","authors":"V Rȃzvan, Florian","year":"2012","venue":"PLOS ONE","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Gerstner and Kistler, 2002] Wulfram Gerstner and Wern- er M. Kistler. Spiking neuron models: Single neurons, populations, plasticity. Cambridge university press, 2002.","title":"Spiking neuron models: Single neurons, populations, plasticity","authors":"Kistler Gerstner, Wulfram Gerstner, Werner M Kistler","year":"2002","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Gütig and Sompolinsky, 2006] Robert Gütig and Haim Sompolinsky. The tempotron: a neuron that learns spike timing-based decisions. Nature neuroscience, 9(3):420, 2006.","title":"Robert Gütig and Haim Sompolinsky. The tempotron: a neuron that learns spike timing-based decisions","authors":"Sompolinsky Gütig","year":"2006","venue":"Nature neuroscience","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Gütig, 2014] Robert Gütig. To spike, or when to spike? Current opinion in neurobiology, 25:134-139, 2014.","title":"To spike, or when to spike?","authors":"Robert Gütig","year":"2014","venue":"Current opinion in neurobiology","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Gütig, 2016] Robert Gütig. Spiking neurons can discover predictive features by aggregate-label learning. Science, 351(6277):aab4113, 2016.","title":"Spiking neurons can discover predictive features by aggregate-label learning","authors":"Robert Gütig","year":"2016","venue":"Science","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Miao et al., 2018] Yu Miao, Huajin Tang, and Gang Pan. A supervised multi-spike learning algorithm for spiking neu- ral networks. International Joint Conference on Neural Networks, pages 1-7, 2018.","title":"A supervised multi-spike learning algorithm for spiking neural networks","authors":"Yu Miao, Huajin Tang, Gang Pan","year":"2018","venue":"International Joint Conference on Neural Networks","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Nakamura et al., 2000] Satoshi Nakamura, Kazuo Hiyane, Futoshi Asano, Takanobu Nishiura, and Takeshi Yamada. Acoustical sound database in real environments for sound scene understanding and hands-free speech recognition. In Language Resources and Evaluation Conference, 2000.","title":"Acoustical sound database in real environments for sound scene understanding and hands-free speech recognition","authors":"Satoshi Nakamura, Kazuo Hiyane, Futoshi Asano, Takanobu Nishiura, Takeshi Yamada","year":"2000","venue":"Language Resources and Evaluation Conference","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Orchard et al., 2015] Garrick Orchard, Cedric Meyer, Ralph Etienne-Cummings, Christoph Posch, Nitish Thakor, and Ryad Benosman. Hfirst: a temporal approach to object recognition. IEEE transactions on pattern analysis and machine intelligence, 37(10):2028-2040, 2015.","title":"Hfirst: a temporal approach to object recognition","authors":"Garrick Orchard, Cedric Meyer, Ralph Etienne-Cummings, Christoph Posch, Nitish Thakor, Ryad Benosman","year":"2015","venue":"IEEE transactions on pattern analysis and machine intelligence","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Pérez-Carrasco et al., 2013] José A. Pérez-Carrasco, Bo Zhao, Carmen Serrano, Begona Acha, Teresa Serrano-Gotarredona, Shouchun Chen, and Bernabé Linares-Barranco. Mapping from frame-driven to frame- free event-driven vision systems by low-rate rate coding and coincidence processing-application to feedforward convnets. IEEE transactions on pattern analysis and machine intelligence, 35(11):2706-2719, 2013.","title":"Mapping from frame-driven to framefree event-driven vision systems by low-rate rate coding and coincidence processing-application to feedforward convnets","authors":"A José, Bo Pérez-Carrasco, Carmen Zhao, Begona Serrano, Teresa Acha, Shouchun Serrano-Gotarredona, Bernabé Chen, Linares-Barranco","year":"2013","venue":"IEEE transactions on pattern analysis and machine intelligence","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Ponulak and Kasiński, 2010] Filip Ponulak and Andrze- j Kasiński. Supervised learning in spiking neural networks with resume: sequence learning, classification, and spike shifting. Neural Computation, 22(2):467-510, 2010.","title":"Filip Ponulak and Andrzej Kasiński. Supervised learning in spiking neural networks with resume: sequence learning, classification, and spike shifting","authors":"Kasiński Ponulak","year":"2010","venue":"Neural Computation","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Qi et al., 2018] Yu Qi, Jiangrong Shen, Yueming Wang, Huajin Tang, Hang Yu, Zhaohui Wu, and Gang Pan. Joint- ly learning network connections and link weights in spik- ing neural networks. pages 1597-1603. International Joint Conferences on Artificial Intelligence, 2018.","title":"Jointly learning network connections and link weights in spiking neural networks","authors":"Yu Qi, Jiangrong Shen, Yueming Wang, Huajin Tang, Hang Yu, Zhaohui Wu, Gang Pan","year":"2018","venue":"International Joint Conferences on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2018/221"},{"position":15,"raw":"[Song et al., 2000] Sen Song, Kenneth D. Miller, and Lar- ry F. Abbott. Competitive hebbian learning through spike-timing-dependent synaptic plasticity. Nature neuro- science, 3(9):919-926, 2000.","title":"Competitive hebbian learning through spike-timing-dependent synaptic plasticity","authors":"Sen Song, Kenneth D Miller, Larry F Abbott","year":"2000","venue":"Nature neuroscience","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[VanRullen et al., 2005] Rufin VanRullen, Rudy Guyon- neau, and Simon J. Thorpe. Spike times make sense. Trends in neurosciences, 28(1):1-4, 2005.","title":"Spike times make sense","authors":"Rufin Vanrullen, Rudy Guyonneau, Simon J Thorpe","year":"2005","venue":"Trends in neurosciences","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Xiao et al., 2018] Rong Xiao, Huajin Tang, Pengjie Gu, and Xiaoliang Xu. Spike-based encoding and learning of spec- trum features for robust sound recognition. Neurocomput- ing, 2018.","title":"Spike-based encoding and learning of spectrum features for robust sound recognition","authors":"Rong Xiao, Huajin Tang, Pengjie Gu, Xiaoliang Xu","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Xu et al., 2018] Qi Xu, Yu Qi, Hang Yu, Jiangrong Shen, Huajin Tang, and Gang Pan. Csnn: An augmented spiking based framework with perceptron-inception. pages 1646- 1652. International Joint Conferences on Artificial Intelli- gence, 2018.","title":"Csnn: An augmented spiking based framework with perceptron-inception","authors":"Qi Xu, Yu Qi, Hang Yu, Jiangrong Shen, Huajin Tang, Gang Pan","year":"2018","venue":"International Joint Conferences on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2018/228"},{"position":19,"raw":"[Yu et al., 2013] Qiang Yu, Huajin Tang, Kay C. Tan, and Haizhou Li. Precise-spike-driven synaptic plasticity: Learning hetero-association of spatiotemporal spike pat- terns. PLOS ONE, 8(11):e78318, 2013.","title":"Precise-spike-driven synaptic plasticity: Learning hetero-association of spatiotemporal spike patterns","authors":"Qiang Yu, Huajin Tang, Kay C Tan, Haizhou Li","year":"2013","venue":"PLOS ONE","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Yu et al., 2018a] Qiang Yu, Haizhou Li, and Kay C. Tan. Spike timing or rate? neurons learn to make decisions for both through threshold-driven plasticity. IEEE transac- tions on cybernetics, (99):1-12, 2018.","title":"Spike timing or rate? neurons learn to make decisions for both through threshold-driven plasticity","authors":"Yu","year":"2018","venue":"IEEE transactions on cybernetics","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Yu et al., 2018b] Qiang Yu, Longbiao Wang, and Jianwu Dang. Efficient multi-spike learning with tempotron-like ltp and psd-like ltd. In International Conference on Neural Information Processing, pages 545-554, 2018.","title":"Efficient multi-spike learning with tempotron-like ltp and psd-like ltd","authors":"Yu","year":"2018","venue":"International Conference on Neural Information Processing","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Zhang et al., 2018] Malu Zhang, Hong Qu, Ammar Be- latreche, Yi Chen, and Zhang Yi. A highly effective and robust membrane potential-driven supervised learning method for spiking neurons. IEEE transactions on neural networks and learning systems, (99):1-15, 2018.","title":"A highly effective and robust membrane potential-driven supervised learning method for spiking neurons","authors":"Malu Zhang, Hong Qu, Ammar Belatreche, Yi Chen, Zhang Yi","year":"2018","venue":"IEEE transactions on neural networks and learning systems","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Zhao et al., 2014] Bo Zhao, Ruoxi Ding, Shoushun Chen, Bernabe Linares-Barranco, and Huajin Tang. Feedforward categorization on aer motion events using cortex-like fea- tures in a spiking neural network. IEEE transactions on neural networks and learning systems, 26(9):1963-1978, 2014.","title":"Feedforward categorization on aer motion events using cortex-like features in a spiking neural network","authors":"Bo Zhao, Ruoxi Ding, Shoushun Chen, Bernabe Linares-Barranco, Huajin Tang","year":"2014","venue":"IEEE transactions on neural networks and learning systems","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}