{"type":"ScholarlyArticle","title":"CSNN: An Augmented Spiking based Framework with Perceptron-Inception","authors":[{"name":"Qi Xu","slug":"qi-xu","given":"Qi","family":"Xu","affiliation":"College of Computer Science and Technology , Zhejiang University"},{"name":"Yu Qi","slug":"yu-qi","given":"Yu","family":"Qi","affiliation":"College of Computer Science and Technology , Zhejiang University"},{"name":"Hang Yu","slug":"hang-yu","given":"Hang","family":"Yu","affiliation":"College of Computer Science and Technology , Zhejiang University"},{"name":"Jiangrong Shen","slug":"jiangrong-shen","given":"Jiangrong","family":"Shen","affiliation":"College of Computer Science and Technology , Zhejiang University; Qiushi Academy for Advanced Studies , Zhejiang University"},{"name":"Huajin Tang","slug":"huajin-tang","given":"Huajin","family":"Tang","affiliation":"College of Computer Science , Sichuan University"},{"name":"Gang Pan","slug":"gang-pan","given":"Gang","family":"Pan","affiliation":"College of Computer Science and Technology , Zhejiang University"}],"abstract":"Spiking Neural Networks (SNNs) represent and transmit information in spikes, which is considered more biologically realistic and computationally powerful than the traditional Artificial Neural Networks. The spiking neurons encode useful temporal information and possess highly anti-noise property. The feature extraction ability of typical SNNs is limited by shallow structures. This paper focuses on improving the feature extraction ability of SNNs in virtue of powerful feature extraction ability of Convolutional Neural Networks (CNNs). CNNs can extract abstract features resorting to the structure of the convolutional feature maps. We propose a CNN-SNN (CSNN) model to combine feature learning ability of CNNs with cognition ability of SNNs.  The CSNN model learns the encoded spatial temporal representations of images in an event-driven way. We evaluate the CSNN model on the handwritten digits images dataset MNIST and its variational databases. In the presented experimental results, the proposed CSNN model is evaluated regarding learning capabilities, encoding mechanisms, robustness to noisy stimuli and its classification performance. The results show that CSNN behaves well compared to other cognitive models with significantly fewer neurons and training samples. Our work brings more biological realism into modern image classification models, with the hope that these models can inform how the brain performs this high-level vision task.","doi":"10.24963/ijcai.2018/228","url":"https://ijcai.org/proceedings/2018/228","pdf":"https://ijcai.org/proceedings/2018/0228.pdf","markdown":"https://ijcai.org/proceedings/2018/228.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/228","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Humans and AI","track":"Main track","number":228,"pages":{"first":1646,"last":1652},"keywords":["Humans and AI: Cognitive Modeling","Machine Learning: Neural Networks","Humans and AI: Cognitive Systems","Humans and AI: Brain Sciences"],"videos":[],"references":[{"position":1,"raw":"[Berry and Meister, 1998] Michael J Berry and Markus Meister. Refractoriness and neural precision. Journal of Neuroscience, 18(6):2200, 1998.","title":"Refractoriness and neural precision","authors":"J Michael, Markus Berry, Meister","year":"1998","venue":"Journal of Neuroscience","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Diehl and Cook, 2015] Peter U. Diehl and Matthew Cook. Unsupervised learning of digit recognition using spike- timing-dependent plasticity. Frontiers in Computational Neuroscience, 9:99, 2015.","title":"Unsupervised learning of digit recognition using spiketiming-dependent plasticity","authors":"U Peter, Matthew Diehl, Cook","year":"2015","venue":"Frontiers in Computational Neuroscience","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Hodgkin and Huxley, 1952] A. L. Hodgkin and A. F. Hux- ley. A quantitative description of membrane current and its application to conduction and excitation in nerve. Bulletin of Mathematical Biology, 117(4):500-544, 1952.","title":"A quantitative description of membrane current and its application to conduction and excitation in nerve","authors":"A L Hodgkin, A F Huxley","year":"1952","venue":"Bulletin of Mathematical Biology","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Hu et al., 2013] Jun Hu, Huajin Tang, Kay Chen. Tan, Haizhou Li, and Luping Shi. A spike-timing-based inte- grated model for pattern recognition. Neural Computation, 25(2):450-472, 2013.","title":"A spike-timing-based integrated model for pattern recognition","authors":"Jun Hu, Huajin Tang, Kay Chen Tan, Haizhou Li, Luping Shi","year":"2013","venue":"Neural Computation","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Hu et al., 2016] Jun Hu, Huajin Tang, Kay Chen Tan, and Haizhou Li. How the brain formulates memory: A spatio- temporal model research frontier. IEEE Computational In- telligence Magazine, 11(2):56-68, 2016.","title":"How the brain formulates memory: A spatiotemporal model research frontier","authors":"Jun Hu, Huajin Tang, Kay Chen Tan, Haizhou Li","year":"2016","venue":"IEEE Computational Intelligence Magazine","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Hubel and Wiesel, 1968] David H Hubel and Torsten N Wiesel. Receptive fields and functional architecture of monkey striate cortex. Journal of Physiology, 195(1):215- 243, 1968.","title":"Receptive fields and functional architecture of monkey striate cortex","authors":"H David, Torsten N Hubel, Wiesel","year":"1968","venue":"Journal of Physiology","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hussain et al., 2014] S Hussain, Shih Chii Liu, and A Basu. Improved margin multi-class classification using dendritic neurons with morphological learning. In IEEE Interna- tional Symposium on Circuits and Systems, pages 2640- 2643, 2014.","title":"Improved margin multi-class classification using dendritic neurons with morphological learning","authors":"Shih Chii Hussain, Liu, Basu","year":"2014","venue":"IEEE International Symposium on Circuits and Systems","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Izhikevich, 2001] Eugene M. Izhikevich. Resonate-and-fire neurons. Neural Networks, 14(6-7):883-894, 2001.","title":"Resonate-and-fire neurons","authors":"Eugene M Izhikevich","year":"2001","venue":"Neural Networks","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Izhikevich, 2003] Eugene M Izhikevich. Simple model of spiking neurons. IEEE Transactions on Neural Networks, 14(6):1569, 2003.","title":"Simple model of spiking neurons","authors":"Eugene M Izhikevich","year":"2003","venue":"IEEE Transactions on Neural Networks","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Krizhevsky et al., 2012] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. ImageNet classification with deep convolutional neural networks. In International Confer- ence on Neural Information Processing Systems, pages 1097-1105, 2012.","title":"ImageNet classification with deep convolutional neural networks","authors":"Alex Krizhevsky, Ilya Sutskever, Geoffrey E Hinton","year":"2012","venue":"International Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Lampl et al., 2004] Ilan Lampl, David Ferster, Tomaso Pog- gio, and Maximilian Riesenhuber. Intracellular measure- ments of spatial integration and the MAX operation in complex cells of the cat primary visual cortex. Journal of Neurophysiology, 92(5):2704, 2004.","title":"Intracellular measurements of spatial integration and the MAX operation in complex cells of the cat primary visual cortex","authors":"Ilan Lampl, David Ferster, Tomaso Poggio, Maximilian Riesenhuber","year":"2004","venue":"Journal of Neurophysiology","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Larochelle et al., 2007] Hugo Larochelle, Dumitru Erhan, Aaron Courville, James Bergstra, and Yoshua Bengio. An empirical evaluation of deep architectures on problems with many factors of variation. In International Confer- ence on Machine Learning, pages 473-480, 2007.","title":"An empirical evaluation of deep architectures on problems with many factors of variation","authors":"Hugo Larochelle, Dumitru Erhan, Aaron Courville, James Bergstra, Yoshua Bengio","year":"2007","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Lécun et al., 1998] Yann Lécun, Leon Bottou, Yoshua Ben- gio, and Patrick Haffner. Gradient-based learning ap- plied to document recognition. Proceedings of the IEEE, 86(11):2278-2324, 1998.","title":"Gradient-based learning applied to document recognition","authors":"Yann Lécun, Leon Bottou, Yoshua Bengio, Patrick Haffner","year":"1998","venue":"Proceedings of the IEEE","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ma et al., 2017] De Ma, Juncheng Shen, Zonghua Gu, Ming Zhang, Xiaolei Zhu, Xiaoqiang Xu, Qi Xu, Yangjing Shen, and Gang Pan. Darwin: A neuromorphic hardware co-processor based on spiking neural networks. Journal of Systems Architecture, 2017.","title":"Darwin: A neuromorphic hardware co-processor based on spiking neural networks","authors":"De Ma, Juncheng Shen, Zonghua Gu, Ming Zhang, Xiaolei Zhu, Xiaoqiang Xu, Qi Xu, Yangjing Shen, Gang Pan","year":"2017","venue":"Journal of Systems Architecture","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Merolla et al., 2011] Paul Merolla, John Arthur, Filipp Akopyan, Nabil Imam, Rajit Manohar, and Dharmendra S. Modha. A digital neurosynaptic core using embedded crossbar memory with 45pj per spike in 45nm. In Cus- tom Integrated Circuits Conference, pages 1-4, 2011.","title":"A digital neurosynaptic core using embedded crossbar memory with 45pj per spike in 45nm","authors":"Paul Merolla, John Arthur, Filipp Akopyan, Nabil Imam, Rajit Manohar, Dharmendra S Modha","year":"2011","venue":"Custom Integrated Circuits Conference","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Oster et al., 2005] Matthias Oster, Rodney J Douglas, and Shihchii Liu. Computation with spikes in a winner-take- all network. Neural Computation, 21(9):2437, 2005.","title":"Computation with spikes in a winner-takeall network","authors":"Matthias Oster, Rodney J Douglas, Shihchii Liu","year":"2005","venue":"Neural Computation","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Perrinet et al., 2004] Laurent Perrinet, Manuel Samuelides, and Simon Thorpe. Sparse spike coding in an asyn- chronous feed-forward multi-layer neural network using matching pursuit. Neurocomputing, 57:125-134, 2004.","title":"Sparse spike coding in an asynchronous feed-forward multi-layer neural network using matching pursuit","authors":"Laurent Perrinet, Manuel Samuelides, Simon Thorpe","year":"2004","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Peter et al., 2013] O'Connor Peter, Neil Daniel, Shih Chii Liu, Delbruck Tobi, and Pfeiffer Michael. Real-time clas- sification and sensor fusion with a spiking deep belief net- work. Frontiers in Neuroscience, 7:178, 2013.","title":"Real-time classification and sensor fusion with a spiking deep belief network","authors":"O'connor Peter, Neil Daniel, Chii Shih, Delbruck Liu, Pfeiffer Tobi, Michael","year":"2013","venue":"Frontiers in Neuroscience","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Shen et al., 2017] Jiangrong Shen, Kang Lin, Yueming Wang, and Gang Pan. Character recognition from trajecto- ry by recurrent spiking neural networks. In International Conference of the IEEE Engineering in Medicine and Bi- ology Society, page 2900, 2017.","title":"Character recognition from trajectory by recurrent spiking neural networks","authors":"Jiangrong Shen, Kang Lin, Yueming Wang, Gang Pan","year":"2017","venue":"International Conference of the IEEE Engineering in Medicine and Biology Society","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Uzzell and Chichilnisky, 2004] V. J. Uzzell and E. J. Chichilnisky. Precision of spike trains in primate retinal ganglion cells. Journal of Neurophysiology, 92(2):780-9, 2004.","title":"Precision of spike trains in primate retinal ganglion cells","authors":"V J Uzzell, E J Chichilnisky","year":"2004","venue":"Journal of Neurophysiology","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Xu and Pan, 2017] Qi Xu and Gang Pan. SparseConnect: regularising CNNs on fully connected layers. Electronics Letters, 53(18):1246-1248, 2017.","title":"SparseConnect: regularising CNNs on fully connected layers","authors":"Pan ; ] Qi Xu, Gang Xu, Pan","year":"2017","venue":"Electronics Letters","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Yu et al., 2002] Angela J Yu, Martin A Giese, and Toma- so Poggio. Biophysiologically plausible implementa- tions of the maximum operation. Neural Computation, 14(12):2857, 2002.","title":"Biophysiologically plausible implementations of the maximum operation","authors":"Angela J Yu, Martin A Giese, Tomaso Poggio","year":"2002","venue":"Neural Computation","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Yu et al., 2013] Qiang Yu, Huajin Tang, Kay Chen Tan, and Haizhou Li. Rapid feedforward computation by tempo- ral encoding and learning with spiking neurons. IEEE Transaction on Neural Networks and Learning Systems, 24(10):1539-1552, 2013.","title":"Rapid feedforward computation by temporal encoding and learning with spiking neurons","authors":"Qiang Yu, Huajin Tang, Kay Chen Tan, Haizhou Li","year":"2013","venue":"IEEE Transaction on Neural Networks and Learning Systems","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zhou et al., 2018] Zhen Zhou, Jian Bao Wang, Yu Feng Zang, and Gang Pan. PAIR comparison between two within-group conditions of resting-state fMRI improves classification accuracy. Frontiers in Neuroscience, 11:740, 2018.","title":"PAIR comparison between two within-group conditions of resting-state fMRI improves classification accuracy","authors":"Zhen Zhou, Jian, Bao Wang, Yu Feng Zang, Gang Pan","year":"2018","venue":"Frontiers in Neuroscience","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}