{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:24:01Z","timestamp":1778171041496,"version":"3.51.4"},"reference-count":35,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2018]]},"DOI":"10.1587\/transinf.2017rcp0013","type":"journal-article","created":{"date-parts":[[2018,1,31]],"date-time":"2018-01-31T22:33:38Z","timestamp":1517438018000},"page":"376-386","source":"Crossref","is-referenced-by-count":20,"title":["A Threshold Neuron Pruning for a Binarized Deep Neural Network on an FPGA"],"prefix":"10.1587","volume":"E101.D","author":[{"given":"Tomoya","family":"FUJII","sequence":"first","affiliation":[{"name":"Department of Information and Communications Engineering, Tokyo Institute of Technology"}]},{"given":"Shimpei","family":"SATO","sequence":"additional","affiliation":[{"name":"Department of Information and Communications Engineering, Tokyo Institute of Technology"}]},{"given":"Hiroki","family":"NAKAHARA","sequence":"additional","affiliation":[{"name":"Department of Information and Communications Engineering, Tokyo Institute of Technology"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] S. Anwar, K. Hwang, and W. Sung, \u201cStructured pruning of deep convolutional neural networks,\u201d Computer Research Repository (CoRR), Dec., 2015. https:\/\/arxiv.org\/ftp\/arxiv\/papers\/1512\/1512.08571.pdf"},{"key":"2","unstructured":"[2] Caffe: Deep learning framework, http:\/\/caffe.berkeleyvision.org\/"},{"key":"3","unstructured":"[3] Chainer: A powerful, flexible, and intuitive framework of neural networks, http:\/\/chainer.org\/"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] S. Chakradhar, M. Sankaradas, V. Jakkula, and S. Cadambi, \u201cA dynamically configurable coprocessor for convolutional neural networks,\u201d Annual Int'l Symp. on Computer Architecture (ISCA), pp.247-257, 2010. 10.1145\/1815961.1815993","DOI":"10.1145\/1816038.1815993"},{"key":"5","unstructured":"[5] The CIFAR-10 data set, http:\/\/www.cs.toronto.edu\/~kriz\/cifar.html"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] D.C. Ciresan, U. Meier, and J. Schmidhuber, \u201cMulti-column deep neural networks for image classification,\u201d In Proc. CVPR, 2012. 10.1109\/cvpr.2012.6248110","DOI":"10.1109\/CVPR.2012.6248110"},{"key":"7","unstructured":"[7] CUDA-Convent2: Fast convolutional neural network in C++\/CUDA, https:\/\/code.google.com\/p\/cuda-convnet2\/"},{"key":"8","unstructured":"[8] M. Courbariaux, I. Hubara, D. Soudry, R.E. Yaniv, and Y. Bengio, \u201cBinarized neural networks: Training deep neural networks with weights and activations constrained to +1 or-1,\u201d Computer Research Repository (CoRR), March 2016, http:\/\/arxiv.org\/pdf\/1602.02830v3.pdf"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] J. Donahue, L.A. Hendricks, S. Guadarrama, M. Rohrbach, S. Venugopalan, K. Saenko, and T. Darrell, \u201cLong-term recurrent convolutional networks for visual recognition and description,\u201d In Proc. CVPR, 2015. 10.1109\/cvpr.2015.7298878","DOI":"10.21236\/ADA623249"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] A. Dundar, J. Jin, V. Gokhale, B. Martini, and E. Culurciello, \u201cMemory access optimized routing scheme for deep networks on a mobile coprocessor,\u201d HPEC2014, pp.1-6, 2014. 10.1109\/hpec.2014.7040963","DOI":"10.1109\/HPEC.2014.7040963"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] C. Farabet, C. Poulet, J.Y. Han, and Y. LeCun, \u201cCNP: An FPGA-based processor for convolutional networks,\u201d FPL2009, pp.32-37, 2009. 10.1109\/fpl.2009.5272559","DOI":"10.1109\/FPL.2009.5272559"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] C. Farabet, B. Martini, P. Akselrod, S. Talay, Y. LeCun, and E. Culurciello, \u201cHardware accelerated convolutional neural networks for synthetic vision systems,\u201d ISCAS2010, pp.257-260, 2010. 10.1109\/iscas.2010.5537908","DOI":"10.1109\/ISCAS.2010.5537908"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] T. Fujii, S. Sato, H. Nakahara, and M. Motomura, \u201cAn FPGA Realization of a Deep Convolutional Neural Network using a Threshold Neuron Pruning,\u201d Int'l Symp. on Applied Reconfigurable Computing (ARC2017), pp.268-290, 2017. 10.1007\/978-3-319-56258-2_23","DOI":"10.1007\/978-3-319-56258-2_23"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] R. Girshick, J. Donahue, T. Darrell, and J. Malik, \u201cRich feature hierarchies for accurate object detection and semantic segmentation,\u201d In Proc. CVPR, 2014. 10.1109\/cvpr.2014.81","DOI":"10.1109\/CVPR.2014.81"},{"key":"15","unstructured":"[15] I.J. Goodfellow, Y. Bulatov, J. Ibarz, S. Arnoud, and Vi. Shet, \u201cMulti-digit number recognition from street view imagery using deep convolutional neural networks,\u201d arXiv prprint arXiv: 1312.6082, 2013."},{"key":"16","unstructured":"[16] S. Han, H. Mao, and W.J. Dally, \u201cDeep Compression: Compressing deep neural networks with pruning, trained quantization and huffman coding,\u201d ICLR2016, pp.1-14, 2016."},{"key":"17","unstructured":"[17] G.E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R.R. Salakhutdinov, \u201cImproving neural networks by preventing co-adaptation of feature detectors,\u201d arXiv:1207.0580, 2012."},{"key":"18","doi-asserted-by":"publisher","unstructured":"[18] S. Ji, W. Xu, M. Yang, and K. Yu, \u201c3D convolutional neural networks for human action recognition,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.35, no.1, pp.221-231, 2013. 10.1109\/tpami.2012.59","DOI":"10.1109\/TPAMI.2012.59"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] A. Karpathy, G. Toderici, S. Shetty, T. Leung, R. Sukthankar, and L. Fei-Fei, \u201cLarge-scale video classification with convolutional neural networks,\u201d In Proc. CVPR, pp.1725-1732, 2014. 10.1109\/cvpr.2014.223","DOI":"10.1109\/CVPR.2014.223"},{"key":"20","unstructured":"[20] M. Kim and P. Smaragdis, \u201cBitwise neural networks,\u201d CoRR, abs\/1601.06071, 2016."},{"key":"21","doi-asserted-by":"publisher","unstructured":"[21] Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, \u201cGradient-based learning applied to document recognition,\u201d Proc. IEEE, vol.86, no.11, pp.2278-2324, 1998. 10.1109\/5.726791","DOI":"10.1109\/5.726791"},{"key":"22","unstructured":"[22] V. Nair and G.E. Hinton, \u201cRectified linear units improve restricted Boltzmann machines,\u201d ICML, pp.807-814, 2010."},{"key":"23","unstructured":"[23] https:\/\/github.com\/charlyng\/Embedded-Deep-Learning\/tree\/master\/Benchmark-Performance"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] M. Peemen, A.A.A. Setio, B. Mesman, and H. Corporaal, \u201cMemory-centric accelerator design for convolutional neural networks,\u201d ICCD2013, pp.13-19, 2013. 10.1109\/iccd.2013.6657019","DOI":"10.1109\/ICCD.2013.6657019"},{"key":"25","unstructured":"[25] M. Rastegari, V. Ordonez, J. Redmon, and A. Farhadi, \u201cXNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks,\u201d https:\/\/arxiv.org\/pdf\/1603.05279.pdf"},{"key":"26","unstructured":"[26] K. Simonyan and A. Zisserman, \u201cVery deep convolutional networks for large-scale image recognition,\u201d ICLR2015, pp.1-14, 2015."},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] Y. Taigman, M. Yang, M. Ranzato, and L. Wolf, \u201cDeepface: Closing the gap to human-level performance in face verification,\u201d In Proc. CVPR, pp.1701-1708, 2014. 10.1109\/cvpr.2014.220","DOI":"10.1109\/CVPR.2014.220"},{"key":"28","unstructured":"[28] Theano, http:\/\/deeplearning.net\/software\/theano\/"},{"key":"29","unstructured":"[29] Torch: A scientific computing framework for LUTJIT, http:\/\/torch.ch\/"},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] A. Toshev and C. Szegedy, \u201cDeeppose: Human pose estimatiion via deep neural networks,\u201d In Proc. CVPR, 2014. 10.1109\/cvpr.2014.214","DOI":"10.1109\/CVPR.2014.214"},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] Y. Umuroglu, N.J. Fraser, G. Gambardella, M. Blott, P. Leong, M. Jahre, and K. Vissers, \u201cFINN: A Framework for Fast, Scalable Binarized Neural Network Inference,\u201d ISFPGA, 2017. Source code for the Xilinx PYNQ board: https:\/\/github.com\/Xilinx\/BNN-PYNQ","DOI":"10.1145\/3020078.3021744"},{"key":"32","doi-asserted-by":"crossref","unstructured":"[32] J. Qiu, J. Wang, S. Yao, K. Guo, B. Li, E. Zhou, J. Yu, T. Tang, N. Xu, S. Song, Y. Wang, and H. Yang, \u201cGoing deeper with embedded FPGA platform for convolutional neural network,\u201d FPGA2016, pp.26-35, 2016. 10.1145\/2847263.2847265","DOI":"10.1145\/2847263.2847265"},{"key":"33","doi-asserted-by":"crossref","unstructured":"[33] C. Zhang, P. Li, G. Sun, Y. Guan, B. Xiao, and J. Cong, \u201cOptimizing FPGA-based accelerator design for deep convolutional neural networks,\u201d FPGA2015, pp.161-170, 2015. 10.1145\/2684746.2689060","DOI":"10.1145\/2684746.2689060"},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] R. Zhao, W. Song, W. Zhang, T. Xing, J.-H. Lin, M. Srivastava, R. Gupta, and Z. Zhang, \u201cAccelerating Binarized Convolutional Neural Networks with Software-Programmable FPGAs,\u201d ISFPGA, pp.15-24, 2017. 10.1145\/3020078.3021741","DOI":"10.1145\/3020078.3021741"},{"key":"35","unstructured":"[35] S. Zhou, Y. Wu, Z. Ni, X. Zhou, H. Wen, and Y. Zou, \u201cDoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients,\u201d http:\/\/arxiv.org\/pdf\/1606.06160v2.pdf"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E101.D\/2\/E101.D_2017RCP0013\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,10]],"date-time":"2019-10-10T03:14:42Z","timestamp":1570677282000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E101.D\/2\/E101.D_2017RCP0013\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"references-count":35,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2018]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2017rcp0013","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]}}}