{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T13:39:59Z","timestamp":1787924399390,"version":"build-2784847793"},"reference-count":77,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T00:00:00Z","timestamp":1667865600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T00:00:00Z","timestamp":1667865600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"NWO EDIC Project"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Sparse neural networks attract increasing interest as they exhibit comparable performance to their dense counterparts while being computationally efficient. Pruning the dense neural networks is among the most widely used methods to obtain a sparse neural network. Driven by the high training cost of such methods that can be unaffordable for a low-resource device, training sparse neural networks sparsely from scratch has recently gained attention. However, existing sparse training algorithms suffer from various issues, including poor performance in high sparsity scenarios, computing dense gradient information during training, or pure random topology search. In this paper, inspired by the evolution of the biological brain and the Hebbian learning theory, we present a new sparse training approach that evolves sparse neural networks according to the behavior of neurons in the network. Concretely, by exploiting the cosine similarity metric to measure the importance of the connections, our proposed method, \u201cCosine similarity-based and random topology exploration (CTRE)\u201d, evolves the topology of sparse neural networks by adding the most important connections to the network without calculating dense gradient in the backward. We carried out different experiments on eight datasets, including tabular, image, and text datasets, and demonstrate that our proposed method outperforms several state-of-the-art sparse training algorithms in extremely sparse neural networks by a large gap. The implementation code is available on Github.<\/jats:p>","DOI":"10.1007\/s10994-022-06266-w","type":"journal-article","created":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T17:02:56Z","timestamp":1667926976000},"page":"4411-4452","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["A brain-inspired algorithm for training highly sparse neural networks"],"prefix":"10.1007","volume":"111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8183-5541","authenticated-orcid":false,"given":"Zahra","family":"Atashgahi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joost","family":"Pieterse","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiwei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Decebal Constantin","family":"Mocanu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raymond","family":"Veldhuis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mykola","family":"Pechenizkiy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,8]]},"reference":[{"key":"6266_CR1","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., ... Zheng, X. (2015). TensorFlow: Large-scale machine learning on heterogeneous systems, 2015. https:\/\/www.tensorflow.org\/. Software available from tensorflow.org."},{"key":"6266_CR2","unstructured":"Arora, S., Bhaskara, A., Ge, R., & Ma, T. (2014). Provable bounds for learning some deep representations. In International conference on machine learning (pp. 584\u2013592). PMLR, 2014."},{"key":"6266_CR3","doi-asserted-by":"crossref","unstructured":"Atashgahi, Z., Sokar, G., van der Lee, T., Mocanu, E., Mocanu, D. C., Veldhuis, R., & Pechenizkiy, M. (2022).Quick and robust feature selection: the strength of energy-efficient sparse training for autoencoders. Machine Learning (ECML-PKDD 2022 journal track) 1\u201338.","DOI":"10.1007\/s10994-021-06063-x"},{"key":"6266_CR4","unstructured":"Bartunov, S., Santoro, A., Richards, B., Marris, L., Hinton, G. E., & Lillicrap, T. (2018). Assessing the scalability of biologically-motivated deep learning algorithms and architectures. In Proceedings of the 32nd international conference on neural information processing systems (pp. 9390\u20139400)."},{"key":"6266_CR5","unstructured":"Bellec, G., Kappel, D., Maass, W., & Legenstein, R. (2018). Deep rewiring: Training very sparse deep networks. In International conference on learning representations. https:\/\/openreview.net\/forum?id=BJ_wN01C-."},{"key":"6266_CR6","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D, Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J., Winter, C., ... Amodei, D. (2020). Language models are few-shot learners. In Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.\u00a0F. & Lin,H. (eds.), Advances in neural information processing systems (Vol. 33, pp. 1877\u20131901). Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf."},{"key":"6266_CR7","doi-asserted-by":"crossref","unstructured":"Dai, X., Yin, H., & Jha, N.K .(2019). Nest: A neural network synthesis tool based on a grow-and-prune paradigm. IEEE Transactions on Computers, 68(10):1487\u20131497.","DOI":"10.1109\/TC.2019.2914438"},{"key":"6266_CR8","unstructured":"de\u00a0Jorge, P., Sanyal, A., Behl, H.S, Torr, P.H.S., Rogez, G., & Dokania, P.K .(2020). Progressive skeletonization: Trimming more fat from a network at initialization. arXiv preprint arXiv:2006.09081."},{"key":"6266_CR9","unstructured":"Dettmers, T., & Zettlemoyer, L. (2019). Sparse networks from scratch: Faster training without losing performance. arXiv preprint arXiv:1907.04840."},{"key":"6266_CR10","unstructured":"Evci, U., Gale, T., Menick, J., Castro, P. S., & Elsen, E. (2020). Rigging the lottery: Making all tickets winners. In International conference on machine learning (pp. 2943\u20132952). PMLR, 2020."},{"key":"6266_CR11","unstructured":"Fanty, M., & Cole, R. (1991). Spoken letter recognition. In Advances in neural information processing systems (pp. 220\u2013226)."},{"key":"6266_CR12","unstructured":"Frankle, J., & Carbin, M. (2018). The lottery ticket hypothesis: Finding sparse, trainable neural networks. arXiv preprint arXiv:1803.03635."},{"issue":"11","key":"6266_CR13","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000211","volume":"4","author":"K Friston","year":"2008","unstructured":"Friston, K. (2008). Hierarchical models in the brain. PLoS Computational Biology, 4(11), e1000211.","journal-title":"PLoS Computational Biology"},{"key":"6266_CR14","unstructured":"Gale, T., Elsen, E., & Hooker, S.(2019). The state of sparsity in deep neural networks. arXiv preprint arXiv:1902.09574."},{"key":"6266_CR15","unstructured":"Galke, L., & Scherp, A. (2021). Forget me not: A gentle reminder to mind the simple multi-layer perceptron baseline for text classification. arXiv preprint arXiv:2109.03777."},{"key":"6266_CR16","doi-asserted-by":"crossref","unstructured":"Gordon, A., Eban, E., Nachum, O., Chen, B., Wu, H., Yang, T.-J., & Choi, E. (2018). Morphnet: Fast & simple resource-constrained structure learning of deep networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1586\u20131595).","DOI":"10.1109\/CVPR.2018.00171"},{"key":"6266_CR17","unstructured":"Gorishniy, Y., Rubachev, I., Khrulkov, V., & Babenko, A. (2021). Revisiting deep learning models for tabular data. arXiv preprint arXiv:2106.11959."},{"key":"6266_CR18","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A.-R., & Hinton, G. (2013). Speech recognition with deep recurrent neural networks. In 2013 IEEE international conference on acoustics, speech and signal processing (pp. 6645\u20136649). IEEE.","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"6266_CR19","unstructured":"AI High-Level\u00a0Expert Group. (2020). Assessment list for trustworthy artificial intelligence (ALTAI) for self-assessment."},{"key":"6266_CR20","unstructured":"Guo, Y., Yao, A., & Chen, Y.(2016). Dynamic network surgery for efficient dnns. In Proceedings of the 30th international conference on neural information processing systems, NIPS\u201916 (pp. 1387-1395). Red Hook, NY: Curran Associates Inc. ISBN 9781510838819."},{"key":"6266_CR21","unstructured":"Guyon, I., Gunn, S., Nikravesh, M., & Zadeh, L.A .(2008). Feature extraction: Foundations and applications (Vol. 207). Springer."},{"key":"6266_CR22","doi-asserted-by":"crossref","unstructured":"Han, J., Kamber, M., & Pei, J., et al. (2012). Getting to know your data. Data mining (pp. 39\u201382). Netherlands: Elsevier Amsterdam.","DOI":"10.1016\/B978-0-12-381479-1.00002-2"},{"key":"6266_CR23","unstructured":"Han, S., Pool, J., Tran, J., & Dally, W.J .(2015). Learning both weights and connections for efficient neural networks. In Proceedings of the 28th international conference on neural information processing systems (Vol. 1, pp. 1135\u20131143)."},{"key":"6266_CR24","unstructured":"Hassibi, B., & Stork, D.G.(1993). Second order derivatives for network pruning: Optimal brain surgeon. In Advances in neural information processing systems (pp. 164\u2013171)."},{"key":"6266_CR25","doi-asserted-by":"crossref","unstructured":"Hebb, D.O. (2005). The organization of behavior: A neuropsychological theory. Psychology Press.","DOI":"10.4324\/9781410612403"},{"key":"6266_CR26","unstructured":"Hestness, J., Narang, S., Ardalani, N., Diamos, G., Jun, H., Kianinejad, H., Patwary, M., Ali, M., Yang, Y., & Zhou, Y. (2017). Deep learning scaling is predictable, empirically. arXiv preprint arXiv:1712.00409."},{"key":"6266_CR27","unstructured":"Hoefler, T., Alistarh, D., Ben-Nun, T., Dryden, N., & Peste, A. (2021). Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks. arXiv preprint arXiv:2102.00554."},{"key":"6266_CR28","first-page":"20744","volume":"33","author":"S Jayakumar","year":"2020","unstructured":"Jayakumar, S., Pascanu, R., Rae, J., Osindero, S., & Elsen, E. (2020). Top-kast: Top-k always sparse training. Advances in Neural Information Processing Systems, 33, 20744\u201320754.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6266_CR29","doi-asserted-by":"crossref","unstructured":"Jouppi, N.P, Young, C., Patil, N., Patterson, D., Agrawal, G., Bajwa, R., Bates, S., Bhatia, S., Boden, N., & Borchers, A. et\u00a0al.(2017). In-datacenter performance analysis of a tensor processing unit. In Proceedings of the 44th annual international symposium on computer architecture (pp. 1\u201312).","DOI":"10.1145\/3079856.3080246"},{"key":"6266_CR30","unstructured":"Junjie, L., Zhe, X., Runbin, S., Cheung, R.C.C., & So, H.K.H.(2019). Dynamic sparse training: Find efficient sparse network from scratch with trainable masked layers. In International conference on learning representations."},{"key":"6266_CR31","doi-asserted-by":"crossref","unstructured":"Kepner, J., & Robinett, R. (2019). Radix-net: Structured sparse matrices for deep neural networks. In 2019 IEEE international parallel and distributed processing symposium workshops (IPDPSW) (pp. 268\u2013274). IEEE.","DOI":"10.1109\/IPDPSW.2019.00051"},{"key":"6266_CR32","unstructured":"Krizhevsky, A., & Hinton, G. et\u00a0al.(2009). Learning multiple layers of features from tiny images."},{"key":"6266_CR33","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.neucom.2014.11.022","volume":"152","author":"E Kuriscak","year":"2015","unstructured":"Kuriscak, E., Marsalek, P., Stroffek, J., & Toth, P. G. (2015). Biological context of hebb learning in artificial neural networks, a review. Neurocomputing, 152, 27\u201335.","journal-title":"Neurocomputing"},{"key":"6266_CR34","unstructured":"Kusupati, A., Ramanujan, V., Somani, R., Wortsman, M., Jain, P., Kakade, S., & Farhadi, A. (2020). Soft threshold weight reparameterization for learnable sparsity. In Hal, D. III, & Aarti, S. (eds), Proceedings of the 37th international conference on machine learning (Vol. 119, pp. 5544\u20135555). http:\/\/proceedings.mlr.press\/v119\/kusupati20a.html."},{"key":"6266_CR35","doi-asserted-by":"crossref","unstructured":"Lang, K. (1995). Newsweeder: Learning to filter netnews. In Machine learning proceedings 1995 (pp. 331\u2013339). Elsevier.","DOI":"10.1016\/B978-1-55860-377-6.50048-7"},{"key":"6266_CR36","unstructured":"LeCun, Y. (1998). The mnist database of handwritten digits. http:\/\/yann. lecun. com\/exdb\/mnist\/."},{"key":"6266_CR37","unstructured":"LeCun, Y., Denker, J.S., & Solla, S.A. (1990). Optimal brain damage. In Advances in neural information processing systems (pp. 598\u2013605)."},{"key":"6266_CR38","unstructured":"Lee, N., Ajanthan, T., & Torr, P.(2019). SNIP: Single-shot network pruning based on connection sensitivity. In International conference on learning representations. https:\/\/openreview.net\/forum?id=B1VZqjAcYX."},{"key":"6266_CR39","doi-asserted-by":"crossref","unstructured":"Li, B., & Han, L. (2013). Distance weighted cosine similarity measure for text classification. In International conference on intelligent data engineering and automated learning (pp. 611\u2013618). Springer.","DOI":"10.1007\/978-3-642-41278-3_74"},{"key":"6266_CR40","doi-asserted-by":"crossref","unstructured":"Li, Y., Gu, S., Mayer, C., Gool, L.V., & Timofte, R. (2020). Group sparsity: The hinge between filter pruning and decomposition for network compression. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 8018\u20138027).","DOI":"10.1109\/CVPR42600.2020.00804"},{"key":"6266_CR41","doi-asserted-by":"crossref","unstructured":"Liang, M., & Hu, X.(2015). Recurrent convolutional neural network for object recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3367\u20133375).","DOI":"10.1109\/CVPR.2015.7298958"},{"issue":"84\u201391","key":"6266_CR42","first-page":"2019","volume":"156","author":"C Liu","year":"2019","unstructured":"Liu, C., & Wu, H. (2019). Channel pruning based on mean gradient for accelerating convolutional neural networks. Signal Processing, 156(84\u201391), 2019.","journal-title":"Signal Processing"},{"key":"6266_CR43","doi-asserted-by":"crossref","unstructured":"Liu, J., Gong, M., & Miao, Q. (2017). Modeling hebb learning rule for unsupervised learning. In IJCAI (pp. 2315\u20132321).","DOI":"10.24963\/ijcai.2017\/322"},{"key":"6266_CR44","doi-asserted-by":"crossref","unstructured":"Liu, S., van der Lee, T., Yaman, A., Atashgahi, Z., Ferrar, D., & Sokar, G., et al. (2020). Topological insights into sparse neural networks. In proceedings of the european conference on machine learning and principles and practice of knowledge discovery in databases (ECML PKDD) (pp. 2006\u201314085).","DOI":"10.1007\/978-3-030-67664-3_17"},{"issue":"7","key":"6266_CR45","doi-asserted-by":"publisher","first-page":"2589","DOI":"10.1007\/s00521-020-05136-7","volume":"33","author":"S Liu","year":"2021","unstructured":"Liu, S., Mocanu, D. C., Matavalam, A. R. R., Pei, Y., & Pechenizkiy, M. (2021). Sparse evolutionary deep learning with over one million artificial neurons on commodity hardware. Neural Computing and Applications, 33(7), 2589\u20132604.","journal-title":"Neural Computing and Applications"},{"key":"6266_CR46","unstructured":"Liu, S., Mocanu, D. C., Pei, Y., & Pechenizkiy, M. (2021b). Selfish sparse rnn training. In Marina, M., & Tong, Z. (eds), Proceedings of the 38th international conference on machine learning (Vol. 139, pp. 6893\u20136904). https:\/\/proceedings.mlr.press\/v139\/liu21p.html."},{"key":"6266_CR47","unstructured":"Liu, S., Yin, L., Mocanu, D. C., & Pechenizkiy, M. (2021c). Do we actually need dense over-parameterization? in-time over-parameterization in sparse training. In Marina, M., & Tong, Z. (eds), Proceedings of the 38th international conference on machine learning (Vol.139, pp. 6989\u20137000). https:\/\/proceedings.mlr.press\/v139\/liu21y.html."},{"key":"6266_CR48","unstructured":"Louizos, C., Welling, C., & Kingma, D.P. (2018). Learning sparse neural networks through l0 regularization. In International conference on learning representations. https:\/\/openreview.net\/forum?id=H1Y8hhg0b."},{"key":"6266_CR49","doi-asserted-by":"crossref","unstructured":"Luo, C., Zhan, J., Xue, X., Wang, L., Ren, R., & Yang, Q. (2018). Cosine normalization: Using cosine similarity instead of dot product in neural networks. In International conference on artificial neural networks (pp. 382\u2013391). Springer.","DOI":"10.1007\/978-3-030-01418-6_38"},{"key":"6266_CR50","doi-asserted-by":"crossref","unstructured":"Masi, I., Wu, Y., Hassner, T., & Natarajan, P. (2018). Deep face recognition: A survey. In 2018 31st SIBGRAPI conference on graphics, patterns and images (SIBGRAPI) (pp. 471\u2013478). IEEE.","DOI":"10.1109\/SIBGRAPI.2018.00067"},{"issue":"2\u20133","key":"6266_CR51","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/s10994-016-5570-z","volume":"104","author":"DC Mocanu","year":"2016","unstructured":"Mocanu, D. C., Mocanu, E., Nguyen, P. H., Gibescu, M., & Liotta, A. (2016). A topological insight into restricted boltzmann machines. Machine Learning, 104(2\u20133), 243\u2013270.","journal-title":"Machine Learning"},{"issue":"1","key":"6266_CR52","doi-asserted-by":"publisher","first-page":"2383","DOI":"10.1038\/s41467-018-04316-3","volume":"9","author":"DC Mocanu","year":"2018","unstructured":"Mocanu, D. C., Mocanu, E., Stone, P., Nguyen, P. H., Madeleine, G., & Antonio, L. (2018). Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science. Nature Communications, 9(1), 2383.","journal-title":"Nature Communications"},{"key":"6266_CR53","unstructured":"Mocanu, D.\u00a0C., Mocanu, E., Pinto, T., Curci, S., Nguyen, P.H, Gibescu, M., Ernst, D., & Vale, Z.A .(2021). Sparse training theory for scalable and efficient agents. In Proceedings of the 20th international conference on autonomous agents and multiagent systems (pp. 34\u201338)."},{"key":"6266_CR54","unstructured":"Molchanov, Dmitry, A., & Arsenii, V. D. (2017). Variational dropout sparsifies deep neural networks. In International conference on machine learning (pp. 2498\u20132507). PMLR."},{"key":"6266_CR55","unstructured":"Molchanov, P., Tyree, S., Karras, T., Aila, T., & Kautz, J. (2016). Pruning convolutional neural networks for resource efficient inference. arXiv preprint arXiv:1611.06440."},{"key":"6266_CR56","doi-asserted-by":"crossref","unstructured":"Molchanov, P., Mallya, A., Tyree, S., Frosio, I., & Kautz, J. (2019). Importance estimation for neural network pruning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), June.","DOI":"10.1109\/CVPR.2019.01152"},{"key":"6266_CR57","unstructured":"Mostafa, H., & Wang, X. (2019). Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization. In Kamalika, C., & Ruslan, S. (eds), Proceedings of the 36th international conference on machine learning (Vol.\u00a097, pp. 4646\u20134655). http:\/\/proceedings.mlr.press\/v97\/mostafa19a.html."},{"key":"6266_CR58","unstructured":"Neyshabur, B., Li, Z., Bhojanapalli, S., LeCun, Y., & Srebro, N. (2019). The role of over-parametrization in generalization of neural networks. In International conference on learning representations. https:\/\/openreview.net\/forum?id=BygfghAcYX."},{"key":"6266_CR59","doi-asserted-by":"crossref","unstructured":"Nguyen, H.V., & Bai, L. (2010). Cosine similarity metric learning for face verification. In Asian conference on computer vision (pp. 709\u2013720). Springer.","DOI":"10.1007\/978-3-642-19309-5_55"},{"key":"6266_CR60","unstructured":"Pogodin, R., Mehta, Y., Lillicrap, T.P., & Latham, P.E. (2021). Towards biologically plausible convolutional networks. arXiv preprint arXiv:2106.13031."},{"key":"6266_CR61","unstructured":"Popov, S., Morozov, S., & Babenko, A. (2019). Neural oblivious decision ensembles for deep learning on tabular data. arXiv preprint arXiv:1909.06312."},{"key":"6266_CR62","unstructured":"Raihan, M.A., & Aamodt, T.M. (2020) Sparse weight activation training. arXiv preprint arXiv:2001.01969."},{"key":"6266_CR63","unstructured":"Savarese, P., Silva, H., & Maire, M. (2020). Winning the lottery with continuous sparsification. In H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.\u00a0F. Balcan, & H.\u00a0Lin (eds.), Advances in neural information processing systems (Vol. 33, pp. 11380\u201311390). Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/83004190b1793d7aa15f8d0d49a13eba-Paper.pdf."},{"key":"6266_CR64","unstructured":"Scellier, B., & Bengio, Y. (2016). Towards a biologically plausible backprop. arXiv preprint arXiv:1602.05179."},{"key":"6266_CR65","unstructured":"Schumacher, T.(2021). Livewired neural networks: Making neurons that fire together wire together. arXiv preprint arXiv:2105.08111."},{"issue":"3","key":"6266_CR66","doi-asserted-by":"publisher","first-page":"491","DOI":"10.13053\/cys-18-3-2043","volume":"18","author":"G Sidorov","year":"2014","unstructured":"Sidorov, G., Gelbukh, A., G\u00f3mez-Adorno, H., & Pinto, D. (2014). Soft similarity and soft cosine measure: Similarity of features in vector space model. Computaci\u00f3n y Sistemas, 18(3), 491\u2013504.","journal-title":"Computaci\u00f3n y Sistemas"},{"key":"6266_CR67","doi-asserted-by":"crossref","unstructured":"Sun, Y., Wang, X., & Tang, X.(2016). Sparsifying neural network connections for face recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4856\u20134864).","DOI":"10.1109\/CVPR.2016.525"},{"key":"6266_CR68","first-page":"6377","volume":"33","author":"H Tanaka","year":"2020","unstructured":"Tanaka, H., Kunin, D., Yamins, D. L., & Ganguli, S. (2020). Pruning neural networks without any data by iteratively conserving synaptic flow. Advances in Neural Information Processing Systems, 33, 6377\u20136389.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6266_CR69","unstructured":"Tolstikhin, I., Houlsby, N., Kolesnikov, A., Beyer, L., Zhai, X., Unterthiner, T., Yung, J., Keysers, D., Uszkoreit, J., & Lucic, M., et\u00a0al.(2021). Mlp-mixer: An all-mlp architecture for vision. arXiv preprint arXiv:2105.01601."},{"key":"6266_CR70","unstructured":"Wang, C., Grosse, R., Fidler, S., & Zhang, G. (2019a). Eigendamage: Structured pruning in the kronecker-factored eigenbasis. In International conference on machine learning (pp. 6566\u20136575). PMLR."},{"key":"6266_CR71","unstructured":"Wang, C., Zhang, G., & Grosse, R. (2019). Picking winning tickets before training by preserving gradient flow."},{"key":"6266_CR72","unstructured":"Wen, W., Wu, C., Wang, Y., Chen, Y., & Li, H. (2016). Learning structured sparsity in deep neural networks. In Proceedings of the 30th international conference on neural information processing systems, NIPS\u201916 (pp. 2082-2090). Red Hook, NY: Curran Associates Inc."},{"key":"6266_CR73","doi-asserted-by":"crossref","unstructured":"Xia, P., Zhang, L., & Li, F. (2015). Learning similarity with cosine similarity ensemble. Information Sciences, 307:39\u201352. ISSN 0020-0255. https:\/\/doi.org\/10.1016\/j.ins.2015.02.024. URL https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0020025515001243.","DOI":"10.1016\/j.ins.2015.02.024"},{"key":"6266_CR74","unstructured":"Xiao, H., Rasul, K., & Vollgraf, R.(2017). Fashion-mnist: A novel image dataset for benchmarking machine learning algorithms."},{"key":"6266_CR75","doi-asserted-by":"publisher","first-page":"4195","DOI":"10.1109\/ACCESS.2018.2888976","volume":"7","author":"J Yang","year":"2018","unstructured":"Yang, J., Xiao, W., Jiang, C., Hossain, M. S., Muhammad, G., & Amin, S. U. (2018). Ai-powered green cloud and data center. IEEE Access, 7, 4195\u20134203.","journal-title":"IEEE Access"},{"key":"6266_CR76","doi-asserted-by":"crossref","unstructured":"Zhang, M., Zhang, F., Lane, N. D., Shu, Y., Zeng, X., & Fang, B., et al. (2020). Deep learning in the era of edge computing: Challenges and opportunities (p. 2020). Fog Computing: Theory and Practice.","DOI":"10.1002\/9781119551713.ch3"},{"key":"6266_CR77","unstructured":"Zhu, M., & Gupta, S.(2017). To prune, or not to prune: exploring the efficacy of pruning for model compression. arXiv preprint arXiv:1710.01878."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-022-06266-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-022-06266-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-022-06266-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T17:29:36Z","timestamp":1669742976000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-022-06266-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,8]]},"references-count":77,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["6266"],"URL":"https:\/\/doi.org\/10.1007\/s10994-022-06266-w","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,8]]},"assertion":[{"value":"17 October 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 May 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 November 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The implementation code is available on Github at\n                      \n                      .","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}}]}}