{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T12:16:42Z","timestamp":1767183402961,"version":"3.37.3"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"ESI Group through ESI Chair at ENSAM Arts et Metiers Institute of Technology, and the Project","award":["2019-0060"],"award-info":[{"award-number":["2019-0060"]}]},{"name":"\u201cSimulated Reality\u201d at the University of Zaragoza"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tnnls.2023.3241100","type":"journal-article","created":{"date-parts":[[2023,2,16]],"date-time":"2023-02-16T23:07:25Z","timestamp":1676588845000},"page":"10380-10393","source":"Crossref","is-referenced-by-count":4,"title":["Neural Network Layer Algebra: A Framework to Measure Capacity and Compression in Deep Learning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7639-6767","authenticated-orcid":false,"given":"Alberto","family":"Bad\u00edas","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, University of Washington, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5898-7563","authenticated-orcid":false,"given":"Ashis G.","family":"Banerjee","sequence":"additional","affiliation":[{"name":"Department of Industrial and Systems Engineering and the Department of Mechanical Engineering, University of Washington, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref2","first-page":"341","article-title":"Image denoising and inpainting with deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1145\/1390156.1390177"},{"key":"ref4","article-title":"Generating albums with SampleRNN to imitate metal, rock, and punk bands","author":"Carr","year":"2018","journal-title":"arXiv:1811.06633"},{"volume-title":"Playing Dota 2 World Champions","year":"2019","author":"Five","key":"ref5"},{"year":"2018","author":"Rolnick","article-title":"Towards an integrated understanding of neural networks","key":"ref6"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.3390\/math7100992"},{"key":"ref8","article-title":"Mathematics of deep learning","author":"Vidal","year":"2017","journal-title":"arXiv:1712.04741"},{"key":"ref9","first-page":"7729","article-title":"On neuronal capacity","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baldi"},{"issue":"1","key":"ref10","first-page":"1","article-title":"Computational complexity of neural networks: A survey","volume":"1","author":"Orponen","year":"1994","journal-title":"Nordic J. Comput."},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.5555\/2969033.2969153"},{"key":"ref12","article-title":"On the number of response regions of deep feed forward networks with piece-wise linear activations","author":"Pascanu","year":"2013","journal-title":"arXiv:1312.6098"},{"key":"ref13","article-title":"Sensitivity and generalization in neural networks: An empirical study","author":"Novak","year":"2018","journal-title":"arXiv:1802.08760"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/TNNLS.2020.3028431"},{"key":"ref15","article-title":"Size and depth separation in approximating benign functions with neural networks","author":"Vardi","year":"2021","journal-title":"arXiv:2102.00314"},{"key":"ref16","first-page":"5514","article-title":"On the complexity of learning neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref17","first-page":"698","article-title":"On the expressive power of deep learning: A tensor analysis","volume-title":"Proc. Conf. Learn. Theory","author":"Cohen"},{"key":"ref18","first-page":"2847","article-title":"On the expressive power of deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Raghu"},{"key":"ref19","article-title":"Survey of expressivity in deep neural networks","author":"Raghu","year":"2016","journal-title":"arXiv:1611.08083"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1103\/PhysRevLett.118.010601"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1007\/s40687-018-0172-y"},{"key":"ref22","article-title":"Stochastic training of residual networks: A differential equation viewpoint","author":"Sun","year":"2018","journal-title":"arXiv:1812.00174"},{"key":"ref23","first-page":"1822","article-title":"Architectural complexity measures of recurrent neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref24","first-page":"463","article-title":"Rademacher and Gaussian complexities: Risk bounds and structural results","volume":"3","author":"Bartlett","year":"2002","journal-title":"J. Mach. Learn. Res."},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/TNNLS.2013.2293637"},{"volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rieck","article-title":"Neural persistence: A complexity measure for deep neural networks using algebraic topology","key":"ref26"},{"key":"ref27","article-title":"Approximation and estimation for high-dimensional deep learning networks","author":"Barron","year":"2018","journal-title":"arXiv:1809.03090"},{"key":"ref28","article-title":"Complexity, statistical risk, and metric entropy of deep nets using total path variation","author":"Barron","year":"2019","journal-title":"arXiv:1902.00800"},{"key":"ref29","article-title":"An analysis of deep neural network models for practical applications","author":"Canziani","year":"2016","journal-title":"arXiv:1605.07678"},{"key":"ref30","first-page":"1","article-title":"The power of deeper networks for expressing natural functions","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Rolnick"},{"key":"ref31","first-page":"2343","article-title":"Learning functions: When is deep better than shallow","volume-title":"Proc. 31st AAAI Conf. Artif. Intell.","author":"Mhaskar"},{"key":"ref32","first-page":"1188","article-title":"Vapnik-Chervonenkis dimension of neural nets","volume-title":"The Handbook of Brain Theory and Neural Networks","author":"Bartlett","year":"2003"},{"key":"ref33","first-page":"6231","article-title":"The expressive power of neural networks: A view from the width","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref34","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref35","first-page":"315","article-title":"Deep sparse rectifier neural networks","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Glorot"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/ICCV.2015.123"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.48550\/ARXIV.1710.05941"},{"key":"ref38","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Glorot"},{"key":"ref39","article-title":"On the properties of the softmax function with application in game theory and reinforcement learning","author":"Gao","year":"2017","journal-title":"arXiv:1704.00805"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.5555\/3045118.3045167"},{"key":"ref41","first-page":"2483","article-title":"How does batch normalization help optimization?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Santurkar"},{"issue":"1","key":"ref42","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1109\/CVPR.2016.90"},{"issue":"1","key":"ref44","first-page":"2285","article-title":"Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks","volume":"20","author":"Bartlett","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref45","article-title":"Fantastic generalization measures and where to find them","author":"Jiang","year":"2019","journal-title":"arXiv:1912.02178"},{"doi-asserted-by":"publisher","key":"ref46","DOI":"10.1007\/978-3-319-46493-0_38"},{"year":"2009","author":"Krizhevsky","article-title":"Learning multiple layers of features from tiny images","key":"ref47"},{"key":"ref48","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume-title":"Proc. 12th USENIX Symp. Operating Syst. Design Implement.","author":"Abadi"},{"key":"ref49","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke"},{"doi-asserted-by":"publisher","key":"ref50","DOI":"10.1109\/CVPR.2009.5206848"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10623582\/10045745.pdf?arnumber=10045745","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T08:12:55Z","timestamp":1722931975000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10045745\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":50,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3241100","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}