{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T08:25:11Z","timestamp":1775809511480,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9534060","type":"proceedings-article","created":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T20:32:37Z","timestamp":1632342757000},"page":"1-8","source":"Crossref","is-referenced-by-count":11,"title":["It's Hard for Neural Networks to Learn the Game of Life"],"prefix":"10.1109","author":[{"given":"Jacob M.","family":"Springer","sequence":"first","affiliation":[]},{"given":"Garrett T.","family":"Kenyon","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref32","author":"abadi","year":"2015","journal-title":"TensorFlow Large-Scale Machine Learning on Heterogeneous Systems"},{"key":"ref31","author":"chollet","year":"2015","journal-title":"Keras"},{"key":"ref30","author":"zhou","year":"2020","journal-title":"Deconstructing Lottery Tickets Zeros Signs and the Supermask"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5120\/8142-1867"},{"key":"ref11","article-title":"Neural gpus learn algorithms","author":"kaiser","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref12","article-title":"Neural turing machines","author":"graves","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref13","first-page":"190","article-title":"Inferring algorithmic patterns with stack-augmented recurrent nets","author":"joulin","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"8035","article-title":"Neural arithmetic logic units","author":"trask","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.100.032402"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2991332"},{"key":"ref17","article-title":"Gradient descent finds global minima of deep neural networks","author":"du","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref18","article-title":"Elimination of all bad local minima in deep learning","author":"kawaguchi","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref19","first-page":"2603","article-title":"The loss surface of deep and wide neural networks","volume":"70","author":"nguyen","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref28","first-page":"12645","article-title":"MetaInit: Initializing learning by learning to initialize","author":"dauphin","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref27","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"0","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref3","first-page":"164","article-title":"Second order derivatives for network pruning: Optimal brain surgeon","author":"hassibi","year":"1993","journal-title":"Advances in neural information processing systems"},{"key":"ref6","article-title":"Pruning filters for efficient convnets","author":"li","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref29","author":"mishkin","year":"2016","journal-title":"All you need is a good init"},{"key":"ref5","first-page":"598","article-title":"Optimal brain damage","author":"lecun","year":"1990","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-004-0413-4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.7763\/IJESD.2010.V1.63"},{"key":"ref2","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref9","article-title":"A deep learning based approach to reduced order modeling for turbulent flow control using lstm neural networks","author":"mohan","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref1","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","author":"frankle","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref20","first-page":"586","article-title":"Deep learning without poor local minima","author":"kawaguchi","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref22","author":"arora","year":"2018","journal-title":"On the optimization of deep networks Implicit acceleration by overparameterization"},{"key":"ref21","article-title":"Are efficient deep representations learnable?","author":"nye","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref24","author":"li","year":"2018","journal-title":"Measuring the intrinsic dimension of objective landscapes"},{"key":"ref23","author":"park","year":"2019","journal-title":"The effect of network width on stochastic gradient descent and generalization an empirical study"},{"key":"ref26","first-page":"192","article-title":"The loss surfaces of multilayer networks","author":"choromanska","year":"2015","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref25","author":"neyshabur","year":"2018","journal-title":"Towards understanding the role of over-parametrization in generalization of neural networks"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","location":"Shenzhen, China","start":{"date-parts":[[2021,7,18]]},"end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09534060.pdf?arnumber=9534060","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:46:14Z","timestamp":1652197574000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9534060\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9534060","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}