{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:17:28Z","timestamp":1780636648425,"version":"3.54.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"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":[[2020,7]]},"DOI":"10.1109\/ijcnn48605.2020.9206727","type":"proceedings-article","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T00:40:33Z","timestamp":1601426433000},"page":"1-8","source":"Crossref","is-referenced-by-count":10,"title":["Loss Surface Modality of Feed-Forward Neural Network Architectures"],"prefix":"10.1109","author":[{"given":"Anna Sergeevna","family":"Bosman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andries","family":"Petrus Engelbrecht","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marde","family":"Helbig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"keskar","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref31","article-title":"Multi-layer perceptron error surfaces: Visualization, structure and modelling","author":"gallagher","year":"2000","journal-title":"Ph D dissertation University of Queensland St Lucia 4072 Australia"},{"key":"ref30","first-page":"1","article-title":"Entropy-SGD: Biasing gradient descent into wide valleys","author":"chaudhari","year":"2017","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"ref10","article-title":"Depth Creates No Bad Local Minima","author":"lu","year":"2017"},{"key":"ref11","article-title":"Deep, skinny neural networks are not universal approximators","author":"johnson","year":"0"},{"key":"ref12","first-page":"1","article-title":"Neural architecture search: A survey","volume":"20","author":"elsken","year":"2019","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","first-page":"1756","article-title":"Open problem: The landscape of the loss surfaces of multilayer networks","author":"choromanska","year":"2015","journal-title":"Proc 28th Conf Learn Theory"},{"key":"ref14","first-page":"611","article-title":"A survey of factors influencing MLP error surface","volume":"33","author":"kordos","year":"2004","journal-title":"Control and Cybernetics"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00091"},{"key":"ref16","article-title":"Visualising Basins of Attraction for the Cross-Entropy and the Squared Error Neural Network Loss Functions","author":"bosman","year":"2019"},{"key":"ref17","article-title":"Evolutionary algorithms, fitness landscapes and search","author":"jones","year":"1995","journal-title":"Ph D Dissertation New Mexico State University"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/4235.887234"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2009.4983112"},{"key":"ref28","first-page":"1","article-title":"Fast and accurate deep network learning by exponential linear units (ELUs)","author":"clevert","year":"2016","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"ref4","first-page":"442","article-title":"How neural nets work","author":"lapedes","year":"1988","journal-title":"Advances in neural information processing systems"},{"key":"ref27","author":"lecun","year":"2010","journal-title":"MNIST Handwritten Digit Database"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2006.875977"},{"key":"ref6","first-page":"402","article-title":"Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping","author":"caruana","year":"2001","journal-title":"Advances in neural information processing systems"},{"key":"ref29","first-page":"1","article-title":"Empirical analysis of the hessian of over-parametrized neural networks","author":"sagun","year":"2018","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MIE.2009.934790"},{"key":"ref8","first-page":"1","article-title":"Explorations on high dimensional landscapes","author":"sagun","year":"2015","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"ref7","article-title":"The loss surface of deep and wide neural networks","author":"nguyen","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2003.809401"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1039\/C7CP01108C"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2006.06.005"},{"key":"ref20","article-title":"Characterising continuous optimisation problems for particle swarm optimisation performance prediction","author":"malan","year":"2014","journal-title":"Ph D dissertation University of Pretoria"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICIAFS.2014.7069635"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1016\/j.ins.2015.05.010","article-title":"Algorithm selection for black-box continuous optimization problems: A survey on methods and challenges","volume":"317","author":"mu\u00f1oz","year":"2015","journal-title":"Information Sciences"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2014.6900576"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3205651.3208247"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.97.052307"},{"key":"ref25","author":"edwards","year":"1973","journal-title":"Advanced Calculus of Several Variables"}],"event":{"name":"2020 International Joint Conference on Neural Networks (IJCNN)","location":"Glasgow, United Kingdom","start":{"date-parts":[[2020,7,19]]},"end":{"date-parts":[[2020,7,24]]}},"container-title":["2020 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9200848\/9206590\/09206727.pdf?arnumber=9206727","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:53:46Z","timestamp":1656453226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9206727\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/ijcnn48605.2020.9206727","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}