{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-timememory-efficient-deep","title":"Learning Time/Memory-Efficient Deep Architectures with Budgeted Super Networks","arxiv_id":"1706.00046","date":"2017-05-31","proceeding":"CVPR 2018 6","authors":["Tom Veniat","Ludovic Denoyer"],"abstract":"We propose to focus on the problem of discovering neural network\narchitectures efficient in terms of both prediction quality and cost. For\ninstance, our approach is able to solve the following tasks: learn a neural\nnetwork able to predict well in less than 100 milliseconds or learn an\nefficient model that fits in a 50 Mb memory. Our contribution is a novel family\nof models called Budgeted Super Networks (BSN). They are learned using gradient\ndescent techniques applied on a budgeted learning objective function which\nintegrates a maximum authorized cost, while making no assumption on the nature\nof this cost. We present a set of experiments on computer vision problems and\nanalyze the ability of our technique to deal with three different costs: the\ncomputation cost, the memory consumption cost and a distributed computation\ncost. We particularly show that our model can discover neural network\narchitectures that have a better accuracy than the ResNet and Convolutional\nNeural Fabrics architectures on CIFAR-10 and CIFAR-100, at a lower cost.","url_abs":"http://arxiv.org/abs/1706.00046v4","url_pdf":"http://arxiv.org/pdf/1706.00046v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-timememory-efficient-deep","repo_url":"https://github.com/TomVeniat/bsn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.00046","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}