{"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/smash-one-shot-model-architecture-search","title":"SMASH: One-Shot Model Architecture Search through HyperNetworks","arxiv_id":"1708.05344","date":"2017-08-17","proceeding":"ICLR 2018 1","authors":["Andrew Brock","Theodore Lim","J. M. Ritchie","Nick Weston"],"abstract":"Designing architectures for deep neural networks requires expert knowledge\nand substantial computation time. We propose a technique to accelerate\narchitecture selection by learning an auxiliary HyperNet that generates the\nweights of a main model conditioned on that model's architecture. By comparing\nthe relative validation performance of networks with HyperNet-generated\nweights, we can effectively search over a wide range of architectures at the\ncost of a single training run. To facilitate this search, we develop a flexible\nmechanism based on memory read-writes that allows us to define a wide range of\nnetwork connectivity patterns, with ResNet, DenseNet, and FractalNet blocks as\nspecial cases. We validate our method (SMASH) on CIFAR-10 and CIFAR-100,\nSTL-10, ModelNet10, and Imagenet32x32, achieving competitive performance with\nsimilarly-sized hand-designed networks. Our code is available at\nhttps://github.com/ajbrock/SMASH","url_abs":"http://arxiv.org/abs/1708.05344v1","url_pdf":"http://arxiv.org/pdf/1708.05344v1.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":"smash-one-shot-model-architecture-search","repo_url":"https://github.com/ajbrock/SMASH","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"model","task_name":"model"}],"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":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-block","method_name":"Dense Block"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"fractal-block","method_name":"Fractal Block"},{"method_slug":"fractalnet","method_name":"FractalNet"},{"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"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.05344","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}