{"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/practical-block-wise-neural-network","title":"Practical Block-wise Neural Network Architecture Generation","arxiv_id":"1708.05552","date":"2017-08-18","proceeding":"CVPR 2018 6","authors":["Zhao Zhong","Junjie Yan","Wei Wu","Jing Shao","Cheng-Lin Liu"],"abstract":"Convolutional neural networks have gained a remarkable success in computer\nvision. However, most usable network architectures are hand-crafted and usually\nrequire expertise and elaborate design. In this paper, we provide a block-wise\nnetwork generation pipeline called BlockQNN which automatically builds\nhigh-performance networks using the Q-Learning paradigm with epsilon-greedy\nexploration strategy. The optimal network block is constructed by the learning\nagent which is trained sequentially to choose component layers. We stack the\nblock to construct the whole auto-generated network. To accelerate the\ngeneration process, we also propose a distributed asynchronous framework and an\nearly stop strategy. The block-wise generation brings unique advantages: (1) it\nperforms competitive results in comparison to the hand-crafted state-of-the-art\nnetworks on image classification, additionally, the best network generated by\nBlockQNN achieves 3.54% top-1 error rate on CIFAR-10 which beats all existing\nauto-generate networks. (2) in the meanwhile, it offers tremendous reduction of\nthe search space in designing networks which only spends 3 days with 32 GPUs,\nand (3) moreover, it has strong generalizability that the network built on\nCIFAR also performs well on a larger-scale ImageNet dataset.","url_abs":"http://arxiv.org/abs/1708.05552v3","url_pdf":"http://arxiv.org/pdf/1708.05552v3.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":"practical-block-wise-neural-network","repo_url":"https://github.com/elenathFGS/BlockQNN_Keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1708.05552","atlas_url":"https://app.syntology.ai/?focus=1708.05552","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}