{"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/designing-neural-network-architectures-using","title":"Designing Neural Network Architectures using Reinforcement Learning","arxiv_id":"1611.02167","date":"2016-11-07","proceeding":null,"authors":["Bowen Baker","Otkrist Gupta","Nikhil Naik","Ramesh Raskar"],"abstract":"At present, designing convolutional neural network (CNN) architectures\nrequires both human expertise and labor. New architectures are handcrafted by\ncareful experimentation or modified from a handful of existing networks. We\nintroduce MetaQNN, a meta-modeling algorithm based on reinforcement learning to\nautomatically generate high-performing CNN architectures for a given learning\ntask. The learning agent is trained to sequentially choose CNN layers using\n$Q$-learning with an $\\epsilon$-greedy exploration strategy and experience\nreplay. The agent explores a large but finite space of possible architectures\nand iteratively discovers designs with improved performance on the learning\ntask. On image classification benchmarks, the agent-designed networks\n(consisting of only standard convolution, pooling, and fully-connected layers)\nbeat existing networks designed with the same layer types and are competitive\nagainst the state-of-the-art methods that use more complex layer types. We also\noutperform existing meta-modeling approaches for network design on image\nclassification tasks.","url_abs":"http://arxiv.org/abs/1611.02167v3","url_pdf":"http://arxiv.org/pdf/1611.02167v3.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":"designing-neural-network-architectures-using","repo_url":"https://github.com/SAGNIKMJR/MetaQNN_ImageClassification_PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"designing-neural-network-architectures-using","repo_url":"https://github.com/SAGNIKMJR/MetaQNN_ImageGenerationGAN_DiscriminatorFixed_PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"designing-neural-network-architectures-using","repo_url":"https://github.com/SAGNIKMJR/MetaQNN_ImageGenerationVCAE_PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"designing-neural-network-architectures-using","repo_url":"https://github.com/bowenbaker/metaqnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"unanswered"}},{"paper_slug":"designing-neural-network-architectures-using","repo_url":"https://github.com/dylancashman/remap_nas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.02167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.02167"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SAGNIKMJR/MetaQNN_ImageClassification_PyTorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SAGNIKMJR/MetaQNN_ImageGenerationVCAE_PyTorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bowenbaker/metaqnn","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SAGNIKMJR/MetaQNN_ImageGenerationGAN_DiscriminatorFixed_PyTorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dylancashman/remap_nas","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"698817460996c5e9","entry":"get_feat_spatial_size","repo":"SAGNIKMJR/MetaQNN_ImageClassification_PyTorch","repo_kind":"listed","path":"lib/Models/architectures.py","file_url":"https://github.com/SAGNIKMJR/MetaQNN_ImageClassification_PyTorch/blob/HEAD/lib/Models/architectures.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"698817460996c5e9"}},{"code_sha256_prefix":"33b2abb246c229c1","entry":"get_num_flat_features","repo":"SAGNIKMJR/MetaQNN_ImageClassification_PyTorch","repo_kind":"listed","path":"lib/Models/architectures.py","file_url":"https://github.com/SAGNIKMJR/MetaQNN_ImageClassification_PyTorch/blob/HEAD/lib/Models/architectures.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"33b2abb246c229c1"}},{"code_sha256_prefix":"9aaee7a82f9491e0","entry":"image_size_bucket","repo":"SAGNIKMJR/MetaQNN_ImageClassification_PyTorch","repo_kind":"listed","path":"lib/Models/model_state_space_parameters.py","file_url":"https://github.com/SAGNIKMJR/MetaQNN_ImageClassification_PyTorch/blob/HEAD/lib/Models/model_state_space_parameters.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9aaee7a82f9491e0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}