{"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/neural-processes","title":"Neural Processes","arxiv_id":"1807.01622","date":"2018-07-04","proceeding":null,"authors":["Marta Garnelo","Jonathan Schwarz","Dan Rosenbaum","Fabio Viola","Danilo J. Rezende","S. M. Ali Eslami","Yee Whye Teh"],"abstract":"A neural network (NN) is a parameterised function that can be tuned via\ngradient descent to approximate a labelled collection of data with high\nprecision. A Gaussian process (GP), on the other hand, is a probabilistic model\nthat defines a distribution over possible functions, and is updated in light of\ndata via the rules of probabilistic inference. GPs are probabilistic,\ndata-efficient and flexible, however they are also computationally intensive\nand thus limited in their applicability. We introduce a class of neural latent\nvariable models which we call Neural Processes (NPs), combining the best of\nboth worlds. Like GPs, NPs define distributions over functions, are capable of\nrapid adaptation to new observations, and can estimate the uncertainty in their\npredictions. Like NNs, NPs are computationally efficient during training and\nevaluation but also learn to adapt their priors to data. We demonstrate the\nperformance of NPs on a range of learning tasks, including regression and\noptimisation, and compare and contrast with related models in the literature.","url_abs":"http://arxiv.org/abs/1807.01622v1","url_pdf":"http://arxiv.org/pdf/1807.01622v1.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":"neural-processes","repo_url":"https://github.com/deepmind/neural-processes","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"neural-processes","repo_url":"https://github.com/3springs/np_vs_kriging","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"neural-processes","repo_url":"https://github.com/ALRhub/HiP-RSSM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neural-processes","repo_url":"https://github.com/Arnaud15/CS236_Neural_Processes_For_Image_Completion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neural-processes","repo_url":"https://github.com/E-DEEP/PapersReview","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"neural-processes","repo_url":"https://github.com/EmilienDupont/neural-processes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"neural-processes","repo_url":"https://github.com/JEM-Mosig/blog-garnelo_neural_2018","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"neural-processes","repo_url":"https://github.com/Usefulmaths/Neural-Processes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"neural-processes","repo_url":"https://github.com/deepmind/conditional-neural-process","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"neural-processes","repo_url":"https://github.com/google-deepmind/neural-processes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"neural-processes","repo_url":"https://github.com/jusonn/Neural-Process","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"neural-processes","repo_url":"https://github.com/revsic/tf-neural-process","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"neural-processes","repo_url":"https://github.com/wesselb/NeuralProcesses.jl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"neural-processes","repo_url":"https://github.com/yamad07/NeuralProcess","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"gaussian-process","method_name":"Gaussian Process"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.01622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.01622"}},"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/wesselb/NeuralProcesses.jl","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/E-DEEP/PapersReview","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/revsic/tf-neural-process","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yamad07/NeuralProcess","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Usefulmaths/Neural-Processes","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/3springs/np_vs_kriging","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deepmind/neural-processes","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jusonn/Neural-Process","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-deepmind/neural-processes","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Arnaud15/CS236_Neural_Processes_For_Image_Completion","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JEM-Mosig/blog-garnelo_neural_2018","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deepmind/conditional-neural-process","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/EmilienDupont/neural-processes","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ALRhub/HiP-RSSM","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":11},"by_repo_kind":{"listed":{"samples":12,"ran":1,"repositories":3}},"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":"dba028b9ac289b46","entry":"all_forward","repo":"Arnaud15/CS236_Neural_Processes_For_Image_Completion","repo_kind":"listed","path":"NP.py","file_url":"https://github.com/Arnaud15/CS236_Neural_Processes_For_Image_Completion/blob/HEAD/NP.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dba028b9ac289b46"}},{"code_sha256_prefix":"4244bd096a5b4d3e","entry":"KLD_gaussian","repo":"jusonn/Neural-Process","repo_kind":"listed","path":"np_regression.py","file_url":"https://github.com/jusonn/Neural-Process/blob/HEAD/np_regression.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":"4244bd096a5b4d3e"}},{"code_sha256_prefix":"c64f8a677007682e","entry":"celeba","repo":"EmilienDupont/neural-processes","repo_kind":"listed","path":"datasets.py","file_url":"https://github.com/EmilienDupont/neural-processes/blob/HEAD/datasets.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":"c64f8a677007682e"}},{"code_sha256_prefix":"5fd036a6c28983fe","entry":"context_target_split","repo":"EmilienDupont/neural-processes","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/EmilienDupont/neural-processes/blob/HEAD/utils.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":"5fd036a6c28983fe"}},{"code_sha256_prefix":"d51da53a48566f61","entry":"generate_grid","repo":"jusonn/Neural-Process","repo_kind":"listed","path":"np_mnist.py","file_url":"https://github.com/jusonn/Neural-Process/blob/HEAD/np_mnist.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":"d51da53a48566f61"}},{"code_sha256_prefix":"bc1e90169bd42ed3","entry":"get_context_idx","repo":"jusonn/Neural-Process","repo_kind":"listed","path":"np_mnist.py","file_url":"https://github.com/jusonn/Neural-Process/blob/HEAD/np_mnist.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":"bc1e90169bd42ed3"}},{"code_sha256_prefix":"ff65d8af5d3b97d1","entry":"idx_to_y","repo":"jusonn/Neural-Process","repo_kind":"listed","path":"np_mnist.py","file_url":"https://github.com/jusonn/Neural-Process/blob/HEAD/np_mnist.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":"ff65d8af5d3b97d1"}},{"code_sha256_prefix":"895f72cd45ff0f13","entry":"img_mask_to_np_input","repo":"EmilienDupont/neural-processes","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/EmilienDupont/neural-processes/blob/HEAD/utils.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":"895f72cd45ff0f13"}},{"code_sha256_prefix":"aa12408acd63ec57","entry":"log_likelihood","repo":"jusonn/Neural-Process","repo_kind":"listed","path":"np_regression.py","file_url":"https://github.com/jusonn/Neural-Process/blob/HEAD/np_regression.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":"aa12408acd63ec57"}},{"code_sha256_prefix":"6e22049190dc8b13","entry":"mnist","repo":"EmilienDupont/neural-processes","repo_kind":"listed","path":"datasets.py","file_url":"https://github.com/EmilienDupont/neural-processes/blob/HEAD/datasets.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":"6e22049190dc8b13"}},{"code_sha256_prefix":"e912b4a390c2e8fc","entry":"random_context_target_mask","repo":"EmilienDupont/neural-processes","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/EmilienDupont/neural-processes/blob/HEAD/utils.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":"e912b4a390c2e8fc"}},{"code_sha256_prefix":"78e067a8184547c2","entry":"random_split_c_t","repo":"jusonn/Neural-Process","repo_kind":"listed","path":"np_regression.py","file_url":"https://github.com/jusonn/Neural-Process/blob/HEAD/np_regression.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":"78e067a8184547c2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}