{"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/towards-a-neural-statistician","title":"Towards a Neural Statistician","arxiv_id":"1606.02185","date":"2016-06-07","proceeding":null,"authors":["Harrison Edwards","Amos Storkey"],"abstract":"An efficient learner is one who reuses what they already know to tackle a new\nproblem. For a machine learner, this means understanding the similarities\namongst datasets. In order to do this, one must take seriously the idea of\nworking with datasets, rather than datapoints, as the key objects to model.\nTowards this goal, we demonstrate an extension of a variational autoencoder\nthat can learn a method for computing representations, or statistics, of\ndatasets in an unsupervised fashion. The network is trained to produce\nstatistics that encapsulate a generative model for each dataset. Hence the\nnetwork enables efficient learning from new datasets for both unsupervised and\nsupervised tasks. We show that we are able to learn statistics that can be used\nfor: clustering datasets, transferring generative models to new datasets,\nselecting representative samples of datasets and classifying previously unseen\nclasses. We refer to our model as a neural statistician, and by this we mean a\nneural network that can learn to compute summary statistics of datasets without\nsupervision.","url_abs":"http://arxiv.org/abs/1606.02185v2","url_pdf":"http://arxiv.org/pdf/1606.02185v2.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":"towards-a-neural-statistician","repo_url":"https://github.com/comramona/neural-statistician","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"towards-a-neural-statistician","repo_url":"https://github.com/conormdurkan/neural-statistician","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"towards-a-neural-statistician","repo_url":"https://github.com/cravingoxygen/neuralstat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"towards-a-neural-statistician","repo_url":"https://github.com/htso/Pedestrian_in_few_shots","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"towards-a-neural-statistician","repo_url":"https://github.com/lupalab/flowscan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-1-1","task":"Few-Shot Image Classification","dataset":"OMNIGLOT - 1-Shot, 20-way","model":"Neural Statistician","rank_in_archive_order":16,"of":20,"metrics":{"Accuracy":"93.2%"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-1-2","task":"Few-Shot Image Classification","dataset":"OMNIGLOT - 1-Shot, 5-way","model":"Neural Statistician","rank_in_archive_order":15,"of":17,"metrics":{"Accuracy":"98.1"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-5-1","task":"Few-Shot Image Classification","dataset":"OMNIGLOT - 5-Shot, 20-way","model":"Neural Statistician","rank_in_archive_order":16,"of":19,"metrics":{"Accuracy":"98.1%"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-5-2","task":"Few-Shot Image Classification","dataset":"OMNIGLOT - 5-Shot, 5-way","model":"Neural Statistician","rank_in_archive_order":12,"of":16,"metrics":{"Accuracy":"99.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1606.02185","atlas_url":"https://app.syntology.ai/?focus=1606.02185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.02185"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/comramona/neural-statistician","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/htso/Pedestrian_in_few_shots","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lupalab/flowscan","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/conormdurkan/neural-statistician","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cravingoxygen/neuralstat","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":12},"by_repo_kind":{"listed":{"samples":14,"ran":2,"repositories":2}},"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":"f60cb3cead55f81b","entry":"pca","repo":"cravingoxygen/neuralstat","repo_kind":"listed","path":"tsne.py","file_url":"https://github.com/cravingoxygen/neuralstat/blob/HEAD/tsne.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f60cb3cead55f81b"}},{"code_sha256_prefix":"654e67f1bec03fc8","entry":"x2p","repo":"cravingoxygen/neuralstat","repo_kind":"listed","path":"tsne.py","file_url":"https://github.com/cravingoxygen/neuralstat/blob/HEAD/tsne.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"654e67f1bec03fc8"}},{"code_sha256_prefix":"77fb404ad78a22d9","entry":"Hbeta","repo":"cravingoxygen/neuralstat","repo_kind":"listed","path":"tsne.py","file_url":"https://github.com/cravingoxygen/neuralstat/blob/HEAD/tsne.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":"77fb404ad78a22d9"}},{"code_sha256_prefix":"6913afa4a65fe7f8","entry":"apply_batch_norm","repo":"cravingoxygen/neuralstat","repo_kind":"listed","path":"spatial_mnist.py","file_url":"https://github.com/cravingoxygen/neuralstat/blob/HEAD/spatial_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":"6913afa4a65fe7f8"}},{"code_sha256_prefix":"2e7d466cc00bbeab","entry":"gaussian_log_likelihood","repo":"cravingoxygen/neuralstat","repo_kind":"listed","path":"tests.py","file_url":"https://github.com/cravingoxygen/neuralstat/blob/HEAD/tests.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":"2e7d466cc00bbeab"}},{"code_sha256_prefix":"7e9c25119c6905fb","entry":"generate_samples_like","repo":"cravingoxygen/neuralstat","repo_kind":"listed","path":"spatial_mnist.py","file_url":"https://github.com/cravingoxygen/neuralstat/blob/HEAD/spatial_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":"7e9c25119c6905fb"}},{"code_sha256_prefix":"95f11ad1d1b6f501","entry":"independent_model","repo":"lupalab/flowscan","repo_kind":"listed","path":"model/conditionals.py","file_url":"https://github.com/lupalab/flowscan/blob/HEAD/model/conditionals.py","link_basis":"first_harvest_node","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":"95f11ad1d1b6f501"}},{"code_sha256_prefix":"5c72e16208cff35c","entry":"load_images","repo":"cravingoxygen/neuralstat","repo_kind":"listed","path":"spatialcreate.py","file_url":"https://github.com/cravingoxygen/neuralstat/blob/HEAD/spatialcreate.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":"5c72e16208cff35c"}},{"code_sha256_prefix":"b1af56804ab57958","entry":"load_labels","repo":"cravingoxygen/neuralstat","repo_kind":"listed","path":"spatialcreate.py","file_url":"https://github.com/cravingoxygen/neuralstat/blob/HEAD/spatialcreate.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":"b1af56804ab57958"}},{"code_sha256_prefix":"b2874edcc99ce4e6","entry":"main","repo":"lupalab/flowscan","repo_kind":"listed","path":"demos/flowscan_demo.py","file_url":"https://github.com/lupalab/flowscan/blob/HEAD/demos/flowscan_demo.py","link_basis":"first_harvest_node","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":"b2874edcc99ce4e6"}},{"code_sha256_prefix":"6625ee33e78ed05d","entry":"make_in_out","repo":"lupalab/flowscan","repo_kind":"listed","path":"model/conditionals.py","file_url":"https://github.com/lupalab/flowscan/blob/HEAD/model/conditionals.py","link_basis":"first_harvest_node","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":"6625ee33e78ed05d"}},{"code_sha256_prefix":"d96984eb51ffcaa1","entry":"mixture_of_mixtures","repo":"lupalab/flowscan","repo_kind":"listed","path":"model/likelihoods.py","file_url":"https://github.com/lupalab/flowscan/blob/HEAD/model/likelihoods.py","link_basis":"first_harvest_node","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":"d96984eb51ffcaa1"}},{"code_sha256_prefix":"9c2927a6cb5b2667","entry":"new_mixture_of_mixtures","repo":"lupalab/flowscan","repo_kind":"listed","path":"model/likelihoods.py","file_url":"https://github.com/lupalab/flowscan/blob/HEAD/model/likelihoods.py","link_basis":"first_harvest_node","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":"9c2927a6cb5b2667"}},{"code_sha256_prefix":"dffe6cbc0b246e38","entry":"sample_mm","repo":"lupalab/flowscan","repo_kind":"listed","path":"model/conditionals.py","file_url":"https://github.com/lupalab/flowscan/blob/HEAD/model/conditionals.py","link_basis":"first_harvest_node","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":"dffe6cbc0b246e38"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}