{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VRL5X4CJ5ULM6B4BW2TP5KSWZE","short_pith_number":"pith:VRL5X4CJ","schema_version":"1.0","canonical_sha256":"ac57dbf049ed16cf0781b6a6feaa56c93131f17e98c9956d51b16033efef7c35","source":{"kind":"arxiv","id":"1810.09184","version":1},"attestation_state":"computed","paper":{"title":"Learning sparse transformations through backpropagation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Peter Bloem","submitted_at":"2018-10-22T11:34:32Z","abstract_excerpt":"Many transformations in deep learning architectures are sparsely connected. When such transformations cannot be designed by hand, they can be learned, even through plain backpropagation, for instance in attention mechanisms. However, during learning, such sparse structures are often represented in a dense form, as we do not know beforehand which elements will eventually become non-zero. We introduce the adaptive, sparse hyperlayer, a method for learning a sparse transformation, paramatrized sparsely: as index-tuples with associated values. To overcome the lack of gradients from such a discrete"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1810.09184","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2018-10-22T11:34:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d86d793af925f6dee094a9895cab666c8fed0bd03e4ed57266779f7986e12028","abstract_canon_sha256":"4245ffda447cac49c6856a49f0a685677ec7c2ae689145a0c2f640ad34efaa75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:40.843018Z","signature_b64":"uEp0ywzXdOe6WKuroag3LOAjG+Zae6GWcPvUrXJU//y9kzQeand+Z5r8PoUMf8o5MGz6wT5znZtATFmVzvrkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac57dbf049ed16cf0781b6a6feaa56c93131f17e98c9956d51b16033efef7c35","last_reissued_at":"2026-05-18T00:02:40.842528Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:40.842528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning sparse transformations through backpropagation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Peter Bloem","submitted_at":"2018-10-22T11:34:32Z","abstract_excerpt":"Many transformations in deep learning architectures are sparsely connected. When such transformations cannot be designed by hand, they can be learned, even through plain backpropagation, for instance in attention mechanisms. However, during learning, such sparse structures are often represented in a dense form, as we do not know beforehand which elements will eventually become non-zero. We introduce the adaptive, sparse hyperlayer, a method for learning a sparse transformation, paramatrized sparsely: as index-tuples with associated values. To overcome the lack of gradients from such a discrete"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.09184","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1810.09184","created_at":"2026-05-18T00:02:40.842617+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.09184v1","created_at":"2026-05-18T00:02:40.842617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.09184","created_at":"2026-05-18T00:02:40.842617+00:00"},{"alias_kind":"pith_short_12","alias_value":"VRL5X4CJ5ULM","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VRL5X4CJ5ULM6B4B","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VRL5X4CJ","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VRL5X4CJ5ULM6B4BW2TP5KSWZE","json":"https://pith.science/pith/VRL5X4CJ5ULM6B4BW2TP5KSWZE.json","graph_json":"https://pith.science/api/pith-number/VRL5X4CJ5ULM6B4BW2TP5KSWZE/graph.json","events_json":"https://pith.science/api/pith-number/VRL5X4CJ5ULM6B4BW2TP5KSWZE/events.json","paper":"https://pith.science/paper/VRL5X4CJ"},"agent_actions":{"view_html":"https://pith.science/pith/VRL5X4CJ5ULM6B4BW2TP5KSWZE","download_json":"https://pith.science/pith/VRL5X4CJ5ULM6B4BW2TP5KSWZE.json","view_paper":"https://pith.science/paper/VRL5X4CJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.09184&json=true","fetch_graph":"https://pith.science/api/pith-number/VRL5X4CJ5ULM6B4BW2TP5KSWZE/graph.json","fetch_events":"https://pith.science/api/pith-number/VRL5X4CJ5ULM6B4BW2TP5KSWZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VRL5X4CJ5ULM6B4BW2TP5KSWZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VRL5X4CJ5ULM6B4BW2TP5KSWZE/action/storage_attestation","attest_author":"https://pith.science/pith/VRL5X4CJ5ULM6B4BW2TP5KSWZE/action/author_attestation","sign_citation":"https://pith.science/pith/VRL5X4CJ5ULM6B4BW2TP5KSWZE/action/citation_signature","submit_replication":"https://pith.science/pith/VRL5X4CJ5ULM6B4BW2TP5KSWZE/action/replication_record"}},"created_at":"2026-05-18T00:02:40.842617+00:00","updated_at":"2026-05-18T00:02:40.842617+00:00"}