{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OUKF7QOMWLL6CZ3ZFTDL36ZWCA","short_pith_number":"pith:OUKF7QOM","schema_version":"1.0","canonical_sha256":"75145fc1ccb2d7e167792cc6bdfb36100887c0a1409b7aabaf57dcf82c7d5fc3","source":{"kind":"arxiv","id":"1909.12228","version":4},"attestation_state":"computed","paper":{"title":"Locally adaptive activation functions with slope recovery term for deep and physics-informed neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ameya D. Jagtap, George Em Karniadakis, Kenji Kawaguchi","submitted_at":"2019-09-25T16:36:21Z","abstract_excerpt":"We propose two approaches of locally adaptive activation functions namely, layer-wise and neuron-wise locally adaptive activation functions, which improve the performance of deep and physics-informed neural networks. The local adaptation of activation function is achieved by introducing a scalable parameter in each layer (layer-wise) and for every neuron (neuron-wise) separately, and then optimizing it using a variant of stochastic gradient descent algorithm. In order to further increase the training speed, an activation slope based slope recovery term is added in the loss function, which furt"},"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":"1909.12228","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T16:36:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c55f067fe89acd48c9d75c840ff1367eb1adb76622e69338df943089ec7900ab","abstract_canon_sha256":"5890e2c06d41699d42ff9ff67f7fa5c822b6db2fb764e22d487336e2bac393e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:35:11.183305Z","signature_b64":"UUKIG3t2ePTjoNR0PgH+vBYyzpkl/HLwfH/JluGyLcTsZaW7E9/Co60JDa+91G/bOws10zMzoT92DphpCGfuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75145fc1ccb2d7e167792cc6bdfb36100887c0a1409b7aabaf57dcf82c7d5fc3","last_reissued_at":"2026-07-05T02:35:11.182837Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:35:11.182837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Locally adaptive activation functions with slope recovery term for deep and physics-informed neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ameya D. Jagtap, George Em Karniadakis, Kenji Kawaguchi","submitted_at":"2019-09-25T16:36:21Z","abstract_excerpt":"We propose two approaches of locally adaptive activation functions namely, layer-wise and neuron-wise locally adaptive activation functions, which improve the performance of deep and physics-informed neural networks. The local adaptation of activation function is achieved by introducing a scalable parameter in each layer (layer-wise) and for every neuron (neuron-wise) separately, and then optimizing it using a variant of stochastic gradient descent algorithm. In order to further increase the training speed, an activation slope based slope recovery term is added in the loss function, which furt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.12228","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.12228/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1909.12228","created_at":"2026-07-05T02:35:11.182895+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.12228v4","created_at":"2026-07-05T02:35:11.182895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.12228","created_at":"2026-07-05T02:35:11.182895+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUKF7QOMWLL6","created_at":"2026-07-05T02:35:11.182895+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUKF7QOMWLL6CZ3Z","created_at":"2026-07-05T02:35:11.182895+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUKF7QOM","created_at":"2026-07-05T02:35:11.182895+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/OUKF7QOMWLL6CZ3ZFTDL36ZWCA","json":"https://pith.science/pith/OUKF7QOMWLL6CZ3ZFTDL36ZWCA.json","graph_json":"https://pith.science/api/pith-number/OUKF7QOMWLL6CZ3ZFTDL36ZWCA/graph.json","events_json":"https://pith.science/api/pith-number/OUKF7QOMWLL6CZ3ZFTDL36ZWCA/events.json","paper":"https://pith.science/paper/OUKF7QOM"},"agent_actions":{"view_html":"https://pith.science/pith/OUKF7QOMWLL6CZ3ZFTDL36ZWCA","download_json":"https://pith.science/pith/OUKF7QOMWLL6CZ3ZFTDL36ZWCA.json","view_paper":"https://pith.science/paper/OUKF7QOM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.12228&json=true","fetch_graph":"https://pith.science/api/pith-number/OUKF7QOMWLL6CZ3ZFTDL36ZWCA/graph.json","fetch_events":"https://pith.science/api/pith-number/OUKF7QOMWLL6CZ3ZFTDL36ZWCA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUKF7QOMWLL6CZ3ZFTDL36ZWCA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUKF7QOMWLL6CZ3ZFTDL36ZWCA/action/storage_attestation","attest_author":"https://pith.science/pith/OUKF7QOMWLL6CZ3ZFTDL36ZWCA/action/author_attestation","sign_citation":"https://pith.science/pith/OUKF7QOMWLL6CZ3ZFTDL36ZWCA/action/citation_signature","submit_replication":"https://pith.science/pith/OUKF7QOMWLL6CZ3ZFTDL36ZWCA/action/replication_record"}},"created_at":"2026-07-05T02:35:11.182895+00:00","updated_at":"2026-07-05T02:35:11.182895+00:00"}