{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:6IT34CNWDA4I2F7LICHSHMMMQ6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"12afe81e9c734f0ec4c544bcc0b35a2396010bca63cb1c0c4dd0c392cdb587e1","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-15T20:21:54Z","title_canon_sha256":"a892b6e71b5a613a81ca0313731829361ef241acb2d3e22d018678ae0fb70e86"},"schema_version":"1.0","source":{"id":"1301.3476","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.3476","created_at":"2026-05-18T03:31:20Z"},{"alias_kind":"arxiv_version","alias_value":"1301.3476v3","created_at":"2026-05-18T03:31:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.3476","created_at":"2026-05-18T03:31:20Z"},{"alias_kind":"pith_short_12","alias_value":"6IT34CNWDA4I","created_at":"2026-05-18T12:27:36Z"},{"alias_kind":"pith_short_16","alias_value":"6IT34CNWDA4I2F7L","created_at":"2026-05-18T12:27:36Z"},{"alias_kind":"pith_short_8","alias_value":"6IT34CNW","created_at":"2026-05-18T12:27:36Z"}],"graph_snapshots":[{"event_id":"sha256:b5ac2f8e244f6082dbfe89e01fe64e943ad17d3e2b911e2729f66c20ff6df753","target":"graph","created_at":"2026-05-18T03:31:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Recently, we proposed to transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model the linear dependencies instead. We continue the work by firstly introducing a third transformation to normalize the scale of the outputs of each hidden neuron, and secondly by analyzing the connections to second order optimization methods. We show that the transformations make a simple stochastic gradient behave closer to second-order optimization methods and thus speed up learning. This is shown ","authors_text":"Harri Valpola, Tapani Raiko, Tommi Vatanen, Yann LeCun","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-15T20:21:54Z","title":"Pushing Stochastic Gradient towards Second-Order Methods -- Backpropagation Learning with Transformations in Nonlinearities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.3476","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5e80ce566882f84155b1c6470a1d6cbe8296be8916ab676e1a79efd191b1400f","target":"record","created_at":"2026-05-18T03:31:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"12afe81e9c734f0ec4c544bcc0b35a2396010bca63cb1c0c4dd0c392cdb587e1","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-15T20:21:54Z","title_canon_sha256":"a892b6e71b5a613a81ca0313731829361ef241acb2d3e22d018678ae0fb70e86"},"schema_version":"1.0","source":{"id":"1301.3476","kind":"arxiv","version":3}},"canonical_sha256":"f227be09b618388d17eb408f23b18c87a8da49b3582a4a6ce0108a85e8304ba2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f227be09b618388d17eb408f23b18c87a8da49b3582a4a6ce0108a85e8304ba2","first_computed_at":"2026-05-18T03:31:20.417086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:31:20.417086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vOgkhhZ+/JdOfBizBNDmRZcogCUhCnaWJNBIGQelfXDJfdbPCFaHnvDfGcq6OGz5RC755sbck2XTcArL+3QUAA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:31:20.417877Z","signed_message":"canonical_sha256_bytes"},"source_id":"1301.3476","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e80ce566882f84155b1c6470a1d6cbe8296be8916ab676e1a79efd191b1400f","sha256:b5ac2f8e244f6082dbfe89e01fe64e943ad17d3e2b911e2729f66c20ff6df753"],"state_sha256":"1e7415bcb348d9cd3c974a17bfbf0a3bdfbe119b88312478c1e968557c0f6ae6"}