{"paper":{"title":"FiTS: Interpretable Spiking Neurons via Frequency Selectivity and Temporal Shaping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Spiking neurons improve in simple feedforward networks when each one separately selects a target frequency and then adjusts its timing contribution through group delay.","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Jongmin Choi, Joon Son Chung","submitted_at":"2026-05-13T06:42:40Z","abstract_excerpt":"Spiking Neural Networks (SNNs) are a promising framework for event-driven temporal processing. Prior work has improved temporal modeling through richer neuron dynamics and network-level mechanisms such as recurrence and delays, but it remains unclear how individual spiking neurons should specialize within a network. In this work, we introduce FiTS, a spiking neuron that factorizes temporal computation within each neuron into Frequency Selectivity (FS) and Temporal Shaping (TS). The FS module parameterizes each neuron's target frequency as the maximizer of its subthreshold magnitude response, w"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"FiTS consistently improves over a plain Leaky Integrate-and-Fire (LIF) baseline in simple feedforward SNNs without recurrence or network-level delays, while remaining competitive with strong temporal SNN baselines. The learned target frequencies and group-delay shifts provide interpretable neuron-level summaries.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That factorizing temporal computation into an FS module (target frequency as maximizer of subthreshold magnitude response) and a TS module (group-delay modulation) will produce effective specialization and performance gains without requiring additional network mechanisms or post-hoc tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FiTS spiking neurons improve auditory task performance over LIF baselines by factorizing computation into frequency selectivity and group-delay-based temporal shaping, yielding interpretable per-neuron parameters.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Spiking neurons improve in simple feedforward networks when each one separately selects a target frequency and then adjusts its timing contribution through group delay.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ac05f027cf1bb69d8a67dcca44fb68e1a266a3c851421d609a1e836d3f5eb08c"},"source":{"id":"2605.13071","kind":"arxiv","version":1},"verdict":{"id":"daeecd00-1fb0-44c8-a7bd-f6f6c14d8045","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T02:15:47.500392Z","strongest_claim":"FiTS consistently improves over a plain Leaky Integrate-and-Fire (LIF) baseline in simple feedforward SNNs without recurrence or network-level delays, while remaining competitive with strong temporal SNN baselines. The learned target frequencies and group-delay shifts provide interpretable neuron-level summaries.","one_line_summary":"FiTS spiking neurons improve auditory task performance over LIF baselines by factorizing computation into frequency selectivity and group-delay-based temporal shaping, yielding interpretable per-neuron parameters.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That factorizing temporal computation into an FS module (target frequency as maximizer of subthreshold magnitude response) and a TS module (group-delay modulation) will produce effective specialization and performance gains without requiring additional network mechanisms or post-hoc tuning.","pith_extraction_headline":"Spiking neurons improve in simple feedforward networks when each one separately selects a target frequency and then adjusts its timing contribution through group delay."},"references":{"count":45,"sample":[{"doi":"","year":2017,"title":"A low power, fully event-based gesture recognition system","work_id":"cf2f8cfd-0168-4e5c-be7c-0b492c1158fd","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Advancing spatio-temporal processing in spiking neural networks through adaptation","work_id":"7bfd64b6-76c2-42c0-bc07-504a05178e38","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Long short-term memory and learning-to-learn in networks of spiking neurons","work_id":"3d75ca94-24ac-4c0a-ba2e-4cdb0c17d5df","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Alexandre Bittar and Philip N. Garner. A surrogate gradient spiking baseline for speech command recognition.Frontiers in Neuroscience, V olume 16 - 2022, 2022","work_id":"48cd0baf-8a0c-4a04-be5a-53b9275aecff","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"PMSN: A parallel multi-compartment spiking neuron for multi-scale temporal processing","work_id":"a7c313df-ca92-46c0-9be9-17aaf8b14769","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":45,"snapshot_sha256":"5ccb6317c79cb36f60408f14ce3c7fb1d9fe6abcaea692cdc04381dcafffea0b","internal_anchors":1},"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"}