Papers › DeepSITH: Efficient Learning via Decomposition of What and When Across Time Scales

DeepSITH: Efficient Learning via Decomposition of What and When Across Time Scales

9 Apr 2021NeurIPS 2021 12arXiv:2104.04646archive 2025-07-28

Brandon Jacques, Zoran Tiganj, Marc W. Howard, Per B. Sederberg

Extracting temporal relationships over a range of scales is a hallmark of human perception and cognition -- and thus it is a critical feature of machine learning applied to real-world problems. Neural networks are either plagued by the exploding/vanishing gradient problem in recurrent neural networks (RNNs) or must adjust their parameters to learn the relevant time scales (e.g., in LSTMs). This paper introduces DeepSITH, a network comprising biologically-inspired Scale-Invariant Temporal History (SITH) modules in series with dense connections between layers. SITH modules respond to their inputs with a geometrically-spaced set of time constants, enabling the DeepSITH network to learn problems along a continuum of time-scales. We compare DeepSITH to LSTMs and other recent RNNs on several time series prediction and decoding tasks. DeepSITH achieves state-of-the-art performance on these problems.

PaperPDFConference PDFCode

Code

compmem/deepsith officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Time SeriesTime Series AnalysisTime Series Prediction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Dense Connections

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections