Research map / Time series / Foundation models for time series
A deep convolutional neural network that is invariant to time rescaling
Brandon G Jacques, Zoran Tiganj, Aakash Sarkar, Marc Howard, Per Sederberg
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use logarithmically compressed temporal memory with convolution and max pooling instead of a TCN's linear-time memory | SITHCon vs. TCN · Morse Decoder, unseen time scales | accuracy | Improved |
| Use logarithmically compressed temporal memory with convolution and max pooling instead of a TCN's linear-time memory | SITHCon vs. TCN · Morse Addition, unseen time scales | mean squared error | Improved |
| Use logarithmically compressed temporal memory with convolution and max pooling instead of a TCN's linear-time memory | SITHCon vs. TCN · AudioMNIST, unseen time scales | accuracy | Improved |
| Add log-spaced temporal memory nodes to a trained SITHCon network (ablation) | SITHCon · Morse Decoder, maximum time-rescaling with 100% accuracy | maximum time-rescaling | Improved |
| Train on multiple time scales rather than only scale 1.0 | SITHCon · Morse Decoder, intermediate and unseen scales | accuracy | Improved |
| Train on multiple time scales rather than only scale 1.0 | TCN · AudioMNIST, training scales | accuracy | Hurt |
Closest papers by meaning
- Combining Recurrent, Convolutional, and Continuous-time Models with Linear State Space Layers (NeurIPS 2021 · similarity 0.88)
- Long-Term Recurrent Convolutional Networks for Visual Recognition and Description (TPAMI 2016 · similarity 0.86)
- STCN: Stochastic Temporal Convolutional Networks (ICLR 2019 · similarity 0.86)
- Temporal Deformable Convolutional Encoder-Decoder Networks for Video Captioning (AAAI 2019 · similarity 0.86)
- Convolutional Sequence to Sequence Learning (ICML 2017 · similarity 0.86)
- Time Series Representations with Hard-Coded Invariances (ICML 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
