# A deep convolutional neural network that is invariant to time rescaling

arXiv: https://arxiv.org/abs/2107.04616 · HTML: https://mlsanity.com/paper/2107.04616/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 34 references that are in the map.
- First posted on arXiv 9 Jul 2021.

## Builds on (most cited first, 7 of 7)

- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network](https://mlsanity.com/paper/2104.02133/) (2021)
- [AudioMNIST: Exploring Explainable Artificial Intelligence for Audio Analysis on a Simple Benchmark](https://mlsanity.com/paper/1807.03418/) (2018)
- [Exploring the ability of CNNs to generalise to previously unseen scales over wide scale ranges](https://mlsanity.com/paper/2004.01536/) (2020)
- [DeepSITH: Efficient Learning via Decomposition of What and When Across Time Scales](https://mlsanity.com/paper/2104.04646/) (2021)
- [Separable time-causal and time-recursive spatio-temporal receptive fields](https://mlsanity.com/paper/1504.01502/) (2015)

## Built on by (most cited first, 5 of 5)

- [Traveling Waves Encode the Recent Past and Enhance Sequence Learning](https://mlsanity.com/paper/2309.08045/) (2023)
- [Covariant spatio-temporal receptive fields for spiking neural networks](https://mlsanity.com/paper/2405.00318/) (2024)
- [Deep reinforcement learning with time-scale invariant memory](https://mlsanity.com/paper/2412.15292/) (2024)
- [Gradual Forgetting: Logarithmic Compression for Extending Transformer Context Windows](https://mlsanity.com/paper/2510.22109/) (2025)
- [Hierarchical temporal receptive windows and zero-shot timescale generalization in biologically constrained scale-invariant deep networks](https://mlsanity.com/paper/2601.02618/) (2026)

## Abstract (arXiv)

Human learners can readily understand speech, or a melody, when it is presented slower or faster than usual. Although deep convolutional neural networks (CNNs) are extremely powerful in extracting information from time series, they require explicit training to generalize to different time scales. This paper presents a deep CNN that incorporates a temporal representation inspired by recent findings from neuroscience. In the mammalian brain, time is represented by populations of neurons with temporal receptive fields. Critically, the peaks of the receptive fields form a geometric series, such that the population codes a set of temporal basis functions over log time. Because memory for the recent past is a function of log time, rescaling the input results in translation of the memory. The Scale-Invariant Temporal History Convolution network (SITHCon) builds a convolutional layer over this logarithmically-distributed temporal memory. A max-pool operation results in a network that is invariant to rescalings of time modulo edge effects. We compare performance of SITHCon to a Temporal Convolution Network (TCN). Although both networks can learn classification and regression problems on both univariate and multivariate time series f(t), only SITHCon generalizes to rescalings f(at). This property, inspired by findings from contemporary neuroscience and consistent with findings from cognitive psychology, may enable networks that learn with fewer training examples, fewer weights and that generalize more robustly to out of sample data.