Hierarchical Temporal Receptive Windows And Zeroshot Timescale Generalization In Biologically Constrained Scaleinvariant Deep Networks
ASecurity**arXiv ID:** 2601.02618 **Authors:** Aakash Sarkar, Marc W. Howard **Published:** 2026-01-06T00:36:45Z **Abstract:** Human cognition integrates information across nested timescales. While the cortex exhibits hierarchical Temporal Receptive Windows (TRWs), local circuits often display heterogeneous time constants. To reconcile this, we trained biologically constrained deep networks, based on scale-invariant hippocampal time cells, on a language classification task mimicking the hierarchical s...
- 3 stars
- 0 votes
- 0 copies
- 5 views
- Added September 11, 2026
Security analysis
100/100npx -y skills add hiyenwong/ai_collection --skill hierarchical-temporal-receptive-windows-and-zeroshot-timescale-generalization-in-biologically-constrained-scaleinvariant-deep-networks --agent claude-codeAre you the author of Hierarchical Temporal Receptive Windows And Zeroshot Timescale Generalization In Biologically Constrained Scaleinvariant Deep Networks?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-hierarchical-temporal-receptive-windows-and-zerosh)# Hierarchical temporal receptive windows and zero-shot timescale generalization in biologically constrained scale-invariant deep networks
**arXiv ID:** 2601.02618
**Authors:** Aakash Sarkar, Marc W. Howard
**Published:** 2026-01-06T00:36:45Z
**Abstract:**
Human cognition integrates information across nested timescales. While the cortex exhibits hierarchical Temporal Receptive Windows (TRWs), local circuits often display heterogeneous time constants. To reconcile this, we trained biologically constrained deep networks, based on scale-invariant hippocampal time cells, on a language classification task mimicking the hierarchical structure of language (e.g., 'letters' forming 'words'). First, using a feedforward model (SITHCon), we found that a hierarchy of TRWs emerged naturally across layers, despite the network having an identical spectrum of time constants within layers. We then distilled these inductive priors into a biologically plausible recurrent architecture, SITH-RNN. Training a sequence of architectures ranging from generic RNNs to this restricted subset showed that the scale-invariant SITH-RNN learned faster with orders-of-magnitude fewer parameters, and generalized zero-shot to out-of-distribution timescales. These results suggest the brain employs scale-invariant, sequential priors - coding "what" happened "when" - making recurrent networks with such priors particularly well-suited to describe human cognition.
## Skill Description
This skill is generated from the arXiv paper: Hierarchical temporal receptive windows and zero-shot timescale generalization in biologically constrained scale-invariant deep networks (2601.02618).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:2601.02618](http://arxiv.org/abs/2601.02618v1)
Attribution
Related skills
View all in tools →Comments
Loading comments…
Newsletter
Get the weekly list of safe new skills, and the ones we pulled.