Paper Detail

Leveraging Dale's Principle as an Inductive Bias in Recurrent Neural Networks

Jiyi Wang, Chenxiao Yang, Yujia Zhao, Jingzhao Zhang, Lu Mi

arxiv Score 10.0

Published 2026-10-25 · First seen 2026-10-27

Research Track A · General AI

Abstract

One of the fundamental differences between biological neural networks and artificial neural networks (ANNs) is that biological neurons obey Dale's principle: each neuron projects either exclusively excitatory or exclusively inhibitory outputs. While this constraint is central to biological circuits, previous attempts to impose Dale's principle in ANNs have often led to training instability or degraded performance. In this work, we introduce EISep RNN, a recurrent neural network architecture that implements Dale's principle through a learnable excitatory-inhibitory separation. Across a series of learning settings, including multi-task learning, continual learning, and reinforcement learning, EISep achieves more stable training dynamics, competitive or improved performance, and sparser, more modular connectivity than vanilla RNNs and previous Dale-constrained models. EISep also exhibits stable and informative latent dynamics. These results establish Dale's principle as a biologically grounded and computationally effective inductive bias for recurrent neural networks.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{wang2026leveraging,
  title = {Leveraging Dale's Principle as an Inductive Bias in Recurrent Neural Networks},
  author = {Jiyi Wang and Chenxiao Yang and Yujia Zhao and Jingzhao Zhang and Lu Mi},
  year = {2026},
  abstract = {One of the fundamental differences between biological neural networks and artificial neural networks (ANNs) is that biological neurons obey Dale's principle: each neuron projects either exclusively excitatory or exclusively inhibitory outputs. While this constraint is central to biological circuits, previous attempts to impose Dale's principle in ANNs have often led to training instability or degraded performance. In this work, we introduce EISep RNN, a recurrent neural network architecture that},
  url = {https://arxiv.org/abs/2610.34052},
  keywords = {cs.LG},
  eprint = {2610.34052},
  archiveprefix = {arXiv},
}

Metadata

{}