# Training reservoirs without looking back

Source: [nature.com](https://www.nature.com/articles/s43588-026-01079-6) · 2026-11-13 · Computing
Page: https://themorning.science/story/training-reservoirs-without-looking-back-44ecfe61f0982ff6
Kind: research · Impact: low

## In brief

- Nature Computational Science published a paper on 13 November 2026 describing a physical learning framework for reservoir computing.
- The framework trains the reservoir without access to its intermediate states.
- It eliminates coupling between the reservoir's nodes to achieve efficient learning.

## Why it matters

The approach suggests physical reservoir computing hardware could be trained more simply, which may matter for researchers building neuromorphic or physical computing systems.

## Timeline

- 2026-11-13: Paper published online in Nature Computational Science

## Coverage

- [Training reservoirs without looking back](https://www.nature.com/articles/s43588-026-01079-6) — nature.com, 2026-11-13

Tags: reservoir computing, physical learning, neuromorphic computing, machine learning

---

Brief generated by AI (claude-haiku-5-5) from the reporting listed under Coverage. Headlines belong to their publishers. The Morning Science – https://themorning.science