# Dynamical learning of dynamics

arXiv: https://arxiv.org/abs/1902.02875 · HTML: https://mlsanity.com/paper/1902.02875/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2019.

## Built on by (most cited first, 16 of 16)

- [Adaptable Hamiltonian neural networks](https://mlsanity.com/paper/2102.13235/) (2021)
- [W-Transformers : A Wavelet-based Transformer Framework for Univariate Time Series Forecasting](https://mlsanity.com/paper/2209.03945/) (2022)
- [Machine-learning parameter tracking with partial state observation](https://mlsanity.com/paper/2311.09142/) (2023)
- [Learn one size to infer all: Exploiting translational symmetries in delay-dynamical and spatio-temporal systems using scalable neural networks](https://mlsanity.com/paper/2111.03706/) (2021)
- [Learning Hamiltonian dynamics by reservoir computer](https://mlsanity.com/paper/2104.14474/) (2021)
- [Digital twins of nonlinear dynamical systems](https://mlsanity.com/paper/2210.06144/) (2022)
- [Emergence of a stochastic resonance in machine learning](https://mlsanity.com/paper/2211.09955/) (2022)
- [Expressivity of Neural Networks with Random Weights and Learned Biases](https://mlsanity.com/paper/2407.00957/) (2024)
- [Learning to learn ecosystems from limited data -- a meta-learning approach](https://mlsanity.com/paper/2410.07368/) (2024)
- [Reconstructing dynamics from sparse observations with no training on target system](https://mlsanity.com/paper/2410.21222/) (2024)
- [Digital twins of nonlinear dynamical systems: A perspective](https://mlsanity.com/paper/2309.11461/) (2023)
- [Knowledge-based Deep Learning for Modeling Chaotic Systems](https://mlsanity.com/paper/2209.04259/) (2022)
- [Variability of echo state network prediction horizon for partially observed dynamical systems](https://mlsanity.com/paper/2306.10797/) (2023)
- [Adaptive control of recurrent neural networks using conceptors](https://mlsanity.com/paper/2405.07236/) (2024)
- [Vestibular reservoir computing](https://mlsanity.com/paper/2604.09943/) (2026)
- [Inferring bifurcation diagrams of two distinct chaotic systems by a single machine](https://mlsanity.com/paper/2604.26632/) (2026)

## Abstract (arXiv)

The ability of humans and animals to quickly adapt to novel tasks is difficult to reconcile with the standard paradigm of learning by slow synaptic weight modification. Here we show that fixed-weight neural networks can learn to generate required dynamics by imitation. After appropriate weight pretraining, the networks quickly and dynamically adapt to learn new tasks and thereafter continue to achieve them without further teacher feedback. We explain this ability and illustrate it with a variety of target dynamics, ranging from oscillatory trajectories to driven and chaotic dynamical systems.