# Neuromorphic Hardware learns to learn

arXiv: https://arxiv.org/abs/1903.06493 · HTML: https://mlsanity.com/paper/1903.06493/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Mar 2019.

## Built on by (most cited first, 8 of 8)

- [Fast On-Device Adaptation for Spiking Neural Networks via Online-Within-Online Meta-Learning](https://mlsanity.com/paper/2103.03901/) (2021)
- [Memristive Reservoirs Learn to Learn](https://mlsanity.com/paper/2306.12676/) (2023)
- [Bridge Networks: Relating Inputs through Vector-Symbolic Manipulations](https://mlsanity.com/paper/2106.08446/) (2021)
- [Learning to learn online with neuromodulated synaptic plasticity in spiking neural networks](https://mlsanity.com/paper/2206.12520/) (2022)
- [Realizing Molecular Machine Learning through Communications for Biological AI: Future Directions and Challenges](https://mlsanity.com/paper/2212.11910/) (2022)
- [Evolving-to-Learn Reinforcement Learning Tasks with Spiking Neural Networks](https://mlsanity.com/paper/2202.12322/) (2022)
- [Motion Mapping Cognition: A Nondecomposable Primary Process in Human Vision](https://mlsanity.com/paper/2402.04275/) (2024)
- [Learning-to-learn enables rapid learning with phase-change memory-based in-memory computing](https://mlsanity.com/paper/2405.05141/) (2024)

## Abstract (arXiv)

Hyperparameters and learning algorithms for neuromorphic hardware are usually chosen by hand. In contrast, the hyperparameters and learning algorithms of networks of neurons in the brain, which they aim to emulate, have been optimized through extensive evolutionary and developmental processes for specific ranges of computing and learning tasks. Occasionally this process has been emulated through genetic algorithms, but these require themselves hand-design of their details and tend to provide a limited range of improvements. We employ instead other powerful gradient-free optimization tools, such as cross-entropy methods and evolutionary strategies, in order to port the function of biological optimization processes to neuromorphic hardware. As an example, we show that this method produces neuromorphic agents that learn very efficiently from rewards. In particular, meta-plasticity, i.e., the optimization of the learning rule which they use, substantially enhances reward-based learning capability of the hardware. In addition, we demonstrate for the first time Learning-to-Learn benefits from such hardware, in particular, the capability to extract abstract knowledge from prior learning experiences that speeds up the learning of new but related tasks. Learning-to-Learn is especially suited for accelerated neuromorphic hardware, since it makes it feasible to carry out the required very large number of network computations.