mlsanityData to 14 Oct 2026

Self-training superconducting neuromorphic circuits using reinforcement learning rules

arXiv 2404.18774 ↗First posted 29 Apr 2024cond-mat.supr-con cs.AIcited by 0

On the map: Deep reinforcement learning methods → Spiking and neuromorphic RL

Abstract (arXiv)

Reinforcement learning algorithms are used in a wide range of applications, from gaming and robotics to autonomous vehicles. In this paper we describe a set of reinforcement learning-based local weight update rules and their implementation in superconducting hardware. Using SPICE circuit simulations, we implement a small-scale neural network with a learning time of order one nanosecond. This network can be trained to learn new functions simply by changing the target output for a given set of inputs, without the need for any external adjustments to the network. In this implementation the weights are adjusted based on the current state of the overall network response and locally stored information about the previous action. This removes the need to program explicit weight values in these networks, which is one of the primary challenges that analog hardware implementations of neural networks face. The adjustment of weights is based on a global reinforcement signal that obviates the need for circuitry to back-propagate errors.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Spiking and neuromorphic RL, one of 15 directions in Deep reinforcement learning methods. Builds on 6 of its 52 references that are in the map. First posted on arXiv 29 Apr 2024.

Builds on

6 of 52 references.

References · 6

  1. 2021Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systemscited by 128
  2. 2017A Survey of Neuromorphic Computing and Neural Networks in Hardwarecited by 85
  3. 2023Multiplexed gradient descent: Fast online training of modern datasets on hardware neural networks without backpropagationcited by 8
  4. 2016Synchronization dynamics on the picosecond timescale in coupled Josephson junction neuronscited by 4
  5. 2023Hybrid Synaptic Structure for Spiking Neural Network Realizationcited by 1
  6. 2023Deep Neuromorphic Networks with Superconducting Single Flux Quantacited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Bellman Memory Units: A neuromorphic framework for synaptic reinforcement learning with an evolving network topology
  2. 2025Hardware-Aware Fine-Tuning of Spiking Q-Networks on the SpiNNaker2 Neuromorphic Platform
  3. 2026Training slow silicon neurons to control extremely fast robots with spiking reinforcement learning
  4. 2026All On-Board: Fully On-Chip Neuromorphic Q-Learning with Embedded CartPole Simulation
  5. 2020Analog Circuit Design with Dyna-Style Reinforcement Learning
  6. 2023Gradient-descent hardware-aware training and deployment for mixed-signal Neuromorphic processors
  7. 2026AstRL: Analog and Mixed-Signal Circuit Synthesis with Deep Reinforcement Learning
  8. 2026Spiking Neural Networks for Continuous Control: Neuromorphic Reinforcement Learning in Conventional Computing