ArticleNature communications2022
Physical deep learning with biologically inspired training method: gradient-free approach for physical hardware.
Article in Nature communications, 2022. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 18 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
18 citing papers in PubMed.
- Creation of a computational space with model-free metasurface neural network.Nature communications · 2026Article
- Trainable neuromorphic spintronic hardware Via analog finite-difference gradient methods.Nature communications · 2026Article
- Physical neural networks using sharpness-aware training.Nature communications · 2026Article
- Model-free optical processors using in situ reinforcement learning with proximal policy optimization.Light, science & applications · 2026Article
- Gradient descent in materia through homodyne gradient extraction.Nature communications · 2025Article
- Noise-aware training of neuromorphic dynamic device networks.Nature communications · 2025Article
- Training of physical neural networks.Nature · 2025Review
- Principles and metrics of extreme learning machines using a highly nonlinear fiber.Nanophotonics (Berlin, Germany) · 2025Article
- Asymmetrical estimator for training encapsulated deep photonic neural networks.Nature communications · 2025Article
- Noise and Dynamical Synapses as Optimization Tools for Spiking Neural Networks.Entropy (Basel, Switzerland) · 2025Article
- Efficient optimisation of physical reservoir computers using only a delayed input.Communications engineering · 2025Article
- Emergent Self-Adaptation in an Integrated Photonic Neural Network for Backpropagation-Free Learning.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2025Article
- Ornstein-Uhlenbeck Adaptation as a Mechanism for Learning in Brains and Machines.Entropy (Basel, Switzerland) · 2024Article
- Overcoming the coherence time barrier in quantum machine learning on temporal data.Nature communications · 2024Article
- Few- and single-molecule reservoir computing experimentally demonstrated with surface-enhanced Raman scattering and ion gating.Science advances · 2024Article
- Redox-based ion-gating reservoir consisting of (104) oriented LiCoOScientific reports · 2023Article
- Photonic online learning: a perspective.Nanophotonics (Berlin, Germany) · 2023Article
- Parallel and deep reservoir computing using semiconductor lasers with optical feedback.Nanophotonics (Berlin, Germany) · 2023Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
6 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Ever-growing demand for artificial intelligence has motivated research on unconventional computation based on physical devices. While such computation devices mimic brain-inspired analog information processing, the learning procedures still rely on methods optimized for digital processing such as backpropagation, which is not suitable for physical implementation. Here, we present physical deep learning by extending a biologically inspired training algorithm called direct feedback alignment. Unlike the original algorithm, the proposed method is based on random projection with alternative nonlinear activation. Thus, we can train a physical neural network without knowledge about the physical system and its gradient. In addition, we can emulate the computation for this training on scalable physical hardware. We demonstrate the proof-of-concept using an optoelectronic recurrent neural network called deep reservoir computer. We confirmed the potential for accelerated computation with competitive performance on benchmarks. Our results provide practical solutions for the training and acceleration of neuromorphic computation.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.