ReviewNature2025
Training of physical neural networks.
Review in Nature, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 26 papers, 1 of them a synthesis that pooled it.
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
26 citing papers in PubMed, 1 synthesis or guideline pooled it.
- Can AI assess literature like experts? An entropy-based comparison of ChatGPT-4o, DeepSeek R1, and human ratings.Frontiers in research metrics and analytics · 2025Pooled it
- Deep diffractive optical neural networks for detecting skyrmionic topologies of light and their live training.Nature communications · 2026Article
- Emerging integrated photonic neural network technologies for artificial intelligence: from devices to systems.National science review · 2026Review
- How nanophotonics can drive optical computing toward practical applications.Nature nanotechnology · 2026Review
- A Physical Adaptive Material Motor Unit Neural Network: A Hygromorph Composite Material Machine.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026Article
- Few-shot neuromorphic vision in a nonlinear photonic network laser.Science advances · 2026Article
- Physics-Guided Generative Inverse Design of Low-Carbon Concrete via Multi-Objective Latent Space Optimization.ACS omega · 2026Article
- Broadband, Compact, and Training-Free Optical Processors for Parallel Image Classification.ACS nano · 2026Article
- Bio-inspired backpropagation-free training for optical neural networks.Light, science & applications · 2026Article
- Creation of a computational space with model-free metasurface neural network.Nature communications · 2026Article
- Topological acoustic synapse for high-dimensional neuromorphic computing.Science advances · 2026Article
- Dynamical Symbiosis of Solar Cell and Memristor.ACS energy letters · 2026Article
- Physical Implementation of Optical Material-Based Neural Networks Processing Enabled by Long-Persistent Luminescence.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026Article
- Trainable neuromorphic spintronic hardware Via analog finite-difference gradient methods.Nature communications · 2026Article
- Article
- Inverse-designed nanophotonic neural network accelerators for ultra-compact optical computing.Nature communications · 2026Article
- Artificial intelligence-driven nano-enhanced stem cell therapy for neurodegenerative diseases: from rational design to clinical translation.Journal of nanobiotechnology · 2026Review
- Robust and Integrable Time-Varying Metamaterials: A Systematic Survey and Coherent Mapping.Nanomaterials (Basel, Switzerland) · 2026Review
- Physical neural networks using sharpness-aware training.Nature communications · 2026Article
- Learned adaptive properties for mitigation of weight perturbations in embedded spiking networks.Frontiers in neuroscience · 2026Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
28 authors.
Funding
Abstract
Physical neural networks (PNNs) are a class of neural-like networks that make use of analogue physical systems to perform computations. Although at present confined to small-scale laboratory demonstrations, PNNs could one day transform how artificial intelligence (AI) calculations are performed. Could we train AI models many orders of magnitude larger than present ones? Could we perform model inference locally and privately on edge devices? Research over the past few years has shown that the answer to these questions is probably "yes, with enough research". Because PNNs can make use of analogue physical computations more directly, flexibly and opportunistically than traditional computing hardware, they could change what is possible and practical for AI systems. To do this, however, will require notable progress, rethinking both how AI models work and how they are trained-primarily by considering the problems through the constraints of the underlying hardware physics. To train PNNs, backpropagation-based and backpropagation-free approaches are now being explored. These methods have various trade-offs and, so far, no method has been shown to scale to large models with the same performance as the backpropagation algorithm widely used in deep learning today. However, this challenge has been rapidly changing and a diverse ecosystem of training techniques provides clues for how PNNs may one day be used to create both more efficient and larger-scale realizations of present-scale AI models.
Indexed as
Identifiers
40903603What 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.