ArticleNature communications2018
Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science.
Article in Nature communications, 2018. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 41 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
41 citing papers in PubMed.
- Analytically tractable model of synaptic crowding explains emergent small-world structure and network dynamics.Scientific reports · 2026Article
- Exploiting neuro-inspired dynamic sparsity for energy-efficient intelligent perception.Nature communications · 2025Review
- S2Transformer: Exploring Sparsity in Remote Sensing Images for Efficient Super-Resolution.Sensors (Basel, Switzerland) · 2025Article
- Concept transfer of synaptic diversity from biological to artificial neural networks.Nature communications · 2025Article
- Integrating chemical artificial intelligence and cognitive computing for predictive analysis of biological pathways: a case for intrinsically disordered proteins.Biophysical reviews · 2025Review
- Neural network compression for reinforcement learning tasks.Scientific reports · 2025Article
- Dendrites endow artificial neural networks with accurate, robust and parameter-efficient learning.Nature communications · 2025Article
- Brain-inspired wiring economics for artificial neural networks.PNAS nexus · 2025Article
- A survey of model compression techniques: past, present, and future.Frontiers in robotics and AI · 2025Review
- scGO: interpretable deep neural network for cell status annotation and disease diagnosis.Briefings in bioinformatics · 2024Article
- Dendrites endow artificial neural networks with accurate, robust and parameter-efficient learning.ArXiv · 2024Article
- Loss of plasticity in deep continual learning.Nature · 2024Article
- Modelling dataset bias in machine-learned theories of economic decision-making.Nature human behaviour · 2024Article
- Photonic Stochastic Emergent Storage for deep classification by scattering-intrinsic patterns.Nature communications · 2024Article
- Learning delays through gradients and structure: emergence of spatiotemporal patterns in spiking neural networks.Frontiers in computational neuroscience · 2024Article
- Group-informed attentive framework for enhanced diabetes mellitus progression prediction.Frontiers in endocrinology · 2024Article
- Distinctive properties of biological neural networks and recent advances in bottom-up approaches toward a better biologically plausible neural network.Frontiers in computational neuroscience · 2023Review
- Perturbation of deep autoencoder weights for model compression and classification of tabular data.Neural networks : the official journal of the International Neural Network Society · 2022Article
- Pruning deep neural networks generates a sparse, bio-inspired nonlinear controller for insect flight.PLoS computational biology · 2022Article
- Non-smooth Bayesian learning for artificial neural networks.Journal of ambient intelligence and humanized computing · 2022Article
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
Through the success of deep learning in various domains, artificial neural networks are currently among the most used artificial intelligence methods. Taking inspiration from the network properties of biological neural networks (e.g. sparsity, scale-freeness), we argue that (contrary to general practice) artificial neural networks, too, should not have fully-connected layers. Here we propose sparse evolutionary training of artificial neural networks, an algorithm which evolves an initial sparse topology (Erdős-Rényi random graph) of two consecutive layers of neurons into a scale-free topology, during learning. Our method replaces artificial neural networks fully-connected layers with sparse ones before training, reducing quadratically the number of parameters, with no decrease in accuracy. We demonstrate our claims on restricted Boltzmann machines, multi-layer perceptrons, and convolutional neural networks for unsupervised and supervised learning on 15 datasets. Our approach has the potential to enable artificial neural networks to scale up beyond what is currently possible.
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.