ArticleNeural computation2021
The Remarkable Robustness of Surrogate Gradient Learning for Instilling Complex Function in Spiking Neural Networks.
Article in Neural computation, 2021. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 48 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
48 citing papers in PubMed, 221 citations in OpenAlex.
- Temporal prediction captures retinal spiking responses across animal species.Nature communications · 2026Article
- Neuromorphic Cardiac Sensing: A Bio-Inspired Spiking Neural Network with Sensory-Adaptive Encoding for Energy-Efficient Arrhythmia Detection from ECG and PPG Signals.Biomimetics (Basel, Switzerland) · 2026Article
- A Lightweight Keyword Spotting Method Using a Convolutional Spiking Neural Network with Learnable Synaptic Delays.Sensors (Basel, Switzerland) · 2026Article
- A Synchronization-Driven Learning Rule for Pattern Separation in Self-Organizing Probabilistic Spiking Neural Networks.Research square · 2026Article
- Learning Dynamics in Biophysical Spiking Network Models Are Shaped by KCC2/NKCC1 Cotransporter Stoichiometry.The European journal of neuroscience · 2026Article
- A computational theory of short-term synaptic plasticity: synapses learn to tell time.Research square · 2026Article
- Deep-learning-assisted simulation of a cortical circuit: integrating anatomy, physiology and function.bioRxiv : the preprint server for biology · 2026Article
- Task success in trained spiking neural network models coincides with emergence of cross-stimulus-modulated inhibition.Biological cybernetics · 2026Article
- Three factor delay learning rules for spiking neural networks.Frontiers in neuroscience · 2026Article
- Conductance-based reversal potentials in spiking recurrent neural networks enhance energy efficiency and task performance.Frontiers in computational neuroscience · 2026Article
- Adaptive and lightweight surrogate gradients: enhancing training efficiency of spiking neural networks.Frontiers in neuroscience · 2026Article
- Three-factor learning in spiking neural networks: An overview of methods and trends from a machine learning perspective.Patterns (New York, N.Y.) · 2025Review
- Efficient and robust temporal processing with neural oscillations modulated spiking neural networks.Nature communications · 2025Article
- Temporal single spike coding for effective transfer learning in spiking neural networks.Scientific reports · 2025Article
- Learning-efficient spiking neural networks with multi-compartment spatio-temporal backpropagation.iScience · 2025Article
- TDE-3: an improved prior for optical flow computation in spiking neural networks.Frontiers in neuroscience · 2025Article
- Structural influences on synaptic plasticity: The role of presynaptic connectivity in the emergence of E/I co-tuning.PLoS computational biology · 2024Article
- Neuromorphic intermediate representation: A unified instruction set for interoperable brain-inspired computing.Nature communications · 2024Article
- Coincidence detection and integration behavior in spiking neural networks.Cognitive neurodynamics · 2024Article
- LDD: High-Precision Training of Deep Spiking Neural Network Transformers Guided by an Artificial Neural Network.Biomimetics (Basel, Switzerland) · 2024Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
2 authors at 2 institutions in 3 countries.
Funding
Abstract
Brains process information in spiking neural networks. Their intricate connections shape the diverse functions these networks perform. Yet how network connectivity relates to function is poorly understood, and the functional capabilities of models of spiking networks are still rudimentary. The lack of both theoretical insight and practical algorithms to find the necessary connectivity poses a major impediment to both studying information processing in the brain and building efficient neuromorphic hardware systems. The training algorithms that solve this problem for artificial neural networks typically rely on gradient descent. But doing so in spiking networks has remained challenging due to the nondifferentiable nonlinearity of spikes. To avoid this issue, one can employ surrogate gradients to discover the required connectivity. However, the choice of a surrogate is not unique, raising the question of how its implementation influences the effectiveness of the method. Here, we use numerical simulations to systematically study how essential design parameters of surrogate gradients affect learning performance on a range of classification problems. We show that surrogate gradient learning is robust to different shapes of underlying surrogate derivatives, but the choice of the derivative's scale can substantially affect learning performance. When we combine surrogate gradients with suitable activity regularization techniques, spiking networks perform robust information processing at the sparse activity limit. Our study provides a systematic account of the remarkable robustness of surrogate gradient learning and serves as a practical guide to model functional spiking neural networks.
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.