Research map / Architectures and efficiency / Spiking networks

Timing Is All You Need: SpikeCore, Learnable Delays, and Gain Control for Neuromorphic Classification

NeurIPS 2026 · Architectures and efficiency › Spiking networks · approach: Training deep spiking networks

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces SpikeCore, a recurrent spiking neural network architecture with learnable synaptic delays and gain control for neuromorphic classification, aiming to be trainable with standard deep learning frameworks.

Problem

Fully spiking neural networks are hard to train and incompatible with standard deep learning frameworks, while ANN-to-SNN conversion and hybrid approaches sacrifice biological plausibility or deployment efficiency.

Approach

A recurrent spiking architecture (SpikeCore) that uses learnable temporal delays and gain control so that timing itself carries the computation, enabling fully spiking training within standard deep learning frameworks.

Closest papers by meaning

• Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networks (AAAI 2025 · similarity 0.90)
• Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips (ICLR 2024 · similarity 0.89)
• Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings (ICLR 2024 · similarity 0.89)
• Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness (ICLR 2025 · similarity 0.89)
• SpikingSSMs: Learning Long Sequences with Sparse and Parallel Spiking State Space Models (AAAI 2025 · similarity 0.89)
• Multiplication-Free Parallelizable Spiking Neurons with Efficient Spatio-Temporal Dynamics (NeurIPS 2025 · similarity 0.89)