A Scalable, Causal, and Energy Efficient Framework for Neural Decoding with Spiking Neural Networks

2025-10-23

AI Summary

Current neural decoding approaches face a fundamental trade-off: causal models exhibit poor generalization, whereas non-causal models suffer from high energy consumption and limited real-time applicability. To address this, we propose Spikachu—the first spiking neural network (SNN) framework designed for large-scale, cross-session and cross-subject neural decoding. Its core innovation is a temporally adaptive spiking module that enables causal, online, few-shot transfer decoding within a shared latent space. Evaluated on 43 hours of neural recordings from six non-human primates, Spikachu achieves real-time inference while reducing energy consumption by 2.26×–418.81× compared to state-of-the-art artificial neural network (ANN) baselines. It significantly outperforms causal baselines in decoding accuracy and, for the first time, demonstrates robust few-shot generalization across both tasks and subjects.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Deep Neural Architectures and Foundation Models
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Brain-computer interfaces (BCIs) promise to enable vital functions, such as speech and prosthetic control, for individuals with neuromotor impairments. Central to their success are neural decoders, models that map neural activity to intended behavior. Current learning-based decoding approaches fall into two classes: simple, causal models that lack generalization, or complex, non-causal models that generalize and scale offline but struggle in real-time settings. Both face a common challenge, their reliance on power-hungry artificial neural network backbones, which makes integration into real-world, resource-limited systems difficult. Spiking neural networks (SNNs) offer a promising alternative. Because they operate causally these models are suitable for real-time use, and their low energy demands make them ideal for battery-constrained environments. To this end, we introduce Spikachu: a scalable, causal, and energy-efficient neural decoding framework based on SNNs. Our approach processes binned spikes directly by projecting them into a shared latent space, where spiking modules, adapted to the timing of the input, extract relevant features; these latent representations are then integrated and decoded to generate behavioral predictions. We evaluate our approach on 113 recording sessions from 6 non-human primates, totaling 43 hours of recordings. Our method outperforms causal baselines when trained on single sessions using between 2.26 and 418.81 times less energy. Furthermore, we demonstrate that scaling up training to multiple sessions and subjects improves performance and enables few-shot transfer to unseen sessions, subjects, and tasks. Overall, Spikachu introduces a scalable, online-compatible neural decoding framework based on SNNs, whose performance is competitive relative to state-of-the-art models while consuming orders of magnitude less energy.

Problem

• Developing energy-efficient neural decoders for brain-computer interfaces
• Creating causal models suitable for real-time neural decoding applications
• Enabling scalable neural decoding with few-shot transfer across sessions

Innovation

• Uses spiking neural networks for energy-efficient decoding
• Projects binned spikes into a shared latent space
• Scales training across sessions for few-shot transfer