SPINT: Spatial Permutation-Invariant Neural Transformer for Consistent Intracortical Motor Decoding

2025-07-11

AI Summary

Intracortical brain–computer interfaces (iBCIs) suffer from long-standing neural non-stationarity across sessions, leading to substantial degradation in cross-session decoding performance. Existing alignment methods rely on fixed neural landmarks, require session-specific labels or online parameter updates, and thus exhibit poor generalizability and high deployment overhead. To address this, we propose a robust, unsupervised, label-agnostic motor decoding framework that eliminates explicit neural alignment. Built upon a Transformer architecture, our method introduces context-aware dynamic positional encoding and dynamic channel dropout to explicitly model the permutation invariance of neuronal ensembles, enabling gradient-free zero-shot or few-shot adaptation. Evaluated on the multi-session FALCON dataset, our approach significantly outperforms existing unsupervised baselines, achieving stable, high-fidelity cross-session decoding without test-time alignment or fine-tuning.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

Intracortical Brain-Computer Interfaces (iBCI) aim to decode behavior from neural population activity, enabling individuals with motor impairments to regain motor functions and communication abilities. A key challenge in long-term iBCI is the nonstationarity of neural recordings, where the composition and tuning profiles of the recorded populations are unstable across recording sessions. Existing methods attempt to address this issue by explicit alignment techniques; however, they rely on fixed neural identities and require test-time labels or parameter updates, limiting their generalization across sessions and imposing additional computational burden during deployment. In this work, we introduce SPINT - a Spatial Permutation-Invariant Neural Transformer framework for behavioral decoding that operates directly on unordered sets of neural units. Central to our approach is a novel context-dependent positional embedding scheme that dynamically infers unit-specific identities, enabling flexible generalization across recording sessions. SPINT supports inference on variable-size populations and allows few-shot, gradient-free adaptation using a small amount of unlabeled data from the test session. To further promote model robustness to population variability, we introduce dynamic channel dropout, a regularization method for iBCI that simulates shifts in population composition during training. We evaluate SPINT on three multi-session datasets from the FALCON Benchmark, covering continuous motor decoding tasks in human and non-human primates. SPINT demonstrates robust cross-session generalization, outperforming existing zero-shot and few-shot unsupervised baselines while eliminating the need for test-time alignment and fine-tuning. Our work contributes an initial step toward a robust and scalable neural decoding framework for long-term iBCI applications.

Problem

• Addresses nonstationarity in neural recordings for iBCI
• Decodes behavior from unordered neural unit sets
• Enables cross-session generalization without test-time alignment

Innovation

• Spatial permutation-invariant neural transformer for decoding
• Dynamic positional embedding for unit-specific identities
• Dynamic channel dropout for population variability robustness