ConformalHDC: Uncertainty-Aware Hyperdimensional Computing with Application to Neural Decoding

2026-02-24

AI Summary

This work addresses the vulnerability of Hyperdimensional Computing (HDC) to outliers, adversarial perturbations, and out-of-distribution inputs due to its lack of rigorous uncertainty quantification. The study introduces conformal prediction into HDC for the first time, establishing an uncertainty-aware framework with closed decision boundaries. This framework provides finite-sample coverage guarantees through set-valued predictions, enabling reliable rejection of non-conforming inputs, while simultaneously enhancing accuracy via a novel point prediction mechanism grounded in inter-class interactions. Evaluated on multiple real-world datasets using consistency scoring and neural spike data analysis, the approach demonstrates strong empirical performance. Notably, in hippocampal neuron sequence memory tasks, it achieves precise decoding of non-spatial stimuli alongside reliable uncertainty estimation.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• 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

Abstract

Hyperdimensional Computing (HDC) offers a computationally efficient paradigm for neuromorphic learning. Yet, it lacks rigorous uncertainty quantification, leading to open decision boundaries and, consequently, vulnerability to outliers, adversarial perturbations, and out-of-distribution inputs. To address these limitations, we introduce ConformalHDC, a unified framework that combines the statistical guarantees of conformal prediction with the computational efficiency of HDC. For this framework, we propose two complementary variations. First, the set-valued formulation provides finite-sample, distribution-free coverage guarantees. Using carefully designed conformity scores, it forms enclosed decision boundaries that improve robustness to non-conforming inputs. Second, the point-valued formulation leverages the same conformity scores to produce a single prediction when desired, potentially improving accuracy over traditional HDC by accounting for class interactions. We demonstrate the broad applicability of the proposed framework through evaluations on multiple real-world datasets. In particular, we apply our method to the challenging problem of decoding non-spatial stimulus information from the spiking activity of hippocampal neurons recorded as subjects performed a sequence memory task. Our results show that ConformalHDC not only accurately decodes the stimulus information represented in the neural activity data, but also provides rigorous uncertainty estimates and correctly abstains when presented with data from other behavioral states. Overall, these capabilities position the framework as a reliable, uncertainty-aware foundation for neuromorphic computing.

Problem

• Hyperdimensional Computing
• uncertainty quantification
• conformal prediction
• out-of-distribution detection
• neuromorphic computing

Innovation

• Conformal Prediction
• Hyperdimensional Computing
• Uncertainty Quantification
• Neuromorphic Computing
• Neural Decoding