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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liang, Ziyi, Poursiami, Hamed, Yang, Zhishun, Cooper, Keiland, Jaiswal, Akhilesh, Parsa, Maryam, Fortin, Norbert, Shahbaba, Babak
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917293565411328
author Liang, Ziyi
Poursiami, Hamed
Yang, Zhishun
Cooper, Keiland
Jaiswal, Akhilesh
Parsa, Maryam
Fortin, Norbert
Shahbaba, Babak
author_facet Liang, Ziyi
Poursiami, Hamed
Yang, Zhishun
Cooper, Keiland
Jaiswal, Akhilesh
Parsa, Maryam
Fortin, Norbert
Shahbaba, Babak
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_21446
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ConformalHDC: Uncertainty-Aware Hyperdimensional Computing with Application to Neural Decoding
Liang, Ziyi
Poursiami, Hamed
Yang, Zhishun
Cooper, Keiland
Jaiswal, Akhilesh
Parsa, Maryam
Fortin, Norbert
Shahbaba, Babak
Machine Learning
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.
title ConformalHDC: Uncertainty-Aware Hyperdimensional Computing with Application to Neural Decoding
topic Machine Learning
url https://arxiv.org/abs/2602.21446