# Robust Reasoning and Learning with Brain-Inspired Representations under Hardware-Induced Nonlinearities

arXiv: https://arxiv.org/abs/2604.12079 · HTML: https://mlsanity.com/paper/2604.12079/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 35 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 6 of 6)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [In-memory hyperdimensional computing](https://mlsanity.com/paper/1906.01548/) (2019)
- [MIMHD: Accurate and Efficient Hyperdimensional Inference Using Multi-Bit In-Memory Computing](https://mlsanity.com/paper/2106.12029/) (2021)
- [An Overview of In-memory Processing with Emerging Non-volatile Memory for Data-intensive Applications](https://mlsanity.com/paper/1906.06603/) (2019)
- [HEAL: Brain-inspired Hyperdimensional Efficient Active Learning](https://mlsanity.com/paper/2402.11223/) (2024)

## Abstract (arXiv)

Traditional machine learning depends on high-precision arithmetic and near-ideal hardware assumptions, which is increasingly challenged by variability in aggressively scaled semiconductor devices. Compute-in-memory (CIM) architectures alleviate data-movement bottlenecks and improve energy efficiency yet introduce nonlinear distortions and reliability concerns. We address these issues with a hardware-aware optimization framework based on Hyperdimensional Computing (HDC), systematically compensating for non-ideal similarity computations in CIM. Our approach formulates encoding as an optimization problem, minimizing the Frobenius norm between an ideal kernel and its hardware-constrained counterpart, and employs a joint optimization strategy for end-to-end calibration of hypervector representations. Experimental results demonstrate that our method when applied to QuantHD achieves 84% accuracy under severe hardware-induced perturbations, a 48% increase over naive QuantHD under the same conditions. Additionally, our optimization is vital for graph-based HDC reliant on precise variable-binding for interpretable reasoning. Our framework preserves the accuracy of RelHD on the Cora dataset, achieving a 5.4× accuracy improvement over naive RelHD under nonlinear environments. By preserving HDC's robustness and symbolic properties, our solution enables scalable, energy-efficient intelligent systems capable of classification and reasoning on emerging CIM hardware.