Metraipolis › archive › dc_9616a76bbf46

Memristive-Friendly Hadamard Reservoir Computing: Structured, Multiplier-Free Recurrences at Scale — arXiv:2608.28295

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28295
License (as archived)
CC0-1.0
Archived
2026-10-17T10:47:34.388Z
SHA-256 of the archived text
fa2810240dee0b778cf0583a1212e809566453e354eba27055e6c736000371d1
Stable URL of this page
https://metraipolis.com/documento/dc_9616a76bbf46

How to cite

Memristive-Friendly Hadamard Reservoir Computing: Structured, Multiplier-Free Recurrences at Scale — arXiv:2608.28295 — arXiv (en), https://arxiv.org/abs/2608.28295 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9616a76bbf46 (Metraipolis archive dc_9616a76bbf46, sha256 fa2810240dee0b778cf0583a1212e809566453e354eba27055e6c736000371d1)
BibTeX
@misc{dc9616a76bbf46,
  title = {Memristive-Friendly Hadamard Reservoir Computing: Structured, Multiplier-Free Recurrences at Scale — arXiv:2608.28295},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28295},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9616a76bbf46; sha256 fa2810240dee0b778cf0583a1212e809566453e354eba27055e6c736000371d1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28295. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reservoir Computing (RC) designs Recurrent Neural Networks around a fixed, i.e., untrained, recurrent layer, and is a natural candidate for neuromorphic hardware. Memristive-friendly reservoirs derive the neuron dynamics from memristive-device kinetics, but still rely on dense recurrent matrices, which are expensive to realize physically. In this paper, we replace the dense matrix with a structured orthogonal operator, built from sign diagonals, a permutation, and a fast Walsh-Hadamard transform. The operator is multiplier-free, requires $O(N)$ parameters and $O(N\log N)$ operations per step, and is never materialized as a matrix. We instantiate it in a standard and in a memristive-friendly Echo State Network, with one binary input connection per unit. Our mathematical analysis shows that exact orthogonality yields an echo state condition that is tight in the recurrent scaling, and a noise response that is predictable at design time. Moreover, the operator mixes the whole state in a single application. Experiments on twenty classification and seven regression benchmarks, at reservoir sizes up to $N = 8192$, show that the structured models match dense orthogonal reservoirs, and achieve better mean performance than the cycle reservoir by a margin that widens with size. Furthermore, we time the recurrent step on three hardware platforms, where it is up to $50\times$ faster than a dense product and $10^4\times$ smaller in memory. Finally, we ablate the operator and measure the response to noise, quantization, device mismatch and discrete faults.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.28295 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T10:33:42.415Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).