npj Unconventional Computing最新文献

A cybernetic framework for synthetic biological intelligence in the era of neural tissue engineering. 神经组织工程时代合成生物智能的控制论框架。

npj Unconventional Computing Pub Date : 2026-01-01 Epub Date: 2026-07-02 DOI: 10.1038/s44335-026-00077-1

Étienne P Sellar, Nicolas Rouleau

引用次数: 0

Vector symbolic algebras for the Abstraction and Reasoning Corpus. 抽象与推理语料库的向量符号代数。

npj Unconventional Computing Pub Date : 2026-01-01 Epub Date: 2026-10-01 DOI: 10.1038/s44335-026-00100-5

Isaac Joffe, Chris Eliasmith

{"title":"Vector symbolic algebras for the Abstraction and Reasoning Corpus.","authors":"Isaac Joffe, Chris Eliasmith","doi":"10.1038/s44335-026-00100-5","DOIUrl":"https://doi.org/10.1038/s44335-026-00100-5","url":null,"abstract":"The Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI) is a generative, few-shot fluid intelligence benchmark. Although humans effortlessly solve ARC-AGI, it remains extremely difficult for even the most advanced artificial intelligence systems. Inspired by methods for modelling human intelligence spanning neuroscience to psychology, we propose a cognitively inspired ARC-AGI solver. Our solver integrates System 1 intuitions with System 2 reasoning in an efficient and interpretable process using neurosymbolic methods based on Vector Symbolic Algebras (VSAs). Our solver works by object-centric program synthesis, leveraging VSAs to represent abstract objects, guide solution search, and enable sample-efficient neural learning. Preliminary results indicate success, with our solver scoring 10.8% on ARC-AGI-1-Train and 3.0% on ARC-AGI-1-Eval. Additionally, our solver performs well on simpler benchmarks, scoring 94.5% on Sort-of-ARC and 83.1% on 1D-ARC-the latter outperforming GPT-4 at a tiny fraction of the computational cost. Importantly, our approach is unique; we believe we are the first to apply VSAs to ARC-AGI and have developed one of the most cognitively plausible ARC-AGI solvers yet. Our code is available at: https://github.com/ijoffe/ARC-VSA-2025.","PeriodicalId":501715,"journal":{"name":"npj Unconventional Computing","volume":"3 1","pages":"54"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13630561/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149121836","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Achieving high precision in analog in-memory computing systems. 在模拟内存计算系统中实现高精度。

npj Unconventional Computing Pub Date : 2026-01-01 Epub Date: 2026-01-07 DOI: 10.1038/s44335-025-00044-2

Piergiulio Mannocci, Giacomo Larelli, Marco Bonomi, Daniele Ielmini

引用次数: 0

Sliding-window training on readout layer enhances liquid state machines for temporal prediction. 在读出层上的滑动窗口训练增强了液态机的时间预测能力。

npj Unconventional Computing Pub Date : 2026-01-01 Epub Date: 2026-09-16 DOI: 10.1038/s44335-026-00093-1

Shimeng Wu, Andrew Walter, Andy M Tyrrell, Martin A Trefzer

{"title":"Sliding-window training on readout layer enhances liquid state machines for temporal prediction.","authors":"Shimeng Wu, Andrew Walter, Andy M Tyrrell, Martin A Trefzer","doi":"10.1038/s44335-026-00093-1","DOIUrl":"10.1038/s44335-026-00093-1","url":null,"abstract":"Temporal prediction is essential in scientific and engineering problems, particularly for low-power online inference. Reservoir computing is attractive because a fixed recurrent system maps inputs into a high-dimensional state decoded by a simple readout. Liquid state machines instantiate this idea with recurrent spiking neurons, yielding sparse event-driven states suited to neuromorphic and digital hardware. However, the stepwise protocol trains the readout from an instantaneous state, which can be information-limited when evidence is distributed across time. We improve temporal prediction by providing the readout with a finite temporal context. We concatenate a sliding window of recent reservoir spike states and train on either ridge regression or a transformer readout. On the Nonlinear AutoRegressive Moving Average (NARMA5) benchmark, increasing context length improves both readouts. Median test NRMSE for ridge regression decreases from 2.106 under stepwise decoding to 0.317, an 85% reduction. The transformer readout shows the same trend, decreasing from 0.807 to 0.179, a 78% reduction. The same qualitative trend is further observed on NARMA10 and Mackey Glass prediction tasks. These results demonstrate that exposing recent reservoir evolution at the decoder can substantially reduce the limitations of stepwise decoding while retaining the standard reservoir computing protocol.","PeriodicalId":501715,"journal":{"name":"npj Unconventional Computing","volume":"3 1","pages":"52"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13581606/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148993534","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Hybrid quantum-classical photonic neural networks. 混合量子-经典光子神经网络。

npj Unconventional Computing Pub Date : 2025-01-01 Epub Date: 2025-12-01 DOI: 10.1038/s44335-025-00045-1

Tristan Austin, Simon Bilodeau, Andrew Hayman, Nir Rotenberg, Bhavin J Shastri

{"title":"Hybrid quantum-classical photonic neural networks.","authors":"Tristan Austin, Simon Bilodeau, Andrew Hayman, Nir Rotenberg, Bhavin J Shastri","doi":"10.1038/s44335-025-00045-1","DOIUrl":"10.1038/s44335-025-00045-1","url":null,"abstract":"Neuromorphic (brain-inspired) photonics accelerates AI1 with high-speed, energy-efficient solutions for RF communication2, image processing3,4, and fast matrix multiplication5,6. However, integrated neuromorphic photonic hardware faces size constraints that limit network complexity. Recent advances in photonic quantum hardware7 and performant trainable quantum circuits8 offer a path to more scalable photonic neural networks. Here, we show that a combination of classical network layers with trainable continuous variable quantum circuits yields hybrid networks with improved trainability and accuracy. On a classification task, these hybrid networks match the performance of classical networks nearly twice their size. These performance benefits remain even when evaluated at state-of-the-art bit precisions for classical and quantum hardware. Finally, we outline available hardware and a roadmap to hybrid architectures. These hybrid quantum-classical networks demonstrate a unique route to enhance the computational capacity of integrated photonic neural networks without increasing the network size.","PeriodicalId":501715,"journal":{"name":"npj Unconventional Computing","volume":"2 1","pages":"29"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12669026/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145672906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A self-training spiking superconducting neuromorphic architecture. 一个自我训练的尖峰超导神经形态结构。

npj Unconventional Computing Pub Date : 2025-01-01 Epub Date: 2025-03-04 DOI: 10.1038/s44335-025-00021-9

M L Schneider, E M Jué, M R Pufall, K Segall, C W Anderson

引用次数: 0

A neuromorphic multi-scale approach for real-time heart rate and state detection. 实时心率和状态检测的神经形态多尺度方法。

npj Unconventional Computing Pub Date : 2025-01-01 Epub Date: 2025-04-02 DOI: 10.1038/s44335-025-00024-6

Chiara De Luca, Mirco Tincani, Giacomo Indiveri, Elisa Donati

{"title":"A neuromorphic multi-scale approach for real-time heart rate and state detection.","authors":"Chiara De Luca, Mirco Tincani, Giacomo Indiveri, Elisa Donati","doi":"10.1038/s44335-025-00024-6","DOIUrl":"10.1038/s44335-025-00024-6","url":null,"abstract":"With the advent of novel sensor and machine learning technologies, it is becoming possible to develop wearable systems that perform continuous recording and processing of biosignals for health or body state assessment. For example, modern smartwatches can already track physiological functions, including heart rate and its anomalies, with high precision. However, stringent constraints on size and energy consumption pose significant challenges for always-on operation to detect trends across multiple time scales for extended periods of time. To address these challenges, we propose an alternative solution that exploits the ultra-low power consumption features of mixed-signal neuromorphic technologies. We present a biosignal processing architecture that integrates multimodal sensory inputs and processes them using the principles of neural computation to reliably detect trends in heart rate and physiological states. We validate this architecture on a mixed-signal neuromorphic processor and demonstrate its robust operation despite the inherent variability of the analog circuits present in the system. In addition, we demonstrate how the system can process multi scale signals, namely instantaneous heart rate and its long-term states discretized into distinct zones, effectively detecting monotonic changes over extended periods that indicate pathological conditions such as agitation. This approach paves the way for a new generation of energy-efficient stand-alone wearable devices that are particularly suited for scenarios that require continuous health monitoring with minimal device maintenance.","PeriodicalId":501715,"journal":{"name":"npj Unconventional Computing","volume":"2 1","pages":"6"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11964916/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143797550","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Computing with oscillators from theoretical underpinnings to applications and demonstrators 计算与振荡器从理论基础到应用和示范

npj Unconventional Computing Pub Date : 2024-12-04 DOI: 10.1038/s44335-024-00015-z

Aida Todri-Sanial, Corentin Delacour, Madeleine Abernot, Filip Sabo

引用次数: 0

Adiabatic leaky integrate and fire neurons with refractory period for ultra low energy neuromorphic computing 超低能神经形态计算的绝热泄漏积分和不应期放电神经元

npj Unconventional Computing Pub Date : 2024-12-04 DOI: 10.1038/s44335-024-00013-1

Marco Massarotto, Stefano Saggini, Mirko Loghi, David Esseni

{"title":"Adiabatic leaky integrate and fire neurons with refractory period for ultra low energy neuromorphic computing","authors":"Marco Massarotto, Stefano Saggini, Mirko Loghi, David Esseni","doi":"10.1038/s44335-024-00013-1","DOIUrl":"10.1038/s44335-024-00013-1","url":null,"abstract":"In recent years, the in-memory-computing in charge domain has gained significant interest as a promising solution to further enhance the energy efficiency of neuromorphic hardware. In this work, we explore the synergy between the brain-inspired computation and the adiabatic paradigm by presenting an adiabatic Leaky Integrate-and-Fire neuron in 180 nm CMOS technology, that is able to emulate the most important primitives for a valuable neuromorphic computation, such as the accumulation of the incoming input spikes, an exponential leakage of the membrane potential and a tunable refractory period. Differently from previous contributions in the literature, our design can exploit both the charging and recovery phases of the adiabatic operation to ensure a seamless and continuous computation, all the while exchanging energy with the power supply with an efficiency higher than 90% over a wide range of resonance frequencies, and even surpassing 99% for the lowest frequencies. Our simulations unveil a minimum energy per synaptic operation of 470 fJ at a 500 kHz resonance frequency, which yields a 9x energy saving with respect to a non-adiabatic operation.","PeriodicalId":501715,"journal":{"name":"npj Unconventional Computing","volume":" ","pages":"1-11"},"PeriodicalIF":0.0,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44335-024-00013-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142762941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Thermodynamic linear algebra 热力学线性代数

npj Unconventional Computing Pub Date : 2024-11-05 DOI: 10.1038/s44335-024-00014-0

Maxwell Aifer, Kaelan Donatella, Max Hunter Gordon, Samuel Duffield, Thomas Ahle, Daniel Simpson, Gavin Crooks, Patrick J. Coles

{"title":"Thermodynamic linear algebra","authors":"Maxwell Aifer, Kaelan Donatella, Max Hunter Gordon, Samuel Duffield, Thomas Ahle, Daniel Simpson, Gavin Crooks, Patrick J. Coles","doi":"10.1038/s44335-024-00014-0","DOIUrl":"10.1038/s44335-024-00014-0","url":null,"abstract":"Linear algebra is central to many algorithms in engineering, science, and machine learning; hence, accelerating it would have tremendous economic impact. Quantum computing has been proposed for this purpose, although the resource requirements are far beyond current technological capabilities. We consider an alternative physics-based computing paradigm based on classical thermodynamics, to provide a near-term approach to accelerating linear algebra. At first sight, thermodynamics and linear algebra seem to be unrelated fields. Here, we connect solving linear algebra problems to sampling from the thermodynamic equilibrium distribution of a system of coupled harmonic oscillators. We present simple thermodynamic algorithms for solving linear systems of equations, computing matrix inverses, and computing matrix determinants. Under reasonable assumptions, we rigorously establish asymptotic speedups for our algorithms, relative to digital methods, that scale linearly in matrix dimension. Our algorithms exploit thermodynamic principles like ergodicity, entropy, and equilibration, highlighting the deep connection between these two seemingly distinct fields, and opening up algebraic applications for thermodynamic computers.","PeriodicalId":501715,"journal":{"name":"npj Unconventional Computing","volume":" ","pages":"1-11"},"PeriodicalIF":0.0,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44335-024-00014-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142579797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0