न्यूरोमॉर्फिक कंप्यूटिंग एक अंतःविषय क्षेत्र है जो जैविक तंत्रिका नेटवर्क, विशेष रूप से मानव मस्तिष्क की संरचना और कार्य से प्रेरित हार्डवेयर और सॉफ्टवेयर सिस्टम डिज़ाइन करता है। यह गैर-वॉन न्यूमैन आर्किटेक्चर का उपयोग करता है, जिसमें प्रोसेसर और मेमोरी निकटता से एकीकृत होते हैं, जो बड़े पैमाने पर समानांतर गणना, इवेंट-ड्रिवन सूचना प्रसंस्करण और कम-शक्ति संचालन को सक्षम बनाता है। कृत्रिम स्पाइकिंग न्यूरॉन्स और सिनैप्स जैसे तत्वों का उपयोग करते हुए, न्यूरोमॉर्फिक सिस्टम सीखने, अनुकूलन और संवेदी प्रसंस्करण के लिए मस्तिष्क के तंत्र की नकल करते हैं।
यह न्यूरोमॉर्फिक कंप्यूटिंग पर अंग्रेजी में दुनिया भर के प्रकाशनों और पेटेंट का हमारा नवीनतम चयन है, जिसमें कई वैज्ञानिक ऑनलाइन जर्नल शामिल हैं, जिन्हें न्यूरोमॉर्फिक कंप्यूटिंग, स्पाइकिंग न्यूरल नेटवर्क, लीकी इंटीग्रेट-एंड-फायर न्यूरॉन, मेमरिस्टर, न्यूरोमॉर्फिक, सिनैप्टिक प्लास्टिसिटी, एक्सोनल डिले, सिलिकॉन न्यूरॉन, एनालॉग वीएलएसआई, हेबियन लर्निंग और स्पाइकिंग न्यूरल पर वर्गीकृत और केंद्रित किया गया है।
Spiking neural network arrangement for active spad imaging
Patent published on the 2026-06-04 in US under Ref US20260156384 by ECOLE POLYTECHNIQUE FED DE LAUSANNE EPFL [CH] (Lin Yang [ch], Charbon Edoardo [ch])
Abstract: [0000] A spiking neural network system for single-photon imaging is disclosed. The system comprises: a light source for emitting a series of light pulses, one pulse per repetition period, for repeatedly illuminating one or more objects; a single-photon detector for detecting photons received from the one or more objects; a ring circuit connected to the single-photon detector, the ring circuit comprising a set of delay elements connected to one another thereby forming a ring structure, a respecti[...]
Our summary: A spiking neural network system is designed for single-photon imaging. It utilizes a ring circuit with delay elements to store and rotate spikes from a single-photon detector. The system generates images by processing the spikes while preserving their arrival time differences.
spiking neural networks, single-photon imaging, delay elements, ring circuit
Patent
Passive cross-wind and turbulence sensing with neuromorphic camera based imaging
Patent published on the 2026-06-03 in GB under Ref GB2702152 by TELEDYNE DEFENSE ELECTRONICS LLC [US] (Jonathan Partee [us], Mikhail Vorontsov [us])
Abstract: Method comprising: detecting, using a neuromorphic camera, events indicating change of optical flux; determining, based on the events, an optical shift indicating a wind speed or turbulence profile; determining, based on the optical shift, an estimated trajectory of a projectile. Edge detection or user selection may be used to identify a contrast region in the camera’s field of view. Atmospheric turbulence along a path toward an object in the field of view may be determined. A rifle scope may [...]
Our summary: The method utilizes a neuromorphic camera to detect changes in optical flux, enabling the determination of wind speed and turbulence profiles. It generates timestamped event data at high temporal resolution, allowing for the identification of optical distortions affecting projectile trajectories. Artificial intelligence may enhance the analysis of spatio-temporal variations in wind velocity and direction.
neuromorphic camera, optical flux, turbulence sensing, event detection
Patent
Current-mode operation of analog content addressable memories
Patent published on the 2026-04-16 in US under Ref US20260105959 by HEWLETT PACKARD ENTPR DEV LP [US] (Buonanno Luca [us], Pedretti Giacomo [us], Zhao Lei [us], Ignowski James [us])
Abstract: [0000] In certain examples, an analog content addressable memory (ACAM) component includes a plurality of transistors and a memristor. A gate terminal of a first transistor of the plurality of transistors is coupled to a data line for applying an input current, another terminal of the first transistor is coupled to the memristor and a gate terminal of a second transistor, another terminal of the second transistor is coupled to a match line, and the ACAM component is configured to provide a match[...]
Our summary: An analog content addressable memory (ACAM) includes multiple transistors and a memristor. The first transistor applies an input current to the memristor and a second transistor. The ACAM provides a match result based on the input current and the memristor s programmed value.
Analog content addressable memory, Current-mode operation, Transistors, Memristor
Patent
Event-Driven Computer Vision with Spiking Transformers for Energy-Efficient Edge Perception in Sustainable Water Conservancy and Urban Water Utilities
Published on 2026-02-03 by Jing Liu, Hong Liu, Yangdong Li @MDPI
Abstract: Digital transformation in water conservancy and urban water utilities demands perception systems that are accurate, fast, and energy-efficient and maintainable over long service lifecycles at the edge. We present HydroSNN, a neuromorphic computer-vision framework that couples an event-driven sensing pipeline with a spiking-transformer backbone to support monitoring of canals, reservoirs, treatment plants, and buried pipeline networks. By reducing always-on compute and unnecessary data movement, [...]
Our summary: HydroSNN is a neuromorphic computer-vision framework designed for energy-efficient monitoring of water infrastructure. It utilizes an event-driven sensing pipeline and a spiking-transformer backbone to enhance accuracy and reduce operational energy use. The framework introduces novel components for improved performance and sustainability in edge perception systems.
Event-Driven, Spiking Transformers, Energy-Efficient, Water Utilities
Publication
Memristor Synapse—A Device-Level Critical Review
Published on 2026-01-28 by Sridhar Chandrasekaran, Yao-Feng Chang, Firman Mangasa Simanjuntak @MDPI
Abstract: The memristor has long been known as a nonvolatile memory technology alternative and has recently been explored for neuromorphic computing, owing to its capability to mimic the synaptic plasticity of the human brain. The architecture of a memristor synapse device allows ultra-high-density integration by internetworking with crossbar arrays, which benefits large-scale training and learning using advanced machine-learning algorithms. In this review, we present a statistical analysis of neuromorphi[...]
Our summary: This review analyzes memristor synapses for neuromorphic computing, emphasizing their ability to mimic synaptic plasticity. It discusses device-level characteristics and applications in hardware neural networks and highlights future directions in healthcare. The study also covers statistical trends in memristive systems from 2018 to 2025.
Memristor, Neuromorphic Computing, Synaptic Plasticity, Optoelectronic Synapses
Publication
Logic Gates Based on Skyrmions
Published on 2026-01-19 by Yun Shu, Qianrui Li, Wei Zhang, Yi Peng, Ping Lai, Guoping Zhao @MDPI
Abstract: Traditional complementary metal-oxide-semiconductor (CMOS) logic gates serve as the fundamental building blocks of modern computing, operating through the electron charge manipulation wherein binary information is encoded as distinct high- and low-voltage states. However, as physical dimensions approach the quantum limit, conventional logic gates encounter fundamental bottlenecks, including power consumption barriers, memory limitations, and a significant increase in static power dissipation. Co[...]
Our summary: Magnetic skyrmion logic gates offer a promising alternative to traditional CMOS technology. They provide advantages in stability and mobility for information transmission. The development of these gates could lead to ultra-low-power computing solutions in the post-Moore era.
Skyrmions, Logic Gates, Low-Power Computing, Neuromorphic Computing
Publication
Correlation-based Hawkes Aggregation of Neurons with bio-Inspiration
Published on 2026-01-01 by Sophie Jaffard, Samuel Vaiter, Patricia Reynaud-Bouret @JMLR
Abstract: The present work aims at proving mathematically that a neural network inspired by biology can learn a classification task thanks to local transformations only. In this purpose, we propose a spiking neural network named CHANI (Correlation-based Hawkes Aggregation of Neurons with bio-Inspiration), whose neurons activity is modeled by Hawkes processes. Synaptic weights are updated thanks to an expert aggregation algorithm, providing a local and simple learning rule. We were able to prove that our n[...]
Our summary: The study presents CHANI, a spiking neural network utilizing Hawkes processes for classification tasks. It demonstrates that local transformations allow the network to learn effectively and form neuronal assemblies. The findings provide a theoretical framework for understanding local learning rules in biologically inspired networks.
Hawkes processes, spiking neural networks, local transformations, biological inspiration
Publication
A Framework for Optimizing LLM-Oriented Architectures
Published on 2025-12-25 by Sabya Shtaiwi, Dheya Mustafa @MDPI
Abstract: With the increasing computational demands of large language models (LLMs), there is a pressing need for more specialized hardware architectures capable of supporting their dynamic and memory-intensive workloads. This paper examines recent studies on hardware acceleration for AI, focusing on three critical aspects: energy efficiency, architectural adaptability, and runtime security. While notable advancements have been made in accelerating convolutional and deep neural networks using ASICs, FPGAs[...]
Our summary: This paper discusses the need for specialized hardware architectures to support large language models. It identifies limitations in current solutions regarding reconfigurability and real-time security. A novel framework is proposed, emphasizing modular adaptivity, memory-centric processing, and security-by-design principles.
hardware architectures, large language models, energy efficiency, runtime security
Publication
