Neuromorphic Readout for Hadron Calorimeters DOI Creative Commons

Enrico Lupi,

Abhishek,

Max Aehle

et al.

Particles, Journal Year: 2025, Volume and Issue: 8(2), P. 52 - 52

Published: May 1, 2025

We simulate hadrons impinging on a homogeneous lead tungstate (PbWO4) calorimeter using GEANT4 software to investigate how the resulting light yield and its temporal structure, as detected by an array of light-sensitive sensors, can be processed neuromorphic computing system. Our model encodes photon distributions spike trains employs fully connected spiking neural network estimate total deposited energy, well position spatial distribution emissions within sensitive material. The extracted primitives offer valuable topological information about shower development in material, achieved without requiring segmentation active medium. A potential nanophotonic implementation III-V semiconductor nanowires is discussed. It both fast energy efficient.

Language: Английский

DeepSeek or ChatGPT: Can brain‐computer interfaces/brain‐inspired computing achieve leapfrog development with large AI models? DOI Creative Commons
Long Bai, Shugeng Chen, Peng Wang

et al.

Brain‐X, Journal Year: 2025, Volume and Issue: 3(1)

Published: March 1, 2025

Language: Английский

Citations

1
Recent Strategies in Channel Modulation for High-Performance Neuromorphic Computing Based on Electrolyte-Gated Organic Synaptic Transistors DOI
Dongyeong Jeong,

Seokkyu Kim,

Maozhong An

et al.

Korean Journal of Chemical Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: April 3, 2025

Language: Английский

Citations

0
Neuromorphic algorithms for brain implants: a review DOI Creative Commons

Wiktoria Agata Pawlak,

Newton Howard

Frontiers in Neuroscience, Journal Year: 2025, Volume and Issue: 19

Published: April 11, 2025

Neuromorphic computing technologies are about to change modern computing, yet most work thus far has emphasized hardware development. This review focuses on the latest progress in algorithmic advances specifically for potential use brain implants. We discuss current algorithms and emerging neurocomputational models that, when implemented neuromorphic hardware, could match or surpass traditional methods efficiency. Our aim is inspire creation deployment of that not only enhance computational performance implants but also serve broader fields like medical diagnostics robotics inspiring next generations neural

Language: Английский

Citations

0
Method of high-level microarchitecture design of neuromorphic processors based on explicit separation of computations from transaction flow DOI

Ivan Lukashov,

A. A. Antonov, Pavel Kustarev

et al.

Izvestiâ vysših učebnyh zavedenij Priborostroenie, Journal Year: 2025, Volume and Issue: 68(3), P. 228 - 238

Published: April 18, 2025

An original method and a prototype of the software toolbox for designing neuromorphic processors are presented. The is based on high-level description hardware with explicit (at source code level) allocation pipeline transaction flows circulating inside structure separation computations performed in this case from logic dynamic scheduling flow control. This approach allows flexible combination data processing algorithms up-to-date mechanisms improving performance energy consumption microarchitecture, effective sharing responsibilities development complex hardware, reuse auto-configurable microarchitectural structures. A formalization concept (in given context), design route transactions, an algorithm synthesizing RTL “transactional” descriptions proposed. built framework software-controlled generation described. application proposed CAD components demonstrated using example processor executing models fully connected pulse neural networks. confirms achievability competitive characteristics significant improvement project manageability, reuse, reduction number errors overall labor intensity design.

Language: Английский

Citations

0
Ion–Electron Interactions in 2D Nanomaterials-Based Artificial Synapses for Neuromorphic Applications DOI
Tingting Mei, Fandi Chen,

Tianxu Huang

et al.

ACS Nano, Journal Year: 2025, Volume and Issue: unknown

Published: April 29, 2025

With the increasing limitations of conventional computing techniques, particularly von Neumann bottleneck, brain's seamless integration memory and processing through synapses offers a valuable model for technological innovation. Inspired by biological synapse facilitating adaptive, low-power computation modulating signal transmission via ionic conduction, iontronic synaptic devices have emerged as one most promising candidates neuromorphic computing. Meanwhile, atomic-scale thickness tunable electronic properties van der Waals two-dimensional (2D) materials enable possibility designing highly integrated, energy-efficient that closely replicate plasticity. This review comprehensively analyzes advancements in based on 2D materials, focusing electron-ion interactions both transistors memristors. The challenges material stability, scalability, device are evaluated, along with potential solutions future research directions. By highlighting these developments, this insights into advancing systems.

Language: Английский

Citations

0
Neuromorphic Readout for Hadron Calorimeters DOI Creative Commons

Enrico Lupi,

Abhishek,

Max Aehle

et al.

Particles, Journal Year: 2025, Volume and Issue: 8(2), P. 52 - 52

Published: May 1, 2025

We simulate hadrons impinging on a homogeneous lead tungstate (PbWO4) calorimeter using GEANT4 software to investigate how the resulting light yield and its temporal structure, as detected by an array of light-sensitive sensors, can be processed neuromorphic computing system. Our model encodes photon distributions spike trains employs fully connected spiking neural network estimate total deposited energy, well position spatial distribution emissions within sensitive material. The extracted primitives offer valuable topological information about shower development in material, achieved without requiring segmentation active medium. A potential nanophotonic implementation III-V semiconductor nanowires is discussed. It both fast energy efficient.

Language: Английский

Citations

0