中文
相关论文

相关论文: When Routers, Switches and Interconnects Compute: …

200 篇论文

Neuromorphic computing is a non-von Neumann computing paradigm that performs computation by emulating the human brain. Neuromorphic systems are extremely energy-efficient and known to consume thousands of times less power than CPUs and…

神经与进化计算 · 计算机科学 2021-04-30 Prasanna Date , Catherine Schuman , Bill Kay , Thomas Potok

Energy efficiency and low latency are crucial requirements for designing wearable AI-empowered human activity recognition systems, due to the hard constraints of battery operations and closed-loop feedback. While neural network models have…

神经与进化计算 · 计算机科学 2023-08-03 Sizhen Bian , Michele Magno

The rapid growth of data-intensive applications such as generative AI, scientific simulations, and large-scale analytics is driving modern supercomputers and data centers toward increasingly heterogeneous and tightly integrated…

A striking difference between brain-inspired neuromorphic processors and current von Neumann processors architectures is the way in which memory and processing is organized. As Information and Communication Technologies continue to address…

神经与进化计算 · 计算机科学 2017-11-08 Giacomo Indiveri , Shih-Chii Liu

Spiking neural networks play an important role in brain-like neuromorphic computations and in studying working mechanisms of neural circuits. One drawback of training a large scale spiking neural network is that updating all weights is…

神经元与认知 · 定量生物学 2024-08-15 Zhanghan Lin , Haiping Huang

Real-time AI services increasingly operate across the device-edge-cloud continuum, where autonomous AI agents generate latency-sensitive workloads, orchestrate multi-stage processing pipelines, and compete for shared resources under policy…

Diverse scientific and engineering research areas deal with discrete, time-stamped changes in large systems of interacting delay differential equations. Simulating such complex systems at scale on high-performance computing clusters demands…

Artificial intelligence (AI) has revolutionized software development, shifting from task-specific codes (Software 1.0) to neural network-based approaches (Software 2.0). However, applying this transition in engineering software presents…

The development of large-scale artificial intelligence (AI) models is influencing neuroscience research by enabling end-to-end learning from raw brain signals and neural data. In this paper, we review applications of large-scale AI models…

There are increasing number of works addressing the design challenges of fast, scalable solutions for the growing number of new type of applications. Recently, many of the solutions aimed at improving processing element capabilities to…

硬件体系结构 · 计算机科学 2019-12-16 Somnath Mazumdar , Alberto Scionti

While spike timing has been shown to carry detailed stimulus information at the sensory periphery, its possible role in network computation is less clear. Most models of computation by neural networks are based on population firing rates.…

神经元与认知 · 定量生物学 2015-07-17 Michael A. Schwemmer , Adrienne L. Fairhall , Sophie Denéve , Eric T. Shea-Brown

Deciphering the underpinnings of the dynamical processes leading to information transmission, processing, and storing in the brain is a crucial challenge in neuroscience. An inspiring but speculative theoretical idea is that such dynamics…

统计力学 · 物理学 2023-07-21 Guillermo B. Morales , Serena Di Santo , Miguel A. Muñoz

The transition from standard generative AI to \emph{reasoning-centric architectures}, exemplified by models capable of extensive Chain-of-Thought~(CoT) processing, marks a fundamental paradigm shift in system requirements. Unlike…

分布式、并行与集群计算 · 计算机科学 2026-05-20 Moiz Arif , Avinash Maurya , Sudharshan Vazhkudai , Bogdan Nicolae

Ubiquitous artificial intelligence (AI) is considered one of the key services in 6G systems. AI services typically rely on deep neural network (DNN) requiring heavy computation. Hence, in order to support ubiquitous AI, it is crucial to…

网络与互联网体系结构 · 计算机科学 2022-07-27 Sehun Jung , Hyang-Won Lee

Efficient deployment of neural networks on resource-constrained hardware demands optimal use of on-chip memory. In event-based processors, this is particularly critical for routing architectures, where substantial memory is dedicated to…

新兴技术 · 计算机科学 2024-12-03 Jimmy Weber , Theo Ballet , Melika Payvand

Deep learning's success comes with growing energy demands, raising concerns about the long-term sustainability of the field. Spiking neural networks, inspired by biological neurons, offer a promising alternative with potential computational…

神经与进化计算 · 计算机科学 2025-03-05 Adalbert Fono , Manjot Singh , Ernesto Araya , Philipp C. Petersen , Holger Boche , Gitta Kutyniok

The time required for training the neural networks increases with size, complexity, and depth. Training model parameters by backpropagation inherently creates feedback loops. These loops hinder efficient pipelining and scheduling of the…

分布式、并行与集群计算 · 计算机科学 2021-12-30 Nanda K. Unnikrishnan , Keshab K. Parhi

Today's systems are overwhelmingly designed to move data to computation. This design choice goes directly against at least three key trends in systems that cause performance, scalability and energy bottlenecks: (1) data access from memory…

硬件体系结构 · 计算机科学 2019-03-12 Onur Mutlu , Saugata Ghose , Juan Gómez-Luna , Rachata Ausavarungnirun

Large artificial intelligence (AI) models exhibit remarkable capabilities in various application scenarios, but deploying them at the network edge poses significant challenges due to issues such as data privacy, computational resources, and…

人工智能 · 计算机科学 2025-03-28 Wanli Ni , Haofeng Sun , Huiqing Ao , Hui Tian

Executing Spiking Neural Networks (SNNs) on neuromorphic hardware poses the problem of mapping neurons to cores. SNNs operate by propagating spikes between neurons that form a graph through synapses. Neuromorphic hardware mimics them…

硬件体系结构 · 计算机科学 2026-04-22 Marco Ronzani , Cristina Silvano