相关论文: SOI: Scaling Down Computational Complexity by Esti…

Generative Artificial Intelligence (AI) has become incredibly popular in recent years, and the significance of traditional accelerators in dealing with large-scale parameters is urgent. With the diffusion model's parallel structure, the…

The popularity and widespread use of pruning and quantization is driven by the severe resource constraints of deploying deep neural networks to environments with strict latency, memory and energy requirements. These techniques achieve high…

Computed tomography (CT) is a widely-used imaging technology that assists clinical decision-making with high-quality human body representations. To reduce the radiation dose posed by CT, sparse-view and limited-angle CT are developed with…

Neuromorphic hardware platforms, such as Intel's Loihi chip, support the implementation of Spiking Neural Networks (SNNs) as an energy-efficient alternative to Artificial Neural Networks (ANNs). SNNs are networks of neurons with internal…

In real-world applications, observations are often constrained to a small fraction of a system. Such spatial subsampling can be caused by the inaccessibility or the sheer size of the system, and cannot be overcome by longer sampling.…

With edge intelligence, AI models are increasingly pushed to the edge to serve ubiquitous users. However, due to the drift of model, data, and task, AI model deployed at the edge suffers from degraded accuracy in the inference serving…

Mobile platforms must satisfy the contradictory requirements of fast response time and minimum energy consumption as a function of dynamically changing applications. To address this need, system-on-chips (SoC) that are at the heart of these…

The increasing deployment of end use power resources in distribution systems created active distribution systems. Uncontrolled active distribution systems exhibit wide variations of voltage and loading throughout the day as some of these…

Spiking Neural Networks (SNNs), as an emerging biologically inspired computational model, demonstrate significant energy efficiency advantages due to their event-driven information processing mechanism. Compared to traditional Artificial…

We investigate the supervised machine learning of few interacting bosons in optical speckle disorder via artificial neural networks. The learning curve shows an approximately universal power-law scaling for different particle numbers and…

This paper introduces a theoretical framework for a Transformer-augmented, sectional Mixture-of-Experts (MoE) architecture that aims to enhance computational efficiency while preserving model scalability. Unlike conventional MoE models,…

Large language models (LLMs) demonstrate strong language generation capabilities but often struggle with structured reasoning, leading to inconsistent or suboptimal problem-solving. To mitigate this limitation, Guilford's Structure of…

State estimation is key to both analyzing physical mechanisms and enabling real-time control of fluid flows. A common estimation approach is to relate sensor measurements to a reduced state governed by a reduced-order model (ROM). (When…

Online prediction methods are typically presented as serial algorithms running on a single processor. However, in the age of web-scale prediction problems, it is increasingly common to encounter situations where a single processor cannot…

Spiking Neural Networks (SNNs) provide an efficient computational mechanism for temporal signal processing, especially when coupled with low-power SNN inference ASICs. SNNs have been historically difficult to configure, lacking a general…

The advancement of deep learning has led to the emergence of Mixture-of-Experts (MoEs) models, known for their dynamic allocation of computational resources based on input. Despite their promise, MoEs face challenges, particularly in terms…

A comprehensive approach for real-time computations using a database of parameterized linear reduced-order models (ROMs) is proposed. The method proceeds by sampling offline ROMs for specific values of the parameters and interpolating…

As large-scale AI models expand, training becomes costlier and sustaining progress grows harder. Classical scaling laws (e.g., Kaplan et al. (2020), Hoffmann et al. (2022)) predict training loss from a static compute budget yet neglect time…

The search for new, application-specific quantum computers designed to outperform any classical computer is driven by the ending of Moore's law and the quantum advantages potentially obtainable. Photonic networks are promising examples,…

Advances in multicore processors and accelerators have opened the flood gates to greater exploration and application of machine learning techniques to a variety of applications. These advances, along with breakdowns of several trends…