Related papers: Predicting Probabilities of Error to Combine Quant…

A network-based optimization approach, EEE, is proposed for the purpose of providing validation-viable state estimations to remediate the failure of pretrained models. To improve optimization efficiency and convergence, the most important…

Uncertainty quantification (UQ) in scientific machine learning is increasingly critical as neural networks are widely adopted to tackle complex problems across diverse scientific disciplines. For physics-informed neural networks (PINNs), a…

The recent advances in Deep Neural Networks (DNNs) stem from their exceptional performance across various domains. However, their inherent large size hinders deploying these networks on resource-constrained devices like edge, mobile, and…

As neural networks have begun performing increasingly critical tasks for society, ranging from driving cars to identifying candidates for drug development, the value of their ability to perform uncertainty quantification (UQ) in their…

We propose an approach for quantum amplitude estimation (QAE) designed to enhance computational efficiency while minimizing the reliance on quantum resources. Our method leverages quantum computers to generate a sequence of signals, from…

Comparing with traditional learning criteria, such as mean square error (MSE), the minimum error entropy (MEE) criterion is superior in nonlinear and non-Gaussian signal processing and machine learning. The argument of the logarithm in…

Deep learning as a means to inferencing has proliferated thanks to its versatility and ability to approach or exceed human-level accuracy. These computational models have seemingly insatiable appetites for computational resources not only…

Deep learning tools have gained tremendous attention in applied machine learning. However such tools for regression and classification do not capture model uncertainty. In comparison, Bayesian models offer a mathematically grounded…

Compressing large-scale neural networks is essential for deploying models on resource-constrained devices. Most existing methods adopt weight pruning or low-bit quantization individually, often resulting in suboptimal compression rates to…

Deployment of dynamic neural networks on edge accelerators requires careful consideration of hardware constraints beyond conventional complexity metrics such as Multiply-Accumulate operations. In Early-Exiting Neural Networks (EENN), exit…

In this work, we introduce the Quantum Adaptive Excitation Network (QAE-Net), a hybrid quantum-classical framework designed to enhance channel attention mechanisms in Convolutional Neural Networks (CNNs). QAE-Net replaces the classical…

Quantum machine learning promises great speedups over classical algorithms, but it often requires repeated computations to achieve a desired level of accuracy for its point estimates. Bayesian learning focuses more on sampling from…

Increasing the size of large language models (LLMs) has been shown to lead to better performance. However, this comes at the cost of slower and more expensive inference. Early-exiting is a promising approach for improving the efficiency of…

Self-supervised speech models have shown to be useful for various tasks, but their large size limits the use in devices with low computing power and memory. In this work, we explore early exit, an approach for reducing latency by exiting…

Quantum algorithms require accurate representations of electronic states on a quantum device, yet the approximation of electronic wave functions for strongly correlated systems remains a profound theoretical challenge, with existing methods…

Model compression is vital to the deployment of deep learning on edge devices. Low precision representations, achieved via quantization of weights and activations, can reduce inference time and memory requirements. However, quantifying and…

Deep neural networks, while achieving remarkable success across diverse tasks, demand significant resources, including computation, GPU memory, bandwidth, storage, and energy. Network quantization, as a standard compression and acceleration…

Both performance and efficiency are crucial factors for sequence labeling tasks in many real-world scenarios. Although the pre-trained models (PTMs) have significantly improved the performance of various sequence labeling tasks, their…

Edge machine learning can deliver low-latency and private artificial intelligent (AI) services for mobile devices by leveraging computation and storage resources at the network edge. This paper presents an energy-efficient edge processing…

Quantization is essential for reducing the computational cost and memory usage of deep neural networks, enabling efficient inference on low-precision hardware. Despite the growing adoption of uniform and floating-point quantization schemes,…