相关论文: A language-inspired machine learning approach for …

Deep reinforcement learning (RL) is increasingly deployed in resource-constrained environments, yet the go-to function approximators - multilayer perceptrons (MLPs) - are often parameter-inefficient due to an imperfect inductive bias for…

Natural Language Processing (NLP) is widely used in fields like machine translation and sentiment analysis. However, traditional NLP models struggle with accuracy and efficiency. This paper introduces Deep Convolutional Neural Networks…

The recent emergence of new algorithms for permuting models into functionally equivalent regions of the solution space has shed some light on the complexity of error surfaces, and some promising properties like mode connectivity. However,…

Physics-Informed Neural Networks (PINNs) combine deep learning with physical constraints for solving partial differential equations (PDEs), and are widely applied in fluid mechanics, heat transfer, and solid mechanics. However, PINN…

The evolving capabilities of large language models are accompanied by growing sizes and deployment costs, necessitating effective inference optimisation techniques. We propose a novel pruning method utilising centrality measures from graph…

Semantic Communication (SC) is an emerging technology aiming to surpass the Shannon limit. Traditional SC strategies often minimize signal distortion between the original and reconstructed data, neglecting perceptual quality, especially in…

The aim of this paper is to introduce a Mapping-based Hard-constrained Physics-Informed Neural Network (MH-PINN) for efficiently and accurately solving unbounded wave problems. First, we propose a coordinate mapping technique that…

The gravitational collapse of a massless scalar field remains a demanding benchmark for numerical methods in numerical relativity, as it exhibits critical behavior at the boundary between dispersion and black hole formation. In this work we…

Active learning (AL) algorithms aim to identify an optimal subset of data for annotation, such that deep neural networks (DNN) can achieve better performance when trained on this labeled subset. AL is especially impactful in industrial…

DNNs are susceptible to defects like backdoors, adversarial attacks, and unfairness, undermining their reliability. Existing approaches mainly involve retraining, optimization, constraint-solving, or search algorithms. However, most methods…

Addressing the issues of hallucinations and outdated knowledge in large language models is critical for their reliable application. Model Editing presents a promising avenue for mitigating these challenges in a cost-effective manner.…

Active learning methods for neural networks are usually based on greedy criteria which ultimately give a single new design point for the evaluation. Such an approach requires either some heuristics to sample a batch of design points at one…

Compressed sensing (CS) is a promising tool for reducing sampling costs. Current deep neural network (NN)-based CS methods face the challenges of collecting labeled measurement-ground truth (GT) data and generalizing to real applications.…

In this work, we study the problem of non-blind image deconvolution and propose a novel recurrent network architecture that leads to very competitive restoration results of high image quality. Motivated by the computational efficiency and…

Curriculum learning is a bio-inspired training technique that is widely adopted to machine learning for improved optimization and better training of neural networks regarding the convergence rate or obtained accuracy. The main concept in…

Skeleton data is of low dimension. However, there is a trend of using very deep and complicated feedforward neural networks to model the skeleton sequence without considering the complexity in recent year. In this paper, a simple yet…

The success of convolutional neural networks (CNNs) in various applications is accompanied by a significant increase in computation and parameter storage costs. Recent efforts to reduce these overheads involve pruning and compressing the…

This paper deals with the following important research question. Traditionally, the neural network employs non-linear activation functions concatenated with linear operators to approximate a given physical phenomenon. They "fill the space"…

We build a rigorous bridge between deep networks (DNs) and approximation theory via spline functions and operators. Our key result is that a large class of DNs can be written as a composition of max-affine spline operators (MASOs), which…

Sparsity-based methods have a long history in the field of signal processing and have been successfully applied to various image reconstruction problems. The involved sparsifying transformations or dictionaries are typically either…