Related papers: FIRE: Frobenius-Isometry Reinitialization for Bala…

Thermal field reconstruction in post-exposure bake (PEB) is critical for advanced lithography, yet current physics-informed neural networks (PINNs) suffer from inconsistent accuracy due to a misalignment between geometric coordinates,…

This work presents a physics-informed neural network (PINN) based framework to model the strain-rate and temperature dependence of the deformation fields in elastic-viscoplastic solids. To avoid unbalanced back-propagated gradients during…

Neural network quantization aims to reduce the bit-widths of weights and activations, making it a critical technique for deploying deep neural networks on resource-constrained hardware. Most Quantization-Aware Training (QAT) methods rely on…

Recovering a globally accurate complex physics field from limited sensor is critical to the measurement and control in the aerospace engineering. General reconstruction methods for recovering the field, especially the deep learning with…

In various data settings, it is necessary to compare observations from disparate data sources. We assume the data is in the dissimilarity representation and investigate a joint embedding method that results in a commensurate representation…

As a strategy for sustainability of deep learning, reusing an existing model by retraining it rather than training a new model from scratch is critical. In this paper, we propose REpresentation Shift QUantifying Estimator (RESQUE), a…

Neural networks have emerged as powerful surrogates for solving partial differential equations (PDEs), offering significant computational speedups over traditional methods. However, these models suffer from a critical limitation: error…

Humanoid and legged robots interact with the environment through intermittent contacts, making accurate motion estimation fundamentally dependent on reasoning about contact dynamics. However, standard sensing pipelines-whether based on…

Transformer-based large-scale pre-trained models achieve great success. Fine-tuning is the standard practice for leveraging these models in downstream tasks. Among the fine-tuning methods, adapter-tuning provides a parameter-efficient…

For single-carrier systems with frequency domain equalization, decision feedback equalization (DFE) performs better than linear equalization and has much lower computational complexity than sequence maximum likelihood detection. The main…

Federated edge learning (FEEL) is a promising distributed learning technique for next-generation wireless networks. FEEL preserves the user's privacy, reduces the communication costs, and exploits the unprecedented capabilities of edge…

Dark energy can modify the dynamics of dark matter if there exists a direct interaction between them. Thus a measurement of the structure growth, e.g., redshift-space distortions (RSD), can provide a powerful tool to constrain the…

We present FIRE, Fast Interpretable Rule Extraction, an optimization-based framework to extract a small but useful collection of decision rules from tree ensembles. FIRE selects sparse representative subsets of rules from tree ensembles,…

Federated edge learning (FEEL) provides a promising foundation for edge artificial intelligence (AI) by enabling collaborative model training while preserving data privacy. However, limited and heterogeneous local datasets, as well as…

Gradient sparsification, while mitigating communication bottlenecks in Federated Learning (FL), fundamentally alters the geometric landscape of model updates. We reveal that the resultant high-dimensional orthogonality renders traditional…

Physics-informed neural networks (PINNs) have recently emerged as an alternative way of solving partial differential equations (PDEs) without the need of building elaborate grids, instead, using a straightforward implementation. In…

We propose a new framework for processing Fringe Patterns (FP). Our novel approach builds upon the hypothesis that the denoising and normalisation of FPs can be learned by a deep neural network if enough pairs of corrupted and ideal FPs are…

The proper initialization of weights is crucial for the effective training and fast convergence of deep neural networks (DNNs). Prior work in this area has mostly focused on balancing the variance among weights per layer to maintain…

Physics-Informed Neural Network (PINN) is a novel multi-task learning framework useful for solving physical problems modeled using differential equations (DEs) by integrating the knowledge of physics and known constraints into the…

Artificial neural networks have shown remarkable success in supervised learning when trained on a single task using a fixed dataset. However, when neural networks are trained on a reinforcement learning task, their ability to continue…