Related papers: ML-misfit: Learning a robust misfit function for f…

Seismic inversion helps geophysicists build accurate reservoir models for exploration and production purposes. Deep learning-based seismic inversion works by training a neural network to learn a mapping from seismic data to rock properties…

The success of deep learning has inspired recent interests in applying neural networks in statistical inference. In this paper, we investigate the use of deep neural networks for nonparametric regression with measurement errors. We propose…

Equipping a deep model the abaility of few-shot learning, i.e., learning quickly from only few examples, is a core challenge for artificial intelligence. Gradient-based meta-learning approaches effectively address the challenge by learning…

This study takes advantage of recent advances in machine learning to establish a physics-based data analytic platform for distributed reconstruction of mechanical properties in layered components from full waveform data. In this vein, two…

A meta-model is trained on a distribution of similar tasks such that it learns an algorithm that can quickly adapt to a novel task with only a handful of labeled examples. Most of current meta-learning methods assume that the meta-training…

The dynamic allocation of spectrum in 5G / 6G networks is critical to efficient resource utilization. However, applying traditional deep reinforcement learning (DRL) is often infeasible due to its immense sample complexity and the safety…

Multi-output is essential in machine learning that it might suffer from nonconforming residual distributions, i.e., the multi-output residual distributions are not conforming to the expected distribution. In this paper, we propose "Wrapped…

Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms are known to be sensitive to the task distribution…

A machine learning (ML) method is generalizable if it can make predictions on inputs which differ from the training dataset. For predictions of wave-induced ship responses, generalizability is an important consideration if ML methods are to…

We propose a novel learning framework using neural mean-field (NMF) dynamics for inference and estimation problems on heterogeneous diffusion networks. Our new framework leverages the Mori-Zwanzig formalism to obtain an exact evolution…

Recent advances in deep learning from probability distributions successfully achieve classification or regression from distribution samples, thus invariant under permutation of the samples. The first contribution of the paper is to extend…

Wavelet transformation stands as a cornerstone in modern data analysis and signal processing. Its mathematical essence is an invertible transformation that discerns slow patterns from fast ones in the frequency domain. Such an invertible…

Neural Fields (NF) have gained prominence as a versatile framework for complex data representation. This work unveils a new problem setting termed \emph{Meta-Continual Learning of Neural Fields} (MCL-NF) and introduces a novel strategy that…

Machine learning is a powerful approach for fitting microstructural models to diffusion MRI data. Early machine learning microstructure imaging implementations trained regressors to estimate model parameters in a supervised way, using…

Traditional machine learning techniques have achieved great success in improving data-rate performance and reducing latency in millimeter wave (mmWave) communications. However, these methods still face two key challenges: (i) their reliance…

Full Waveform Inversion (FWI) is a successful and well-established inverse method for reconstructing material models from measured wave signals. In the field of seismic exploration, FWI has proven particularly successful in the…

Millimeter wave (mmWave) communication, utilizing beamforming techniques to address the inherent path loss limitation, is considered as one of the key technologies to support ever increasing high throughput and low latency demands of…

We propose a new neural sequence model training method in which the objective function is defined by $\alpha$-divergence. We demonstrate that the objective function generalizes the maximum-likelihood (ML)-based and reinforcement learning…

Employing large antenna arrays is a key characteristic of millimeter wave (mmWave) and terahertz communication systems. However, due to the adoption of fully analog or hybrid analog/digital architectures, as well as non-ideal hardware or…

Feature learning (FL), where neural networks adapt their internal representations during training, remains poorly understood. Using methods from statistical physics, we derive a tractable, self-consistent mean-field (MF) theory for the…