Related papers: RoseNNa: A performant, portable library for neural…

Ultra-large make-on-demand compound libraries now contain billions of readily available compounds. This represents a golden opportunity for in-silico drug discovery. One challenge, however, is the time and computational cost of an…

Modern information technology services largely depend on cloud infrastructures to provide their services. These cloud infrastructures are built on top of datacenter networks (DCNs) constructed with high-speed links, fast switching gear, and…

Graph neural network (GNN) potentials such as SchNet improve the accuracy and transferability of molecular dynamics (MD) simulation by learning many-body interactions, but remain slower than classical force fields due to fragmented kernels…

This paper is concerned with the development of a hybrid data-driven technique for unsteady fluid-structure interaction systems. The proposed data-driven technique combines the deep learning framework with a projection-based low-order…

Recurrent neural networks (RNNs), especially long short-term memory (LSTM) RNNs, are effective network for sequential task like speech recognition. Deeper LSTM models perform well on large vocabulary continuous speech recognition, because…

Quantum computational fluid dynamics (QCFD) offers a promising alternative to classical computational fluid dynamics (CFD) by leveraging quantum algorithms for higher efficiency. This paper introduces a comprehensive QCFD method, including…

As deep learning models scale, their training cost has surged significantly. Due to both hardware advancements and limitations in current software stacks, the need for data efficiency has risen. Data efficiency refers to the effective…

In an ever expanding set of research and application areas, deep neural networks (DNNs) set the bar for algorithm performance. However, depending upon additional constraints such as processing power and execution time limits, or…

Physics-informed deep learning has drawn tremendous interest in recent years to solve computational physics problems, whose basic concept is to embed physical laws to constrain/inform neural networks, with the need of less data for training…

Deep Reinforcement Learning (RL) can yield capable agents and control policies in several domains but is commonly plagued by prohibitively long training times. Additionally, in the case of continuous control problems, the applicability of…

This paper introduces a tensor neural network (TNN) to address nonparametric regression problems, leveraging its distinct sub-network structure to effectively facilitate variable separation and enhance the approximation of complex,…

Simulating fluid flow around arbitrary shapes is key to solving various engineering problems. However, simulating flow physics across complex geometries remains numerically challenging and computationally resource-intensive, particularly…

This paper presents a new Computational Fluid Dynamics database, developed at ONERA, to support the advancement of machine learning techniques for aerodynamic field prediction. It contains 468 Reynolds-Averaged Navier-Stokes simulations…

Physics-informed neural networks (PINNs) have shown remarkable prospects in solving partial differential equations (PDEs) involving fluid mechanics. However, the method has so far succeeded only in inviscid flows and incompressible viscous…

Interpretability of Deep Neural Networks (DNNs) is a growing field driven by the study of vision and language models. Yet, some use cases, like image captioning, or domains like Deep Reinforcement Learning (DRL), require complex modelling,…

Recursive Neural Networks (RvNNs), which compose sequences according to their underlying hierarchical syntactic structure, have performed well in several natural language processing tasks compared to similar models without structural…

In this paper, we propose an elegant solution that is directly addressing the bottlenecks of the traditional deep learning approaches and offers a clearly explainable internal architecture that can outperform the existing methods, requires…

While there is a large body of research on efficient processing of deep neural networks (DNNs), ultra-low-latency realization of these models for applications with stringent, sub-microsecond latency requirements continues to be an…

To improve the throughput and energy efficiency of Deep Neural Networks (DNNs) on customized hardware, lightweight neural networks constrain the weights of DNNs to be a limited combination (denoted as $k\in\{1,2\}$) of powers of 2. In such…

Time series classification underpins applications such as human activity recognition, healthcare monitoring, and gesture detection in the IoT domain. Tiny Machine Learning enables models to run directly on low-power microcontroller units,…