1.2k citations
- University of California San DiegoUS90 papers
- Centre National de la Recherche ScientifiqueFR12 papers
- University of California, BerkeleyUS12 papers
- Harvard University PressUS8 papers
- Stockholm UniversitySE8 papers
- University of Illinois Urbana-ChampaignUS8 papers
- Washington State UniversityUS8 papers
- Cardiff UniversityGB7 papers
- Harvard UniversityUS7 papers
- Institut National de Physique Nucléaire et de Physique des ParticulesFR7 papers
- Universität HamburgDE7 papers
- Université Paris CitéFR7 papers
9 papers · 1 filter
Knowledge-guided generative surrogate modeling for high-dimensional design optimization under scarce data
Bingran Wang, Seongha Jeong, Sebastiaan P. C. van Schie +3
Surrogate models are widely used in mechanical design and manufacturing process optimization, where high-fidelity computational models may be unavailable or prohibitively expensive…
Explaining GNN Explanations with Edge Gradients
Jesse He, Akbar Rafiey, Gal Mishne +1
In recent years, the remarkable success of graph neural networks (GNNs) on graph-structured data has prompted a surge of methods for explaining GNN predictions. However, the state-…
Theoretical Guarantees for Low-Rank Compression of Deep Neural Networks
Shihao Zhang, Rayan Saab
Deep neural networks have achieved state-of-the-art performance across numerous applications, but their high memory and computational demands present significant challenges, partic…
Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
Xuan Zhang, Limei Wang, Jacob Helwig +60
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences. Today, AI has started to advance natural sciences by improving, accelerating…
IKD+: Reliable Low Complexity Deep Models For Retinopathy Classification
Shreyas Bhat Brahmavar, Rohit Rajesh, Tirtharaj Dash +6
Deep neural network (DNN) models for retinopathy have estimated predictive accuracies in the mid-to-high 90%. However, the following aspects remain unaddressed: State-of-the-art mo…
A Theoretical Perspective on Hyperdimensional Computing
Anthony Thomas, Sanjoy Dasgupta, Tajana Rosing
Hyperdimensional (HD) computing is a set of neurally inspired methods for obtaining high-dimensional, low-precision, distributed representations of data. These representations can…