Related papers: A Fortran-Keras Deep Learning Bridge for Scientifi…

Introduction: Epigenomic datasets from high-throughput sequencing experiments are commonly summarized as genomic intervals. As the volume of this data grows, so does interest in analyzing it through deep learning. However, the heterogeneity…

Quantum neural networks represent a new machine learning paradigm that has recently attracted much attention due to its potential promise. Under certain conditions, these models approximate the distribution of their dataset with a truncated…

Prior-Fitted Networks (PFNs) have recently been proposed to efficiently perform tabular classification tasks. Although they achieve good performance on small datasets, they encounter limitations with larger datasets. These limitations…

The use of large pretrained neural networks to create contextualized word embeddings has drastically improved performance on several natural language processing (NLP) tasks. These computationally expensive models have begun to be applied to…

Deep learning models typically use single-precision (FP32) floating point data types for representing activations and weights, but a slew of recent research work has shown that computations with reduced-precision data types (FP16, 16-bit…

Functional brain network (FBN) modeling often relies on local pairwise interactions, whose limitation in capturing high-order dependencies is theoretically analyzed in this paper. Meanwhile, the computational burden and heuristic nature of…

Current neural networks for predictions of molecular properties use quantum chemistry only as a source of training data. This paper explores models that use quantum chemistry as an integral part of the prediction process. This is done by…

Emerging GPU architectures for high performance computing are well suited to a data-parallel programming model. This paper presents preliminary work examining a programming methodology that provides Fortran programmers with access to these…

Due to the unprecedented success of deep learning, it has become an integral component in several multimedia computing applications in todays world. Unfortunately, deep learning systems are not perfect and can fail, sometimes abruptly,…

Development of scientific software involves tradeoffs between ease of use, generality, and performance. We describe the design of a general hyperbolic PDE solver that can be operated with the convenience of MATLAB yet achieves efficiency…

For performing successful measurements within limited experimental time, efficient use of preliminary data plays a crucial role. This work shows that a simple feedforward type neural networks approach for learning preliminary experimental…

Standard kernel methods for machine learning usually struggle when dealing with large datasets. We review a recently introduced Structured Deep Kernel Network (SDKN) approach that is capable of dealing with high-dimensional and huge…

Neural networks are powerful function approximators, yet their ``black-box" nature often renders them opaque and difficult to interpret. While many post-hoc explanation methods exist, they typically fail to capture the underlying reasoning…

This work presents FG-Net, a general deep learning framework for large-scale point clouds understanding without voxelizations, which achieves accurate and real-time performance with a single NVIDIA GTX 1080 GPU. First, a novel noise and…

From AlexNet to Inception, autoencoders to diffusion models, the development of novel and powerful deep learning models and learning algorithms has proceeded at breakneck speeds. In part, we believe that rapid iteration of model…

Solving partial differential equations (PDEs) is an important yet challenging task in fluid mechanics. In this study, we embed an improved Fourier series into neural networks and propose a physics-informed Fourier basis neural network…

With the rapid development of in-depth learning, neural network and deep learning algorithms have been widely used in various fields, e.g., image, video and voice processing. However, the neural network model is getting larger and larger,…

Being able to learn from complex data with phase information is imperative for many signal processing applications. Today' s real-valued deep neural networks (DNNs) have shown efficiency in latent information analysis but fall short when…

The need for scalable and expressive models in machine learning is paramount, particularly in applications requiring both structural depth and flexibility. Traditional deep learning methods, such as multilayer perceptrons (MLP), offer depth…

Kolmogorov-Arnold networks (KANs) have attracted attention recently as an alternative to multilayer perceptrons (MLPs) for scientific machine learning. However, KANs can be expensive to train, even for relatively small networks. Inspired by…