23 papers · ranked by Valyu relevance
Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer + 17 more
'Gregory Chanan' 'Trevor Killeen' 'Zeming Lin' 'Natalia Gimelshein' 'Luca Antiga' 'Alban Desmaison' 'Andreas Köpf' 'Edward Z. Yang' 'Zach DeVito' 'Martin Raison' 'Alykhan Tejani' 'Sasank Chilamkurthy' 'Benoit Steiner' 'Lu Fang' 'Junjie Bai' 'Soumith Chintala'] Deep learning frameworks have often focused on either…
Aws Ismail Abu Eid, Salameh A. Mjlae, Suzie Yaseen Rababa’h, Ahmed Hammad + 1 more
This comprehensive benchmarking study explores the performance of three prominent machine learning libraries: PyTorch, Keras with TensorFlow backend, and Scikit-learn with the same criteria, software, and hardware. The evaluation encompasses two diverse datasets, “student performance” and “College Attending Plan…
Matteo De Matola, Giorgio Arcara
Convolutional neural networks (CNNs) are a class of artificial neural networks (ANNs). Since the early 2010s, they have been widely adopted as models of primate vision and classifiers of neuroimaging data, becoming relevant for a wealth of neuroscientific fields. However, the majority of neuroscience researchers come…
Yueming Hao, Xu Zhao, Bin Bao, David Berard + 3 more
'Adnan Aziz' 'Xu Liu'] Deep learning (DL) has been a revolutionary technique in various domains. To facilitate the model development and deployment, many deep learning frameworks are proposed, among which Py-Torch is one of the most popular solutions. The performance of ecosystem around PyTorch is critically important…
Abhishek Ghosh, Ajay Nayak, Ashish Panwar, Arkaprava Basu
CUDA Graphs — a recent hardware feature introduced for NVIDIA GPUs — aim to reduce CPU launch overhead by capturing and launching a series of GPU tasks (kernels) as a DAG. However, deploying CUDA Graphs faces several challenges today due to the static structure of a graph. It also incurs performance overhead due to…
Zakariya Ba Alawi
—This paper presents a comprehensive comparative survey of TensorFlow and PyTorch, the two leading deep learning frameworks, focusing on their usability, performance, and deployment trade-offs. We review each framework's programming paradigm and developer experience, contrasting TensorFlow's graph-based (now optionally…
JohnMark Taylor, Nikolaus Kriegeskorte
Deep neural network models (DNNs) are essential to modern AI and provide powerful models of information processing in biological neural networks. Researchers in both neuroscience and engineering are pursuing a better understanding of the internal representations and operations that undergird the successes and failures…
JohnMark Taylor, Nikolaus Kriegeskorte
Deep neural network models (DNNs) are essential to modern AI and provide powerful models of information processing in biological neural networks. Researchers in both neuroscience and engineering are pursuing a better understanding of the internal representations and operations that undergird the successes and failures…
JohnMark Taylor, Nikolaus Kriegeskorte
Deep neural network models (DNNs) are essential to modern AI and provide powerful models of information processing in biological neural networks. Researchers in both neuroscience and engineering are pursuing a better understanding of the internal representations and operations that undergird the successes and failures…
Liang Liang, Minliang Liu, John Elefteriades, Wei Sun
Finite-element analysis (FEA) is widely used as a standard tool for stress and deformation analysis of solid structures, including human tissues and organs. For instance, FEA can be applied at a patient-specific level to assist in medical diagnosis and treatment planning, such as risk assessment of thoracic aortic…
Jacob Huth, Timothée Masquelier, Angelo Arleo
We developed Convis, a Python simulation toolbox for large scale neural populations which offers arbitrary receptive fields by 3D convolutions executed on a graphics card. The resulting software proves to be flexible and easily extensible in Python, while building on the PyTorch library (The Pytorch Project, [32])…
Gabriele Orlando, Luis Serrano, Joost Schymkowitz, Frederic Rousseau + 1 more
AlphaFold () started a revolution in computational biology by allowing researchers to access reliable structural information for virtually any natural protein. The general protein folding problem, however, is still far from being solved: while we can predict the conformations of well-studied proteins, inferring the…
Haotian Li
Machine learning and deep learning are novel and trending approaches to solving real-world scientific problems. Graph machine learning is dedicated to performing learning methods, such as graph neural networks, on non-Euclidean data such as graphs. Molecules, with their natural graph structures, could be analyzed by…
Zachary DeVito, Jason Ansel, Will Constable, Michael Suo + 2 more
'Ailing Zhang' 'Kim Hazelwood'] Python has become the de-facto language for training deep neural networks, coupling a large suite of scientific computing libraries with efficient libraries for tensor computation such as PyTorch (Paszke et al., 2019) or TensorFlow (Abadi et al., 2016). However, when models are used for…
Authors not listed
In this work we introduce TorchANI 2.0, a significantly improved version of the free and open source TorchANI software package for training and evaluation of ANI (ANAKIN-ME) deep learning models. TorchANI 2.0 builds upon the foundation of its predecessor, while addressing its limitations and introducing new features.…
Richard Gast, Thomas R. Knösche, Ann Kennedy, Daniele Marinazzo
The mathematical study of real-world dynamical systems relies on models composed of differential equations. Numerical methods for solving and analyzing differential equation systems are essential when complex biological problems have to be studied, such as the spreading of a virus, the evolution of competing species in…
Hassam Tahir, Eun-Sung Jung, Petros Daras
This paper delves into image detection based on distributed deep-learning techniques for intelligent traffic systems or self-driving cars. The accuracy and precision of neural networks deployed on edge devices (e.g., CCTV (closed-circuit television) for road surveillance) with small datasets may be compromised, leading…
Piero Gasparotto, Luis Barba, Hans-Christian Stadler, Greta Assmann + 5 more
Serial Crystallography (SX) involves the processing of thousands of diffraction patterns coming from crystals in random orientations. To compile a complete dataset, these patterns must be indexed (i.e., determine orientation), integrated, and merged. We introduce the TORO (TOrch-powered Robust Optimization) Indexer, a…
Nathan Frey, Ryan Soklaski, Simon Axelrod, Siddharth Samsi + 3 more
Massive scale, both in terms of data availability and computation, enables significant breakthroughs in key application areas of deep learning such as natural language processing (NLP) and computer vision. There is emerging evidence that scale may be a key ingredient in scientific deep learning, but the importance of…
Esben Bjerrum, Tobias Rastemo, Ross Irwin, Christos Kannas + 1 more
Recent years have seen a large interest in using the Simplified Molecular Input Line Entry System (SMILES) chemical language as input for deep learning architectures solving chemical tasks. Many successful applications have been demonstrated within de novo molecular design, quantitative structure-activity relationship…
Authors not listed
Obtaining quantitative information about residence time behavior (i.e., the residence time distribution function) in realistic experimental systems is oftentimes experimentally challenging and numerically complex. The conventional way is to conduct very simple pulse or step tracer experiments or construct elaborate…
Authors not listed
Modeling of chemical reactions is essential for understanding kinetic mechanisms and predicting possible outcomes of reacting systems. Quantum mechanical calculations are accurate but often prohibitively expensive. Deep learning has emerged as a faster alternative, but progress is slowed by a fragmented software…
Authors not listed
Accurate prediction of redox potentials of iron (Fe) complexes, in tandem with uncertainty quantification, is essential to advance technologies related to electro-deposition and energy storage by enabling reliable modeling, guiding experimental design, and improving the efficiency of material discovery. Since…