Related papers: NeuralMag: an open-source nodal finite-difference …

Numerical simulation is indispensable in industrial design processes. It can replace expensive experiments and even reduce the need for prototypes. While products designed with the aid of numerical simulation undergo continuous improvement,…

Neural networks have revolutionized the area of artificial intelligence and introduced transformative applications to almost every scientific field and industry. However, this success comes at a great price; the energy requirements for…

Retrieval-Augmented Generation (RAG) significantly enhances the performance of large language models (LLMs) in downstream tasks by integrating external knowledge. To facilitate researchers in deploying RAG systems, various RAG toolkits have…

Brain-inspired computing - leveraging neuroscientific principles underpinning the unparalleled efficiency of the brain in solving cognitive tasks - is emerging to be a promising pathway to solve several algorithmic and computational…

We introduce torchNTK, a python library to calculate the empirical neural tangent kernel (NTK) of neural network models in the PyTorch framework. We provide an efficient method to calculate the NTK of multilayer perceptrons. We compare the…

TensorCircuit is an open source quantum circuit simulator based on tensor network contraction, designed for speed, flexibility and code efficiency. Written purely in Python, and built on top of industry-standard machine learning frameworks,…

We introduce the Neural Field Turing Machine (NFTM), a differentiable architecture that unifies symbolic computation, physical simulation, and perceptual inference within continuous spatial fields. NFTM combines a neural controller,…

We present NEP-PACK a novel open-source library for the solution of nonlinear eigenvalue problems (NEPs). The package provides a framework to represent NEPs, as well as efficient implementations of many state-of-the-art algorithms. The…

Neuromorphic computing with non-volatile memory (NVM) can significantly improve performance and lower energy consumption of machine learning tasks implemented using spike-based computations and bio-inspired learning algorithms. High…

The two main thrusts of computational science are more accurate predictions and faster calculations; to this end, the zeitgeist in molecular dynamics (MD) simulations is pursuing machine learned and data driven interatomic models, e.g.…

Neuromorphic architectures have been introduced as platforms for energy efficient spiking neural network execution. The massive parallelism offered by these architectures has also triggered interest from non-machine learning application…

Scalable and efficient numerical simulations continue to gain importance, as computation is firmly established as the third pillar of discovery, alongside theory and experiment. Meanwhile, the performance of computing hardware grows through…

Variational principles are a unifying mathematical framework across many areas of physics, yet their instruction at the undergraduate level remains primarily analytical. This work presents a pedagogically oriented and computationally…

Temporal Neural Networks (TNNs), a special class of spiking neural networks, draw inspiration from the neocortex in utilizing spike-timings for information processing. Recent works proposed a microarchitecture framework and custom macro…

Traditional artificial intelligence implemented in software is usually executed on accurate digital computers. Nevertheless, the nanoscale devices for the implementation of neuromorphic computing may not be ideally identical, and the…

As dynamical systems equipped with neural network controllers (neural feedback systems) become increasingly prevalent, it is critical to develop methods to ensure their safe operation. Verifying safety requires extending control theoretic…

The desire to empower resource-limited edge devices with computer vision (CV) must overcome the high energy consumption of collecting and processing vast sensory data. To address the challenge, this work proposes an energy-efficient…

Multimodal program synthesis, which leverages different types of user input to synthesize a desired program, is an attractive way to scale program synthesis to challenging settings; however, it requires integrating noisy signals from the…

The energy and latency costs of deep neural network inference are increasingly driven by deployment rather than training, motivating hardware-specialized alternatives to arithmetic-heavy models. Field-Programmable Gate Arrays (FPGAs)…

We present mumax+, an extensible GPU-accelerated micromagnetic simulator with a Python user interface, to address the challenges posed by current magnetism research into systems with complex magnetic ordering and interfaces. It is a general…