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

In robot control, planning, and learning, there is a need for rigid-body dynamics libraries that are highly performant, easy to use, and compatible with CPUs and accelerators. While existing libraries often excel at either low-latency CPU…

Scientific machine learning often requires combining known physics with unknown parameters or correction terms learned from data. Existing approaches either ignore known structure, encode it as a soft penalty, or require hand-written…

Magpy is a C++ accelerated Python package for modelling and simulating the magnetic dynamics of nano-sized particles. Nanoparticles are modelled as a system of three-dimensional macrospins and simulated with a set of coupled stochastic…

In recent years, numerous vision and learning tasks have been (re)formulated as nonconvex and nonsmooth programmings(NNPs). Although some algorithms have been proposed for particular problems, designing fast and flexible optimization…

Long-term, high-fidelity simulation of slow-changing physical systems, such as the ocean and climate, presents a fundamental challenge in scientific computing. Traditional autoregressive machine learning models often fail in these tasks as…

We present our latest advancements of machine-learned potentials (MLPs) based on the neuroevolution potential (NEP) framework introduced in [Fan et al., Phys. Rev. B 104, 104309 (2021)] and their implementation in the open-source package…

Applications in robotics or other size-, weight- and power-constrained autonomous systems at the edge often require real-time and low-energy solutions to large optimization problems. Event-based and memory-integrated neuromorphic…

Literate computing has emerged as an important tool for computational studies and open science, with growing folklore of best practices. In this work, we report two case studies - one in computational magnetism and another in computational…

We present an open-source Python framework for NeuroEvolution Optimization with Reinforcement Learning (NEORL) developed at the Massachusetts Institute of Technology. NEORL offers a global optimization interface of state-of-the-art…

Machine learning libraries such as TensorFlow and PyTorch simplify model implementation. However, researchers are still required to perform a non-trivial amount of manual tasks such as GPU allocation, training status tracking, and…

Multimodal-Attributed Graph (MAG) learning has achieved remarkable success in modeling complex real-world systems by integrating graph topology with rich attributes from multiple modalities. With the rapid proliferation of novel MAG models…

In this paper we demonstrate how the Nengo neural modeling and simulation libraries enable users to quickly develop robotic perception and action neural networks for simulation on neuromorphic hardware using familiar tools, such as Keras…

Modern deep neural networks increasingly make use of features such as dynamic control flow, data structures and dynamic tensor shapes. Existing deep learning systems focus on optimizing and executing static neural networks which assume a…

Reservoir computing is an emerging methodology for neuromorphic computing that is especially well-suited for hardware implementations in size, weight, and power (SWaP) constrained environments. This work proposes a novel hardware…

Spintronic nano-neurons offer a promising route towards energy-efficient, high-performance hardware neural networks thanks to their inherent low-input nonlinear dynamics. However, training such networks remains a major bottleneck as it…

We present MiniTensor, an open source tensor operations library that focuses on minimalism, correctness, and performance. MiniTensor exposes a familiar PyTorch-like Python API while it executes performance critical code in a Rust engine.…

Neural network frameworks such as PyTorch and TensorFlow are the workhorses of numerous machine learning applications ranging from object recognition to machine translation. While these frameworks are versatile and straightforward to use,…

We introduce Nerva, a fast neural network library under development in C++. It supports sparsity by using the sparse matrix operations of Intel's Math Kernel Library (MKL), which eliminates the need for binary masks. We show that Nerva…

Computer simulations are used widely across the engineering and science disciplines, including in the research and development of magnetic devices using computational micromagnetics. In this work, we identify and review different approaches…

DNN+NeuroSim is an integrated framework to benchmark compute-in-memory (CIM) accelerators for deep neural networks, with hierarchical design options from device-level, to circuit-level and up to algorithm-level. A python wrapper is…