Related papers: Data-Driven Gradient Optimization for Field Emissi…

One of the most important parts of Artificial Neural Networks is minimizing the loss functions which tells us how good or bad our model is. To minimize these losses we need to tune the weights and biases. Also to calculate the minimum value…

We present the electromagnetic design study of a multi cell, \beta_g= 0.9, 650 MHz elliptic superconducting radiofrequency cavity, which can be used for accelerating H- particles in the linear accelerator part of a Spallation Neutron…

When machine learning models encounter data which is out of the distribution on which they were trained they have a tendency to behave poorly, most prominently over-confidence in erroneous predictions. Such behaviours will have disastrous…

We have reported previously on the conditioning of the high-gradient accelerating cavities in the Fermilab Linac. Automated measurements of the sparking rate have been recorded since 1994 and are reported here. The sparking rate has…

Predictive Coding Networks (PCNs) aim to learn a generative model of the world. Given observations, this generative model can then be inverted to infer the causes of those observations. However, when training PCNs, a noticeable pathology is…

We report on the development of a radio frequency (RF) linear accelerator (linac) for multiple-ion beams that is made from stacks of low cost wafers. The accelerator lattice is comprised of RF-acceleration gaps and electrostatic quadrupole…

The growing complexity of radar signals demands responsive and accurate detection systems that can operate efficiently on resource-constrained edge devices. Existing models, while effective, often rely on substantial computational resources…

We propose a new technique that boosts the convergence of training generative adversarial networks. Generally, the rate of training deep models reduces severely after multiple iterations. A key reason for this phenomenon is that a deep…

Although lower hybrid waves are effective at driving currents in present-day tokamaks, they are expected to interact strongly with high-energy particles in extrapolating to reactors. In the presence of a radial alpha particle birth…

This paper describes the development progress of high current superconducting RF linacs in Los Alamos, performed to support a design of the linac for the APT (Accelerator Production of Tritium) Project. The APT linac design includes a CW…

Policy gradient methods hold great potential for solving complex continuous control tasks. Still, their training efficiency can be improved by exploiting structure within the optimization problem. Recent work indicates that supervised…

Machine learning has emerged as a popular and powerful approach for solving problems in astrophysics. We review applications of machine learning techniques for the analysis of ground-based gravitational-wave detector data. Examples include…

Improving performance of deep learning models and reducing their training times are ongoing challenges in deep neural networks. There are several approaches proposed to address these challenges one of which is to increase the depth of the…

Compact, reliable and little consuming accelerators are required for the treatment of tumours with ions. TERA proposes the "cyclinac", composed of a high-frequency, fast-cycling linac which boosts the energy of the particles previously…

Deep neural networks tend to make overconfident predictions and often require additional detectors for misclassifications, particularly for safety-critical applications. Existing detection methods usually only focus on adversarial attacks…

High penetration from volatile renewable energy resources in the grid and the varying nature of loads raise the need for frequent line switching to ensure the efficient operation of electrical distribution networks. Operators must ensure…

Nowadays, Computational Fluid Dynamics (CFD) is a fundamental tool for industrial design. However, the computational cost of doing such simulations is expensive and can be detrimental for real-world use cases where many simulations are…

A major challenge in training large-scale machine learning models is configuring the training process to maximize model performance, i.e., finding the best training setup from a vast design space. In this work, we unlock a gradient-based…

The Fermilab Linac delivers a variable intensity, 400-MeV beam to the The MuCool Test Area experimental hall via a beam line specifically designed to facilitate measurements of the Linac beam emittance and properties. A 10 m,…

Quantum computing requires the optimization of control pulses to achieve high-fidelity quantum gates. We propose a machine learning-based protocol to address the challenges of evaluating gradients and modeling complex system dynamics. By…