Related papers: Optimizing a Superconducting Radiofrequency Gun Us…

Robust imitation learning using disturbance injections overcomes issues of limited variation in demonstrations. However, these methods assume demonstrations are optimal, and that policy stabilization can be learned via simple augmentations.…

Aligning a lens system relative to an imager is a critical challenge in camera manufacturing. While optimal alignment can be mathematically computed under ideal conditions, real-world deviations caused by manufacturing tolerances often…

High-fidelity electron microscopy simulations required for quantitative crystal structure refinements face a fundamental challenge: while physical interactions are well-described theoretically, real-world experimental effects are…

Deep neural networks ( DNNs ) are becoming a key enabling technology for many application domains. However, on-device inference on battery-powered, resource-constrained embedding systems is often infeasible due to prohibitively long…

The interaction of relativistically intense lasers with opaque targets represents a highly non-linear, multi-dimensional parameter space. This limits the utility of sequential 1D scanning of experimental parameters for the optimisation of…

Resource allocation and transceivers in wireless networks are usually designed by solving optimization problems subject to specific constraints, which can be formulated as variable or functional optimization. If the objective and constraint…

Training a deep neural network to maximize a target objective has become the standard recipe for successful machine learning over the last decade. These networks can be optimized with supervised learning, if the target objective is…

Diffusion-based inpainting can reconstruct missing image areas with high quality from sparse data, provided that their location and their values are well optimised. This is particularly useful for applications such as image compression,…

Deep reinforcement learning (deep RL) is a combination of deep learning with reinforcement learning principles to create efficient methods that can learn by interacting with its environment. This led to breakthroughs in many complex tasks…

Recirculating energy recovery linacs are a promising technology for delivering high power particle beams ($\sim$GW) while only requiring low power ($\sim$kW) RF sources. This is achieved by decelerating the used bunches and using the energy…

Unprecedented high volumes of data are becoming available with the growth of the advanced metering infrastructure. These are expected to benefit planning and operation of the future power system, and to help the customers transition from a…

Using RF signals for wireless sensing has gained increasing attention. However, due to the unwanted multi-path fading in uncontrollable radio environments, the accuracy of RF sensing is limited. Instead of passively adapting to the…

The incorporation of high-performance optoelectronic devices into photonic neuromorphic processors can substantially accelerate computationally intensive operations in machine learning (ML) algorithms. However, the conventional device…

We present an efficient subpixel refinement method usinga learning-based approach called Linear Predictors. Two key ideas are shown in this paper. Firstly, we present a novel technique, called Symbolic Linear Predictors, which makes the…

Optimal control and sequential decision making are widely used in many complex tasks. Optimal control over a sequence of natural images is a first step towards understanding the role of vision in control. Here, we formalize this problem as…

The design and optimization of optical components, such as Bragg gratings, are critical for applications in telecommunications, sensing, and photonic circuits. To overcome the limitations of traditional design methods that rely heavily on…

The energy recovery linac test facility (ERL-TF), a compact ERL-FEL (free electron laser) two-purpose machine, was proposed at the Institute of High Energy Physics, Beijing. As one important component of the ERL-TF, the photo-injector…

The design of fusion devices is typically based on computationally expensive simulations. This can be alleviated using high aspect ratio models that employ a reduced number of free parameters, especially in the case of stellarator…

In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark. But despite their clear empirical advantages, it is still not well…

We demonstrate that deep reinforcement learning (deep RL) provides a highly effective strategy for the control and self-tuning of optical systems. Deep RL integrates the two leading machine learning architectures of deep neural networks and…