Search for: All records

We study the performance of a cloud-based GPU-accelerated inference server to speed up event reconstruction in neutrino data batch jobs. Using detector data from the ProtoDUNE experiment and employing the standard DUNE grid job submission tools, we attempt to reprocess the data by running several thousand concurrent grid jobs, a rate we expect to be typical of current and future neutrino physics experiments. We process most of the dataset with the GPU version of our processing algorithm and the remainder with the CPU version for timing comparisons. We find that a 100-GPU cloud-based server is able to easily meet the processing demand, and that using the GPU version of the event processing algorithm is two times faster than processing these data with the CPU version when comparing to the newest CPUs in our sample. The amount of data transferred to the inference server during the GPU runs can overwhelm even the highest-bandwidth network switches, however, unless care is taken to observe network facility limits or otherwise distribute the jobs to multiple sites. We discuss the lessons learned from this processing campaign and several avenues for future improvements.

 

The Earth mover’s distance (EMD) is a useful metric for image recognition and classification, but its usual implementations are not differentiable or too slow to be used as a loss function for training other algorithms via gradient descent. In this paper, we train a convolutional neural network (CNN) to learn a differentiable, fast approximation of the EMD and demonstrate that it can be used as a substitute for computing-intensive EMD implementations. We apply this differentiable approximation in the training of an autoencoder-inspired neural network (encoder NN) for data compression at the high-luminosity LHC at CERN The goal of this encoder NN is to compress the data while preserving the information related to the distribution of energy deposits in particle detectors. We demonstrate that the performance of our encoder NN trained using the differentiable EMD CNN surpasses that of training with loss functions based on mean squared error.

 

Mixed Reality provides a powerful medium for transparent and effective human-robot communication, especially for robots with significant physical limitations (e.g., those without arms). To enhance nonverbal capabilities for armless robots, this article presents two studies that explore two different categories of mixed reality deictic gestures for armless robots: a virtual arrow positioned over a target referent (a non-ego-sensitive allocentric gesture) and a virtual arm positioned over the gesturing robot (an ego-sensitive allocentric gesture). In Study 1, we explore the tradeoffs between these two types of gestures with respect to both objective performance and subjective social perceptions. Our results show fundamentally different task-oriented versus social benefits, with non-ego-sensitive allocentric gestures enabling faster reaction time and higher accuracy, but ego-sensitive gestures enabling higher perceived social presence, anthropomorphism, and likability. In Study 2, we refine our design recommendations by showing that in fact these different gestures should not be viewed as mutually exclusive alternatives, and that by using them together, robots can achieve both task-oriented and social benefits. 

Recently, researchers have initiated a new wave of convergent research in which Mixed Reality visualizations enable new modalities of human-robot communication, including Mixed Reality Deictic Gestures (MRDGs) – the use of visualizations like virtual arms or arrows to serve the same purpose as traditional physical deictic gestures. But while researchers have demonstrated a variety of benefits to these gestures, it is unclear whether the success of these gestures depends on a user’s level and type of cognitive load. We explore this question through an experiment grounded in rich theories of cognitive resources, attention, and multi-tasking, with significant inspiration drawn from Multiple Resource Theory. Our results suggest that MRDGs provide task-oriented benefits regardless of cognitive load, but only when paired with complex language. These results suggest that designers can pair rich referring expressions with MRDGs without fear of cognitively overloading their users. 

The high instantaneous luminosity of the CERN Large Hadron Collider leads to multiple proton–proton interactions in the same or nearby bunch crossings (pileup). Advanced pileup mitigation algorithms are designed to remove this noise from pileup particles and improve the performance of crucial physics observables. This study implements a semi-supervised graph neural network for particle-level pileup noise removal, by identifying individual particles produced from pileup. The graph neural network is firstly trained on charged particles with known labels, which can be obtained from detector measurements on data or simulation, and then inferred on neutral particles for which such labels are missing. This semi-supervised approach does not depend on the neutral particle pileup label information from simulation, and thus allows us to perform training directly on experimental data. The performance of this approach is found to be consistently better than widely-used domain algorithms and comparable to the fully-supervised training using simulation truth information. The study serves as the first attempt at applying semi-supervised learning techniques to pileup mitigation, and opens up a new direction of fully data-driven machine learning pileup mitigation studies.

 

We investigate the effectiveness of robot-generated mixed reality gestures. Our findings demonstrate how these gestures increase user effectiveness by decreasing user response time, and that robots can pair long referring expressions with mixed reality gestures without cognitively overloading users. 

Efficient machine learning implementations optimized for inference in hardware have wide-ranging benefits, depending on the application, from lower inference latency to higher data throughput and reduced energy consumption. Two popular techniques for reducing computation in neural networks are pruning, removing insignificant synapses, and quantization, reducing the precision of the calculations. In this work, we explore the interplay between pruning and quantization during the training of neural networks for ultra low latency applications targeting high energy physics use cases. Techniques developed for this study have potential applications across many other domains. We study various configurations of pruning during quantization-aware training, which we term quantization-aware pruning , and the effect of techniques like regularization, batch normalization, and different pruning schemes on performance, computational complexity, and information content metrics. We find that quantization-aware pruning yields more computationally efficient models than either pruning or quantization alone for our task. Further, quantization-aware pruning typically performs similar to or better in terms of computational efficiency compared to other neural architecture search techniques like Bayesian optimization. Surprisingly, while networks with different training configurations can have similar performance for the benchmark application, the information content in the network can vary significantly, affecting its generalizability. 

Mixed Reality visualizations provide a powerful new approach for enabling gestural capabilities on non-humanoid robots. This paper explores two different categories of mixed-reality deictic gestures for armless robots: a virtual arrow positioned over a target referent (a non-ego-sensitive allocentric gesture) and a virtual arm positioned over the gesturing robot (an ego-sensitive allocentric gesture). Specifically, we present the results of a within-subjects Mixed Reality HRI experiment (N=23) exploring the trade-offs between these two types of gestures with respect to both objective performance and subjective social perceptions. Our results show a clear trade-off between performance and social perception, with non-ego-sensitive allocentric gestures enabling faster reaction time and higher accuracy, but ego-sensitive gestures enabling higher perceived social presence, anthropomorphism, and likability. 

Abstract This paper presents a roadmap to the application of AI techniques and big data (BD) for different modelling, design, monitoring, manufacturing and operation purposes of different superconducting applications. To help superconductivity researchers, engineers, and manufacturers understand the viability of using AI and BD techniques as future solutions for challenges in superconductivity, a series of short articles are presented to outline some of the potential applications and solutions. These potential futuristic routes and their materials/technologies are considered for a 10–20 yr time-frame. 

We present the first experiment analyzing the effectiveness of robot-generated mixed reality gestures using real robotic and mixed reality hardware. Our findings demonstrate how these gestures increase user effectiveness by decreasing user response time during visual search tasks, and show that robots can safely pair longer, more natural referring expressions with mixed reality gestures without worrying about cognitively overloading their interlocutors.