Estimating uncertainty is at the core of performing scientific measurements in HEP: a measurement is not useful without an estimate of its uncertainty. The goal of uncertainty quantification (UQ) is inextricably linked to the question, "how do we physically and statistically interpret these uncertainties?" The answer to this question depends not only on the computational task we aim to undertake, but also on the methods we use for that task. For artificial intelligence (AI) applications in HEP, there are several areas where interpretable methods for UQ are essential, including inference, simulation, and control/decision-making. There exist some methods for each of these areas, but they have not yet been demonstrated to be as trustworthy as more traditional approaches currently employed in physics (e.g., non-AI frequentist and Bayesian methods). Shedding light on the questions above requires additional understanding of the interplay of AI systems and uncertainty quantification. We briefly discuss the existing methods in each area and relate them to tasks across HEP. We then discuss recommendations for avenues to pursue to develop the necessary techniques for reliable widespread usage of AI with UQ over the next decade.

2D animation is a common factor in game development, used for characters, effects and background art. It involves work that takes both skill and time, but parts of which are repetitive and tedious. Automated animation approaches exist, but are designed without animators in mind. The focus is heavily on real-life video, which follows strict laws of how objects move, and does not account for the stylistic movement often present in 2D animation. We propose a problem formulation that more closely adheres to the standard workflow of animation. We also demonstrate a model, SketchBetween, which learns to map between keyframes and sketched in-betweens to rendered sprite animations. We demonstrate that our problem formulation provides the required information for the task and that our model outperforms an existing method.

As a significant ingredient regarding health status, data-driven state-of-health (SOH) estimation has become dominant for lithium-ion batteries (LiBs). To handle data discrepancy across batteries, current SOH estimation models engage in transfer learning (TL), which reserves apriori knowledge gained through reusing partial structures of the offline trained model. However, multiple degradation patterns of a complete life cycle of a battery make it challenging to pursue TL. The concept of the stage is introduced to describe the collection of continuous cycles that present a similar degradation pattern. A transferable multi-stage SOH estimation model is proposed to perform TL across batteries in the same stage, consisting of four steps. First, with identified stage information, raw cycling data from the source battery are reconstructed into the phase space with high dimensions, exploring hidden dynamics with limited sensors. Next, domain invariant representation across cycles in each stage is proposed through cycling discrepancy subspace with reconstructed data. Third, considering the unbalanced discharge cycles among different stages, a switching estimation strategy composed of a lightweight model with the long short-term memory network and a powerful model with the proposed temporal capsule network is proposed to boost estimation accuracy. Lastly, an updating scheme compensates for estimation errors when the cycling consistency of target batteries drifts. The proposed method outperforms its competitive algorithms in various transfer tasks for a run-to-failure benchmark with three batteries. Especially through transferring the estimation model from batteries B7 to B6, the proposed method improves the estimation accuracy by as high as 42.6% in the third stage in terms of the root mean square error, compared to other state-of-the-art approaches.

This study proposes an end-to-end unsupervised diffeomorphic deformable registration framework based on moving mesh parameterization. Using this parameterization, a deformation field can be modeled with its transformation Jacobian determinant and curl of end velocity field. The new model of the deformation field has three important advantages; firstly, it relaxes the need for an explicit regularization term and the corresponding weight in the cost function. The smoothness is implicitly embedded in the solution which results in a physically plausible deformation field. Secondly, it guarantees diffeomorphism through explicit constraints applied to the transformation Jacobian determinant to keep it positive. Finally, it is suitable for cardiac data processing, since the nature of this parameterization is to define the deformation field in terms of the radial and rotational components. The effectiveness of the algorithm is investigated by evaluating the proposed method on three different data sets including 2D and 3D cardiac MRI scans. The results demonstrate that the proposed framework outperforms existing learning-based and non-learning-based methods while generating diffeomorphic transformations.

This paper presents Lidar-based Simultaneous Localization and Mapping (SLAM) for autonomous driving vehicles. Fusing data from landmark sensors and a strap-down Inertial Measurement Unit (IMU) in an adaptive Kalman filter (KF) plus the observability of the system are investigated. In addition to the vehicle's states and landmark positions, a self-tuning filter estimates the IMU calibration parameters as well as the covariance of the measurement noise. The discrete-time covariance matrix of the process noise, the state transition matrix, and the observation sensitivity matrix are derived in closed-form making them suitable for real-time implementation. Examining the observability of the 3D SLAM system leads to the conclusion that the system remains observable upon a geometrical condition on the alignment of the landmarks.

Recent studies suggest that artificial neural networks (ANNs) that match the spectral properties of the mammalian visual cortex -- namely, the $\sim 1/n$ eigenspectrum of the covariance matrix of neural activities -- achieve higher object recognition performance and robustness to adversarial attacks than those that do not. To our knowledge, however, no previous work systematically explored how modifying the ANN's spectral properties affects performance. To fill this gap, we performed a systematic search over spectral regularizers, forcing the ANN's eigenspectrum to follow $1/n^\alpha$ power laws with different exponents $\alpha$. We found that larger powers (around 2--3) lead to better validation accuracy and more robustness to adversarial attacks on dense networks. This surprising finding applied to both shallow and deep networks and it overturns the notion that the brain-like spectrum (corresponding to $\alpha \sim 1$) always optimizes ANN performance and/or robustness. For convolutional networks, the best $\alpha$ values depend on the task complexity and evaluation metric: lower $\alpha$ values optimized validation accuracy and robustness to adversarial attack for networks performing a simple object recognition task (categorizing MNIST images of handwritten digits); for a more complex task (categorizing CIFAR-10 natural images), we found that lower $\alpha$ values optimized validation accuracy whereas higher $\alpha$ values optimized adversarial robustness. These results have two main implications. First, they cast doubt on the notion that brain-like spectral properties ($\alpha \sim 1$) \emph{always} optimize ANN performance. Second, they demonstrate the potential for fine-tuned spectral regularizers to optimize a chosen design metric, i.e., accuracy and/or robustness.

Reliable spatial uncertainty evaluation of object detection models is of special interest and has been subject of recent work. In this work, we review the existing definitions for uncertainty calibration of probabilistic regression tasks. We inspect the calibration properties of common detection networks and extend state-of-the-art recalibration methods. Our methods use a Gaussian process (GP) recalibration scheme that yields parametric distributions as output (e.g. Gaussian or Cauchy). The usage of GP recalibration allows for a local (conditional) uncertainty calibration by capturing dependencies between neighboring samples. The use of parametric distributions such as as Gaussian allows for a simplified adaption of calibration in subsequent processes, e.g., for Kalman filtering in the scope of object tracking. In addition, we use the GP recalibration scheme to perform covariance estimation which allows for post-hoc introduction of local correlations between the output quantities, e.g., position, width, or height in object detection. To measure the joint calibration of multivariate and possibly correlated data, we introduce the quantile calibration error which is based on the Mahalanobis distance between the predicted distribution and the ground truth to determine whether the ground truth is within a predicted quantile. Our experiments show that common detection models overestimate the spatial uncertainty in comparison to the observed error. We show that the simple Isotonic Regression recalibration method is sufficient to achieve a good uncertainty quantification in terms of calibrated quantiles. In contrast, if normal distributions are required for subsequent processes, our GP-Normal recalibration method yields the best results. Finally, we show that our covariance estimation method is able to achieve best calibration results for joint multivariate calibration.

High-tech giants and start-ups are investing in drone technologies to provide urban air delivery service, which is expected to solve the last-mile problem and mitigate road traffic congestion. However, air delivery service will not scale up without proper traffic management for drones in dense urban environment. Currently, a range of Concepts of Operations (ConOps) for unmanned aircraft system traffic management (UTM) are being proposed and evaluated by researchers, operators, and regulators. Among these, the tube-based (or corridor-based) ConOps has emerged in operations in some regions of the world for drone deliveries and is expected to continue serving certain scenarios that with dense and complex airspace and requires centralized control in the future. Towards the tube-based ConOps, we develop a route network planning method to design routes (tubes) in a complex urban environment in this paper. In this method, we propose a priority structure to decouple the network planning problem, which is NP-hard, into single-path planning problems. We also introduce a novel space cost function to enable the design of dense and aligned routes in a network. The proposed method is tested on various scenarios and compared with other state-of-the-art methods. Results show that our method can generate near-optimal route networks with significant computational time-savings.

The focus of this paper is a proof of concept, machine learning (ML) pipeline that extracts heart rate from pressure sensor data acquired on low-power edge devices. The ML pipeline consists an upsampler neural network, a signal quality classifier, and a 1D-convolutional neural network optimized for efficient and accurate heart rate estimation. The models were designed so the pipeline was less than 40 kB. Further, a hybrid pipeline consisting of the upsampler and classifier, followed by a peak detection algorithm was developed. The pipelines were deployed on ESP32 edge device and benchmarked against signal processing to determine the energy usage, and inference times. The results indicate that the proposed ML and hybrid pipeline reduces energy and time per inference by 82% and 28% compared to traditional algorithms. The main trade-off for ML pipeline was accuracy, with a mean absolute error (MAE) of 3.28, compared to 2.39 and 1.17 for the hybrid and signal processing pipelines. The ML models thus show promise for deployment in energy and computationally constrained devices. Further, the lower sampling rate and computational requirements for the ML pipeline could enable custom hardware solutions to reduce the cost and energy needs of wearable devices.

I am going to speak with you using an AI voice because I have a sore throat. I had built a text to speech voice synthesizer as my college project in my Computer Science Engineering undergrads decades back. I am using Google WaveNet for text to speech. This is #SudhaLive my weekly livestream where I share opportunities in AI space -- jobs, fellowship, courses and my analysis of one topic from the AI world. Let's hear a female voice from India now.