Search

Autonomous and intelligent systems (AIS) facilitate a wide range of beneficial applications across a variety of different domains. However, technical characteristics such as unpredictability and lack of transparency, as well as potential unintended consequences, pose considerable challenges to the current governance infrastructure. Furthermore, the speed of development and deployment of applications outpaces the ability of existing governance institutions to put in place effective ethical-legal oversight. New approaches for agile, distributed and multilevel governance are needed. This work presents a practical framework for multilevel governance of AIS. The framework enables mapping actors onto six levels of decision-making including the international, national and organizational levels. Furthermore, it offers the ability to identify and evolve existing tools or create new tools for guiding the behavior of actors within the levels. Governance mechanisms enable actors to shape and enforce regulations and other tools, which when complemented with good practices contribute to effective and comprehensive governance.

Reinforcement learning algorithms need exploration to learn. However, unsupervised exploration prevents the deployment of such algorithms on safety-critical tasks and limits real-world deployment. In this paper, we propose a new algorithm called Ensemble Model Predictive Safety Certification that combines model-based deep reinforcement learning with tube-based model predictive control to correct the actions taken by a learning agent, keeping safety constraint violations at a minimum through planning. Our approach aims to reduce the amount of prior knowledge about the actual system by requiring only offline data generated by a safe controller. Our results show that we can achieve significantly fewer constraint violations than comparable reinforcement learning methods., Comment: Published in: Proc. of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2024)

Label-free approaches are attractive in cytological imaging due to their flexibility and cost efficiency. They are supported by machine learning methods, which, despite the lack of labeling and the associated lower contrast, can classify cells with high accuracy where the human observer has little chance to discriminate cells. In order to better integrate these workflows into the clinical decision making process, this work investigates the calibration of confidence estimation for the automated classification of leukocytes. In addition, different visual explanation approaches are compared, which should bring machine decision making closer to professional healthcare applications. Furthermore, we were able to identify general detection patterns in neural networks and demonstrate the utility of the presented approaches in different scenarios of blood cell analysis., Comment: Presented at the 3rd Workshop on Interpretable Machine Learning in Healthcare (IMLH) @ ICML 2023

Hydrogen-like light muonic ions, in which one negative muon replaces all the electrons, are extremely sensitive probes of nuclear structure, because the large muon mass increases tremendously the wave function overlap with the nucleus. Using pulsed laser spectroscopy we have measured three 2S-2P transitions in the muonic helium-3 ion ($\mu^3$He$^+$), an ion formed by a negative muon and bare helium-3 nucleus. This allowed us to extract the Lamb shift $E(2P_{1/2}-2S_{1/2})= 1258.598(48)^{\rm exp}(3)^{\rm theo}$ meV, the 2P fine structure splitting $E_{\rm FS}^{\rm exp} = 144.958(114)$ meV, and the 2S-hyperfine splitting (HFS) $E_{\rm HFS}^{\rm exp} = -166.495(104)^{\rm exp}(3)^{\rm theo}$ meV in $\mu^3$He$^+$. Comparing these measurements to theory we determine the rms charge radius of the helion ($^3$He nucleus) to be $r_h$ = 1.97007(94) fm. This radius represents a benchmark for few nucleon theories and opens the way for precision tests in $^3$He atoms and $^3$He-ions. This radius is in good agreement with the value from elastic electron scattering, but a factor 15 more accurate. Combining our Lamb shift measurement with our earlier one in $\mu^4$He$^+$ we obtain $r_h^2-r_\alpha^2 = 1.0636(6)^{\rm exp}(30)^{\rm theo}$ fm$^2$ to be compared to results from the isotope shift measurements in regular He atoms, which are however affected by long-standing tensions. By comparing $E_{\rm HFS}^{\rm exp}$ with theory we also obtain the two-photon-exchange contribution (including higher orders) which is another important benchmark for ab-initio few-nucleon theories aiming at understanding the magnetic and current structure of light nuclei., Comment: 8 pages, 5 figures

The paucity of labeled data is a typical challenge in the automotive industry. Annotating time-series measurements requires solid domain knowledge and in-depth exploratory data analysis, which implies a high labeling effort. Conventional Active Learning (AL) addresses this issue by actively querying the most informative instances based on the estimated classification probability and retraining the model iteratively. However, the learning efficiency strongly relies on the initial model, resulting in the trade-off between the size of the initial dataset and the query number. This paper proposes a novel Few-Shot Learning (FSL)-based AL framework, which addresses the trade-off problem by incorporating a Prototypical Network (ProtoNet) in the AL iterations. The results show an improvement, on the one hand, in the robustness to the initial model and, on the other hand, in the learning efficiency of the ProtoNet through the active selection of the support set in each iteration. This framework was validated on UCI HAR/HAPT dataset and a real-world braking maneuver dataset. The learning performance significantly surpasses traditional AL algorithms on both datasets, achieving 90% classification accuracy with 10% and 5% labeling effort, respectively., Comment: 4th International Conference on Industry 4.0 and Smart Manufacturing

The quality of datasets plays a crucial role in the successful training and deployment of deep learning models. Especially in the medical field, where system performance may impact the health of patients, clean datasets are a safety requirement for reliable predictions. Therefore, outlier detection is an essential process when building autonomous clinical decision systems. In this work, we assess the suitability of Self-Organizing Maps for outlier detection specifically on a medical dataset containing quantitative phase images of white blood cells. We detect and evaluate outliers based on quantization errors and distance maps. Our findings confirm the suitability of Self-Organizing Maps for unsupervised Out-Of-Distribution detection on the dataset at hand. Self-Organizing Maps perform on par with a manually specified filter based on expert domain knowledge. Additionally, they show promise as a tool in the exploration and cleaning of medical datasets. As a direction for future research, we suggest a combination of Self-Organizing Maps and feature extraction based on deep learning., Comment: Presented at the 2nd Workshop on Interpretable Machine Learning in Healthcare (IMLH) @ ICML 2022

In this work, we propose a data-driven approach to optimize the parameters of a simulation such that control policies can be directly transferred from simulation to a real-world quadrotor. Our neural network-based policies take only onboard sensor data as input and run entirely on the embedded hardware. In extensive real-world experiments, we compare low-level Pulse-Width Modulated control with higher-level control structures such as Attitude Rate and Attitude, which utilize Proportional-Integral-Derivative controllers to output motor commands. Our experiments show that low-level controllers trained with reinforcement learning require a more accurate simulation than higher-level control policies.

Recent development of Deep Reinforcement Learning (DRL) has demonstrated superior performance of neural networks in solving challenging problems with large or even continuous state spaces. One specific approach is to deploy neural networks to approximate value functions by minimising the Mean Squared Bellman Error (MSBE) function. Despite great successes of DRL, development of reliable and efficient numerical algorithms to minimise the MSBE is still of great scientific interest and practical demand. Such a challenge is partially due to the underlying optimisation problem being highly non-convex or using incomplete gradient information as done in Semi-Gradient algorithms. In this work, we analyse the MSBE from a smooth optimisation perspective and develop an efficient Approximate Newton's algorithm. First, we conduct a critical point analysis of the error function and provide technical insights on optimisation and design choices for neural networks. When the existence of global minima is assumed and the objective fulfils certain conditions, suboptimal local minima can be avoided when using over-parametrised neural networks. We construct a Gauss Newton Residual Gradient algorithm based on the analysis in two variations. The first variation applies to discrete state spaces and exact learning. We confirm theoretical properties of this algorithm such as being locally quadratically convergent to a global minimum numerically. The second employs sampling and can be used in the continuous setting. We demonstrate feasibility and generalisation capabilities of the proposed algorithm empirically using continuous control problems and provide a numerical verification of our critical point analysis. We outline the difficulties of combining Semi-Gradient approaches with Hessian information. To benefit from second-order information complete derivatives of the MSBE must be considered during training., Comment: 29 pages, 8 figures

Modern automation systems rely on closed loop control, wherein a controller interacts with a controlled process, based on observations. These systems are increasingly complex, yet most controllers are linear Proportional-Integral-Derivative (PID) controllers. PID controllers perform well on linear and near-linear systems but their simplicity is at odds with the robustness required to reliably control complex processes. Modern machine learning offers a way to extend PID controllers beyond their linear capabilities by using neural networks. However, such an extension comes at the cost of losing stability guarantees and controller interpretability. In this paper, we examine the utility of extending PID controllers with recurrent neural networks-namely, General Dynamic Neural Networks (GDNN); we show that GDNN (neural) PID controllers perform well on a range of control systems and highlight how they can be a scalable and interpretable option for control systems. To do so, we provide an extensive study using four benchmark systems that represent the most common control engineering benchmarks. All control benchmarks are evaluated with and without noise as well as with and without disturbances. The neural PID controller performs better than standard PID control in 15 of 16 tasks and better than model-based control in 13 of 16 tasks. As a second contribution, we address the lack of interpretability that prevents neural networks from being used in real-world control processes. We use bounded-input bounded-output stability analysis to evaluate the parameters suggested by the neural network, thus making them understandable. This combination of rigorous evaluation paired with better interpretability is an important step towards the acceptance of neural-network-based control approaches. It is furthermore an important step towards interpretable and safely applied artificial intelligence.

This report first provides a brief overview of a number of supervised learning algorithms for regression tasks. Among those are neural networks, regression trees, and the recently introduced Nexting. Nexting has been presented in the context of reinforcement learning where it was used to predict a large number of signals at different timescales. In the second half of this report, we apply the algorithms to historical weather data in order to evaluate their suitability to forecast a local weather trend. Our experiments did not identify one clearly preferable method, but rather show that choosing an appropriate algorithm depends on the available side information. For slowly varying signals and a proficient number of training samples, Nexting achieved good results in the studied cases., Comment: 9 pages, 8 Figures, 2 Tables