Goto

Collaborating Authors

 Weber, Michael


Harnessing Generative AI for Economic Insights

arXiv.org Artificial Intelligence

We use generative AI to extract managerial expectations about their economic outlook from over 120,000 corporate conference call transcripts. The overall measure, AI Economy Score, robustly predicts future economic indicators such as GDP growth, production, and employment, both in the short term and to 10 quarters. This predictive power is incremental to that of existing measures, including survey forecasts. Moreover, industry and firm-level measures provide valuable information about sector-specific and individual firm activities. Our findings suggest that managerial expectations carry unique insights about economic activities, with implications for both macroeconomic and microeconomic decision-making.


Interpretable Anomaly Detection in Cellular Networks by Learning Concepts in Variational Autoencoders

arXiv.org Artificial Intelligence

This paper addresses the challenges of detecting anomalies in cellular networks in an interpretable way and proposes a new approach using variational autoencoders (VAEs) that learn interpretable representations of the latent space for each Key Performance Indicator (KPI) in the dataset. This enables the detection of anomalies based on reconstruction loss and Z-scores. We ensure the interpretability of the anomalies via additional information centroids (c) using the K-means algorithm to enhance representation learning. We evaluate the performance of the model by analyzing patterns in the latent dimension for specific KPIs and thereby demonstrate the interpretability and anomalies. The proposed framework offers a faster and autonomous solution for detecting anomalies in cellular networks and showcases the potential of deep learning-based algorithms in handling big data.


Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety

arXiv.org Artificial Intelligence

The use of deep neural networks (DNNs) in safety-critical applications like mobile health and autonomous driving is challenging due to numerous model-inherent shortcomings. These shortcomings are diverse and range from a lack of generalization over insufficient interpretability to problems with malicious inputs. Cyber-physical systems employing DNNs are therefore likely to suffer from safety concerns. In recent years, a zoo of state-of-the-art techniques aiming to address these safety concerns has emerged. This work provides a structured and broad overview of them. We first identify categories of insufficiencies to then describe research activities aiming at their detection, quantification, or mitigation. Our paper addresses both machine learning experts and safety engineers: The former ones might profit from the broad range of machine learning topics covered and discussions on limitations of recent methods. The latter ones might gain insights into the specifics of modern ML methods. We moreover hope that our contribution fuels discussions on desiderata for ML systems and strategies on how to propel existing approaches accordingly.


A Planning-Based Assistance System for Setting Up a Home Theater

AAAI Conferences

Modern technical devices are often too complex for many users to be able to use them to their full extent. Based on planning technology, we are able to provide advanced user assistance for operating technical devices. We present a system that assists a human user in setting up a complex home theater consisting of several HiFi devices. For a human user, the task is rather challenging due to a large number of different ports of the devices and the variety of available cables. The system supports the user by giving detailed instructions how to assemble the theater. Its performance is based on advanced user-centered planning capabilities including the generation, repair, and explanation of plans.


Towards Territorial Privacy in Smart Environments

AAAI Conferences

Territorial privacy is an old concept for privacy of the personal space dating back to the 19th century. Despite its former relevance, territorial privacy has been neglected in recent years, while privacy research and legislation mainly focused on the issue of information privacy. However, with the prospect of smart and ubiquitous environments, territorial privacy deserves new attention. Walls, as boundaries between personal and public spaces, will be insufficient to guard territorial privacy when our environments are permeated with numerous computing and sensing devices, that gather and share real-time information about us. Territorial privacy boundaries spanning both the physical and virtual world are required for the demarcation of personal spaces in smart environments. In this paper, we analyze and discuss the issue of territorial privacy in smart environments. We further propose a real-time user-centric observation model to describe multimodal observation channels of multiple physical and virtual observers. The model facilitates the definition of a territorial privacy boundary by separating desired from undesired observers, regardless of whether they are physically present in the user’s private territory or virtually participating in it. Moreover, we outline future research challenges and identify areas of work that require attention in the context of territorial privacy in smart environments.