110 citations · 340 across the 22 of their papers we have counts for
23 papers
Detecting Systematic Weaknesses in Vision Models along Predefined Human-Understandable Dimensions
Sujan Sai Gannamaneni, Rohil Prakash Rao, Michael Mock +2
Slice discovery methods (SDMs) are prominent algorithms for finding systematic weaknesses in DNNs. They identify top-k semantically coherent slices/subsets of data where a DNN-unde…
Assessing Systematic Weaknesses of DNNs using Counterfactuals
Sujan Sai Gannamaneni, Michael Mock, Maram Akila
With the advancement of DNNs into safety-critical applications, testing approaches for such models have gained more attention. A current direction is the search for and identificat…
Guideline for Trustworthy Artificial Intelligence -- AI Assessment Catalog
Maximilian Poretschkin, Anna Schmitz, Maram Akila +11
Artificial Intelligence (AI) has made impressive progress in recent years and represents a key technology that has a crucial impact on the economy and society. However, it is clear…
A Survey on Uncertainty Toolkits for Deep Learning
Maximilian Pintz, Joachim Sicking, Maximilian Poretschkin +1
The success of deep learning (DL) fostered the creation of unifying frameworks such as tensorflow or pytorch as much as it was driven by their creation in return. Having common bui…
Tailored Uncertainty Estimation for Deep Learning Systems
Joachim Sicking, Maram Akila, Jan David Schneider +4
Uncertainty estimation bears the potential to make deep learning (DL) systems more reliable. Standard techniques for uncertainty estimation, however, come along with specific combi…
Validation of Simulation-Based Testing: Bypassing Domain Shift with Label-to-Image Synthesis
Julia Rosenzweig, Eduardo Brito, Hans-Ulrich Kobialka +8
Many machine learning applications can benefit from simulated data for systematic validation - in particular if real-life data is difficult to obtain or annotate. However, since si…
Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
Sebastian Houben, Stephanie Abrecht, Maram Akila +38
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 s…
Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilities
Julia Rosenzweig, Joachim Sicking, Sebastian Houben +2
An important pillar for safe machine learning (ML) is the systematic mitigation of weaknesses in neural networks to afford their deployment in critical applications. An ubiquitous…
Plants Don't Walk on the Street: Common-Sense Reasoning for Reliable Semantic Segmentation
Linara Adilova, Elena Schulz, Maram Akila +4
Data-driven sensor interpretation in autonomous driving can lead to highly implausible predictions as can most of the time be verified with common-sense knowledge. However, learnin…
A Novel Regression Loss for Non-Parametric Uncertainty Optimization
Joachim Sicking, Maram Akila, Maximilian Pintz +3
Quantification of uncertainty is one of the most promising approaches to establish safe machine learning. Despite its importance, it is far from being generally solved, especially…
DenseHMM: Learning Hidden Markov Models by Learning Dense Representations
Joachim Sicking, Maximilian Pintz, Maram Akila +1
We propose DenseHMM - a modification of Hidden Markov Models (HMMs) that allows to learn dense representations of both the hidden states and the observables. Compared to the standa…
Wasserstein Dropout
Joachim Sicking, Maram Akila, Maximilian Pintz +3
Despite of its importance for safe machine learning, uncertainty quantification for neural networks is far from being solved. State-of-the-art approaches to estimate neural uncerta…
Characteristics of Monte Carlo Dropout in Wide Neural Networks
Joachim Sicking, Maram Akila, Tim Wirtz +2
Monte Carlo (MC) dropout is one of the state-of-the-art approaches for uncertainty estimation in neural networks (NNs). It has been interpreted as approximately performing Bayesian…
Exact local correlations in kicked chains at light cone edges
Boris Gutkin, Petr Braun, Maram Akila +2
We show that local correlators in a wide class of kicked chains can be calculated exactly at light cone edges. Extending previous works on dual-unitary systems, the correlators bet…
Local correlations in dual-unitary kicked chains
Boris Gutkin, Petr Braun, Maram Akila +2
We show that for dual-unitary kicked chains, built upon a pair of complex Hadamard matrices, correlators of strictly local, traceless operators vanish identically for sufficiently…
Transition from Quantum Chaos to Localization in Spin Chains
Petr Braun, Daniel Waltner, Maram Akila +2
Recent years have seen an increasing interest in quantum chaos and related aspects of spatially extended systems, such as spin chains. However, the results are strongly system depe…
GSE spectra in uni-directional quantum systems
Maram Akila, Boris Gutkin
Generically, spectral statistics of spinless systems with time reversal invariance (TRI) and chaotic dynamics are well described by the Gaussian Orthogonal ensemble (GOE). However,…
Collectivity and Periodic Orbits in a Chain of Interacting, Kicked Spins
Maram Akila, Daniel Waltner, Boris Gutkin +2
The field of quantum chaos originated in the study of spectral statistics for interacting many-body systems, but this heritage was almost forgotten when single-particle systems mov…
Semiclassical Prediction of Large Spectral Fluctuations in Interacting Kicked Spin Chains
Maram Akila, Boris Gutkin, Peter Braun +2
While plenty of results have been obtained for single-particle quantum systems with chaotic dynamics through a semiclassical theory, much less is known about quantum chaos in the m…
Semiclassical Identification of Periodic Orbits in a Quantum Many-Body System
Maram Akila, Daniel Waltner, Boris Gutkin +2
While a wealth of results has been obtained for chaos in single-particle quantum systems, much less is known about chaos in quantum many-body systems. We contribute to recent effor…
Trace formula for spin chains
Daniel Waltner, Petr Braun, Maram Akila +1
While detailed information about the semiclassics for single-particle systems is available, much less is known about the connection between quantum and classical dynamics for many-…
Particle-Time Duality in the Kicked Ising Chain I: The Dual Operator
M. Akila, D. Waltner, B. Gutkin +1
We demonstrate that the dynamics of kicked spin chains possess a remarkable duality property. The trace of the unitary evolution operator for spins at time is related to on…
Spectral statistics of nearly unidirectional quantum graphs
Maram Akila, Boris Gutkin
The energy levels of a quantum graph with time reversal symmetry and unidirectional classical dynamics are doubly degenerate and obey the spectral statistics of the Gaussian Unitar…