Search Results for author: Ute Schmid

Found 18 papers, 3 papers with code

Effect of Superpixel Aggregation on Explanations in LIME -- A Case Study with Biological Data

1 code implementation17 Oct 2019 Ludwig Schallner, Johannes Rabold, Oliver Scholz, Ute Schmid

Quick-Shift resulted in the least and Compact-Watershed in the highest correspondence with the reference relevance areas.

Image Classification Superpixels

Beneficial and Harmful Explanatory Machine Learning

no code implementations9 Sep 2020 Lun Ai, Stephen H. Muggleton, Céline Hocquette, Mark Gromowski, Ute Schmid

USML is demonstrated by a measurable increase in human performance of a task following provision to the human of a symbolic machine learned theory for task performance.

BIG-bench Machine Learning Self-Learning

Enabling Verification of Deep Neural Networks in Perception Tasks Using Fuzzy Logic and Concept Embeddings

no code implementations3 Jan 2022 Gesina Schwalbe, Christian Wirth, Ute Schmid

In this work, we present a simple, yet effective, approach to verify that a CNN complies with symbolic predicate logic rules which relate visual concepts.

Explainable artificial intelligence

An Interactive Explanatory AI System for Industrial Quality Control

no code implementations17 Mar 2022 Dennis Müller, Michael März, Stephan Scheele, Ute Schmid

Machine learning based image classification algorithms, such as deep neural network approaches, will be increasingly employed in critical settings such as quality control in industry, where transparency and comprehensibility of decisions are crucial.

BIG-bench Machine Learning Defect Detection +2

Explainable Online Lane Change Predictions on a Digital Twin with a Layer Normalized LSTM and Layer-wise Relevance Propagation

no code implementations4 Apr 2022 Christoph Wehner, Francis Powlesland, Bashar Altakrouri, Ute Schmid

The core implementation includes consuming live data from a digital twin on a German highway, live predictions and explanations of lane changes by extending LRP to layer normalized LSTMs, and an interface for communicating and explaining the predictions to a human user.

Decision Making

Explanatory machine learning for sequential human teaching

1 code implementation20 May 2022 Lun Ai, Johannes Langer, Stephen H. Muggleton, Ute Schmid

We propose a framework for the effects of sequential teaching on comprehension based on an existing definition of comprehensibility and provide evidence for support from data collected in human trials.

BIG-bench Machine Learning Inductive logic programming

CorrLoss: Integrating Co-Occurrence Domain Knowledge for Affect Recognition

no code implementations31 Oct 2022 Ines Rieger, Jaspar Pahl, Bettina Finzel, Ute Schmid

Neural networks are widely adopted, yet the integration of domain knowledge is still underutilized.

Explaining Hate Speech Classification with Model Agnostic Methods

no code implementations30 May 2023 Durgesh Nandini, Ute Schmid

This has been achieved by first predicting the classification of a text and then providing a posthoc, model agnostic and surrogate interpretability approach for explainability and to prevent model bias.

Classification Hate Speech Detection

Task Planning Support for Arborists and Foresters: Comparing Deep Learning Approaches for Tree Inventory and Tree Vitality Assessment Based on UAV-Data

no code implementations4 Jul 2023 Jonas-Dario Troles, Richard Nieding, Sonia Simons, Ute Schmid

Furthermore, Bamberg already has a georeferenced tree cadastre of around 15, 000 solitary trees in the city area, which is also used to generate helpful information.

Explaining with Attribute-based and Relational Near Misses: An Interpretable Approach to Distinguishing Facial Expressions of Pain and Disgust

no code implementations27 Aug 2023 Bettina Finzel, Simon P. Kuhn, David E. Tafler, Ute Schmid

In this paper, we present an approach for generating contrastive explanations to explain facial expressions of pain and disgust shown in video sequences.

Attribute Explanation Generation

Cannot find the paper you are looking for? You can Submit a new open access paper.