Michael Siebers

Otto-Friedrich-Universität Bamberg · Department of Applied Computer Sciences

In recent research, human-understandable explanations of machine learning models have received a lot of attention. Often explanations are given in form of model simplifications or visualizations. However, as shown in cognitive science as well as in early AI research, concept understanding can also be improved by the alignment of a given instance fo...

In recent research, human-understandable explanations of machine learning models have received a lot of attention. Often explanations are given in form of model simplifications or visualizations. However, as shown in cognitive science as well as in early AI research, concept understanding can also be improved by the alignment of a given instance fo...

With the increasing prevalence of Machine Learning in everyday life, a growing number of people will be provided with Machine-Learned assessments on a regular basis. We believe that human users interacting with systems based on Machine-Learned classifiers will demand and profit from the systems’ decisions being explained in an approachable and comp...

With the increasing number of deep learning applications, there is a growing demand for explanations. Visual explanations provide information about which parts of an image are relevant for a classifier’s decision. However, highlighting of image parts (e.g., an eye) cannot capture the relevance of a specific feature value for a class (e.g., that the...

With the increasing number of deep learning applications, there is a growing demand for explanations. Visual explanations provide information about which parts of an image are relevant for a classifier's decision. However, highlighting of image parts (e.g., an eye) cannot capture the relevance of a specific feature value for a class (e.g., that the...

Sind Maschinen bald schlauer als wir? Haben dann die Roboter das Sagen? Um diese Fragen realistisch beantworten zu können, musst du erst einmal herausfinden, was Künstliche Intelligenz eigentlich ist. Dieses Buch hilft dir dabei. Kapitel für Kapitel beantwortet es folgende Fragen: Wie denken Computer? Wie lernen Computer? Wie spielen Computer? Wie...

Future work environments will offer technical applications to manage increasing amounts of information for organizations, teams, and individuals. In this context, psychological concepts of intentional forgetting (IF) can be applied to improve the performance of work systems or to extend the cognitive capacities of humans in technical systems. Diffe...

Emerging technologies at work encourage the collection and storage of large amounts of data. However, these vast quantities of data are likely to impair efficient work decisions by employees over time, with negative consequences for the organization. As human attention increasingly represents the scarce resource at work, the present paper focuses o...

Future work environments offer numerous technical applications to manage increasing amounts of information for organizations, teams, and individuals. Psychological concepts of intentional forgetting (IF) can be applied to improve the performance of work systems or to extend cognitive capacities of humans in technical systems. Different IF mechanism...

Dare2Del is an assistive system which facilitates intentional forgetting of irrelevant digital objects. For an assistive system to be helpful, the user has to trust the system’s decisions. Explanations are a crucial component in establishing this trust. We will introduce different types of explanations which can vary along different dimensions such...

Many people believe that every fourth year is a leap year. However, this rule is too general: year X is a leap year if X is divisible by 4 except if X is divisible by 100 except if X is divisible by 400. We call such a theory with alternating generalisation and specialisation a step-wise narrowed theory. We present and evaluate an extension to the...

Current trends, like digital transformation and ubiquitous computing, yield in massive increase in available data and information. In artificial intelligence (AI) systems, capacity of knowledge bases is limited due to computational complexity of many inference algorithms. Consequently, continuously sampling information and unfiltered storing in kno...

Background Given the unreliable self-report in patients with dementia, pain assessment should also rely on the observation of pain behaviors, such as facial expressions. Ideal observers should be well trained and should observe the patient continuously in order to pick up any pain-indicative behavior; which are requisitions beyond realistic possibi...

We present the design of a cognitive companion |Dare2Del| which supports humans to temporarily ignore or permanently delete digital objects. The design of the system is inspired by successful human strategies. The system will combine logical knowledge representation and inference with machine learning. Thereby, the advantages of an explicit model a...

While some computational models of intelligence test problems were proposed throughout the second half of the XXth century, in the first years of the XXIst century we have seen an increasing number of computer systems being able to score well on particular intelligence test tasks. However, despitethis increasing trend there has been no general acco...

We investigate the application of grammar inference to the analysis of facial expressions to discover underlying sequential regularities characteristic for a specific mental state. The input consists of sequences of action units (AUs), which represent basic facial signals. The typical classification task for facial expression analysis is to assign...

Abstract While some computational models of intelligence test problems were proposed throughout the second half of the XXth century, in the first years of the XXIst century we have seen an increasing number of computer systems being able to score well on particular intelligence test tasks. However, despite this increasing trend there has been no ge...

In this paper we present an approach to avoid dead-ends during automated plan generation. A first-order logic formula can be learned that holds in a state if the application of a specific action will lead to a dead-end. Starting from small problems within a problem domain examples of states where the application of the action will lead to a dead-en...

We present a framework for cognitive modeling of aesthetic decision making based on dynamic prototypes. Starting point of our work is empirical evidence which shows that subjects’ initial ratings of attractiveness of objects can be influenced by adapting them to new, typically more innovative objects. The framework consists of three steps: (1) Esti...

Since Ekman and Friesen published their Facial Action Coding System in 1978 the typical facial expressions of many mental states have been studied. However, most research concentrates on the set of action units present during some facial expression---the sequence of the action units is ignored. In this paper we investigate human facial expression d...

The induction of natural number series is a prototypical intelligence test task. We present a system which solves this task semi-analytically. As first step the term structure defining a given number series is guessed. Then the semi-instantiated formula is used to abduct new number series examples which can be solved more easily.

We present an application of grammar inference in the domain of facial expression analysis. Many approaches to automated expressions recognition are based on the identification of basic facial signals – so called action units (AUs). Based on the facial action coding system (FACS), special subsets of such AUs are mapped into symbolic representations...

Proceedings of KogWis 2012. 11th Biannual Conference of the German Cognitive Science Society

Text: Research on assistive home technology (AT) aims to reduce care costs and increase quality of life of people with dementia. Currently it is unclear what the needs of people with dementia are and what kind of support they desire. The reported survey aims to identify personal attitudes towards AT in daily living: As how disturbing is the loss of...

Combining supervised and unsupervised learning is no new idea. Nevertheless, this was mainly done in a semi-supervised fashion. I will present a first approach to a framework using both methods on a classification task without using unlabeled data. I will evaluate the framework on an artificial data set and provide further research plans and ideas.

Selecting appropriate features has become a key task when dealing with high-dimensional data. We present a new algorithm designed to find an optimal solution for classification tasks. Our approach combines forward selection, backward elimination and exhaustive search. We demonstrate its capabilities and limits using artificial and real world data s...

Pain is a highly affective state that is accompanied by a facial expression. In this paper we compare different classiers on their possibilities to classify pain from facial point data. Furthermore we investigate the need for training classiers on each subject's data individually. We show that most used classiers are suitable for the classifying fa...