Barbara Hammer

Barbara Hammer
Bielefeld University · CITEC - Cognitive Interaction Technology

Prof.Dr.

About

488
Publications
55,148
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
6,927
Citations
Additional affiliations
April 2010 - present
April 2010 - present
Bielefeld University
Position
  • Professor
October 2008 - October 2008
University of Groningen

Publications

Publications (488)
Article
When measuring data with hyperspectral cameras drift in the data distribution occurs over time and when the sensing device is changed. Frequently, this drift is characterized by intensity shift or wavelength shifts. In this contribution, we propose novel methods that reverse these shifts and demonstrate their capability to avoid the negative impact...
Preprint
Full-text available
Dimensionality reduction is a popular preprocessing and a widely used tool in data mining. Transparency, which is usually achieved by means of explanations, is nowadays a widely accepted and crucial requirement of machine learning based systems like classifiers and recommender systems. However, transparency of dimensionality reduction and other dat...
Preprint
Full-text available
Transparency is a major requirement of modern AI based decision making systems deployed in real world. A popular approach for achieving transparency is by means of explanations. A wide variety of different explanations have been proposed for single decision making systems. In practice it is often the case to have a set (i.e. ensemble) of decisions...
Preprint
The notion of concept drift refers to the phenomenon that the data generating distribution changes over time; as a consequence machine learning models may become inaccurate and need adjustment. In this paper we consider the problem of detecting those change points in unsupervised learning. Many unsupervised approaches rely on the discrepancy betwee...
Preprint
Full-text available
Counterfactual explanations (CFEs) highlight what changes to a model's input would have changed its prediction in a particular way. CFEs have gained considerable traction as a psychologically grounded solution for explainable artificial intelligence (XAI). Recent innovations introduce the notion of computational plausibility for automatically gener...
Preprint
Full-text available
To foster usefulness and accountability of machine learning (ML), it is essential to explain a model's decisions in addition to evaluating its performance. Accordingly, the field of explainable artificial intelligence (XAI) has resurfaced as a topic of active research, offering approaches to address the "how" and "why" of automated decision-making....
Article
Full-text available
Many of today’s decision making systems deployed in the real world are not static—they are changing and adapting over time, a phenomenon known as model adaptation takes place. Because of their wide reaching influence and potentially serious consequences, the need for transparency and interpretability of AI-based decision making systems is widely ac...
Preprint
Full-text available
Data stream classification is an important problem in the field of machine learning. Due to the non-stationary nature of the data where the underlying distribution changes over time (concept drift), the model needs to continuously adapt to new data statistics. Stream-based Active Learning (AL) approaches address this problem by interactively queryi...
Preprint
Full-text available
Water distribution networks are a key component of modern infrastructure for housing and industry. They transport and distribute water via widely branched networks from sources to consumers. In order to guarantee a working network at all times, the water supply company continuously monitors the network and takes actions when necessary -- e.g. react...
Preprint
Full-text available
Over the last years, word and sentence embeddings have established as text preprocessing for all kinds of NLP tasks and improved performances in these tasks significantly. Unfortunately, it has also been shown that these embeddings inherit various kinds of biases from the training data and thereby pass on biases present in society to NLP solutions....
Preprint
Full-text available
Recent developments in transfer learning have boosted the advancements in natural language processing tasks. The performance is, however, dependent on high-quality, manually annotated training data. Especially in the biomedical domain, it has been shown that one training corpus is not enough to learn generic models that are able to efficiently pred...
Preprint
The notion of concept drift refers to the phenomenon that the distribution, which is underlying the observed data, changes over time; as a consequence machine learning models may become inaccurate and need adjustment. Many unsupervised approaches for drift detection rely on measuring the discrepancy between the sample distributions of two time wind...
Preprint
Full-text available
While machine learning models are usually assumed to always output a prediction, there also exist extensions in the form of reject options which allow the model to reject inputs where only a prediction with an unacceptably low certainty would be possible. With the ongoing rise of eXplainable AI, a lot of methods for explaining model predictions hav...
Preprint
Full-text available
Accurate traffic prediction is a key ingredient to enable traffic management like rerouting cars to reduce road congestion or regulating traffic via dynamic speed limits to maintain a steady flow. A way to represent traffic data is in the form of temporally changing heatmaps visualizing attributes of traffic, such as speed and volume. In recent wor...
Article
Full-text available
We present a modelling framework for the investigation of supervised learning in non-stationary environments. Specifically, we model two example types of learning systems: prototype-based learning vector quantization (LVQ) for classification and shallow, layered neural networks for regression tasks. We investigate so-called student–teacher scenario...
Preprint
Full-text available
Over the last years, word and sentence embeddings have established as text preprocessing for all kinds of NLP tasks and improved the performances significantly. Unfortunately, it has also been shown that these embeddings inherit various kinds of biases from the training data and thereby pass on biases present in society to NLP solutions. Many paper...
Article
While machine learning (ML) gives rise to astonishing results in automated systems, it is usually at the cost of large data requirements. This makes many successful algorithms from ML unsuitable for human-machine interaction, where the machine must learn from a small number of training samples that can be provided by a user within a reasonable time...
Preprint
Full-text available
Prediction of movements is essential for successful cooperation with intelligent systems. We propose a model that integrates organized spatial information as given through the moving body's skeletal structure. This inherent structure is exploited in our model through application of Graph Convolutions and we demonstrate how this allows leveraging th...
Article
Decentralization is a central characteristic of biological motor control that allows for fast responses relying on local sensory information. In contrast, the current trend of Deep Reinforcement Learning (DRL) based approaches to motor control follows a centralized paradigm using a single, holistic controller that has to untangle the whole input in...
Article
The automation of quality control in manufacturing has made great strides in recent years, in particular following new developments in machine learning, specifically deep learning, which allow to solve challenging tasks such as visual inspection or quality prediction. Yet, optimum quality control pipelines are often not obvious in specific settings...
Book
Full-text available
Science, technology, and commerce increasingly recognise the importance of ma- chine learning approaches for data-intensive, evidence-based decision making. This is accompanied by increasing numbers of machine learning applications and volumes of data. Nevertheless, the capacities of processing systems or hu- man supervisors or domain experts remai...
Chapter
In complex industrial settings, it is common practice to monitor the operation of machines in order to detect undesired states, adjust maintenance schedules, optimize system performance or collect usage statistics of individual machines. In this work, we focus on estimating the power output of a Combined Heat and Power (CHP) machine of a medium-siz...
Chapter
Many decision making systems deployed in the real world are not static - a phenomenon known as model adaptation takes place over time. The need for transparency and interpretability of AI-based decision models is widely accepted and thus have been worked on extensively. Usually, explanation methods assume a static system that has to be explained. E...
Chapter
Neural Style Transfer has been successfully applied in the creative process for generating novel artistic 2D images by transferring the style of a painting to an existing content image. These techniques which rely on deep neural networks have been extended to further computational creativity tasks like video, motion and animation stylization. Howev...
Conference Paper
Full-text available
Today, many data are not any longer static but occur as dynamic data streams with high velocity, variability and volume. This leads to new challenges to be addressed by novel or adapted algorithms. In this tutorial we provide an introduction into the field of streaming data analysis summarizing its major characteristics and highlighting important r...
Preprint
Full-text available
Detecting drifts in data is essential for machine learning applications, as changes in the statistics of processed data typically has a profound influence on the performance of trained models. Most of the available drift detection methods require access to true labels during inference time. In a real-world scenario, true labels usually available on...
Article
Differentiable neural computers (DNCs) extend artificial neural networks with an explicit memory without interference, thus enabling the model to perform classic computation tasks, such as graph traversal. However, such models are difficult to train, requiring long training times and large datasets. In this work, we achieve some of the computationa...
Article
Memory-augmented neural networks equip a recurrent neural network with an explicit memory to support tasks that require information storage without interference over long times. A key motivation for such research is to perform classic computation tasks, such as parsing. However, memory-augmented neural networks are notoriously hard to train, requir...
Article
When training automated systems, it has been shown to be beneficial to adapt the representation of data by learning a problem-specific metric. This metric is global. We extend this idea and, for the widely used family of k nearest neighbors algorithms, develop a method that allows learning locally adaptive metrics. These local metrics not only impr...
Article
The increasing use of machine learning in practice and legal regulations like EU’s GDPR cause the necessity to be able to explain the prediction and behavior of machine learning models. A prominent example of particularly intuitive explanations of AI models in the context of decision making are counterfactual explanations. Yet, it is still an open...
Preprint
Full-text available
Even though deep neural networks succeed on many different tasks including semantic segmentation, they lack on robustness against adversarial examples. To counteract this exploit, often adversarial training is used. However, it is known that adversarial training with weak adversarial attacks (e.g. using the Fast Gradient Method) does not improve th...
Article
Motivation: Innovative microfluidic systems carry the promise to greatly facilitate spatio-temporal analysis of single cells under well-defined environmental conditions, allowing novel insights into population heterogeneity and opening new opportunities for fundamental and applied biotechnology. Microfluidics experiments, however, are accompanied...
Preprint
Transparency is an essential requirement of machine learning based decision making systems that are deployed in real world. Often, transparency of a given system is achieved by providing explanations of the behavior and predictions of the given system. Counterfactual explanations are a prominent instance of particular intuitive explanations of deci...
Preprint
Full-text available
Memory-augmented neural networks equip a recurrent neural network with an explicit memory to support tasks that require information storage without interference over long times. A key motivation for such research is to perform classic computation tasks, such as parsing. However, memory-augmented neural networks are notoriously hard to train, requir...
Preprint
Full-text available
In complex industrial settings, it is common practice to monitor the operation of machines in order to detect undesired states, adjust maintenance schedules, optimize system performance or collect usage statistics of individual machines. In this work, we focus on estimating the power output of a Combined Heat and Power (CHP) machine of a medium-siz...
Preprint
Many decision making systems deployed in the real world are not static - a phenomenon known as model adaptation takes place over time. The need for transparency and interpretability of AI-based decision models is widely accepted and thus have been worked on extensively. Usually, explanation methods assume a static system that has to be explained. E...
Article
Full-text available
Reliable object tracking that is based on video data constitutes an important challenge in diverse areas, including, among others, assisted surgery. Particle filtering offers a state-of-the-art technology for this challenge. Becaise a particle filter is based on a probabilistic model, it provides explicit likelihood values; in theory, the question...
Preprint
Full-text available
Fairness and explainability are two important and closely related requirements of decision making systems. While ensuring and evaluating fairness as well as explainability of decision masking systems has been extensively studied independently, only little effort has been investigated into studying fairness of explanations on their own - i.e. the ex...
Book
The multi-volume set LNAI 12975 until 12979 constitutes the refereed proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2021, which was held during September 13-17, 2021. The conference was originally planned to take place in Bilbao, Spain, but changed to an online event due to the COVID-19 pa...
Book
The multi-volume set LNAI 12975 until 12979 constitutes the refereed proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2021, which was held during September 13-17, 2021. The conference was originally planned to take place in Bilbao, Spain, but changed to an online event due to the COVID-19 pa...
Chapter
Full-text available
Collections of text documents such as product reviews and microblogs often evolve over time. In practice, however, classifiers trained on them are updated infrequently, leading to performance degradation over time. While approaches for automatic drift detection have been proposed, they were often designed for low-dimensional sensor data, and it is...
Preprint
Full-text available
Machine learning is a double-edged sword: it gives rise to astonishing results in automated systems, but at the cost of tremendously large data requirements. This makes many successful algorithms from machine learning unsuitable for human-machine interaction, where the machine must learn from a small number of training samples that can be provided...
Article
The recent surge of interest in explainability in artificial intelligence (XAI) is propelled by not only technological advancements in machine learning, but also by regulatory initiatives to foster transparency in algorithmic decision making. In this article, we revise the current concept of explainability and identify three limitations: passive ex...
Article
Full-text available
Learning vector quantization (LVQ) constitutes a very popular machine learning technology with applications, for example, in biomedical data analysis, predictive maintenance/quality as well as product individualization. Albeit probabilistic LVQ variants exist, its deterministic counterparts are often preferred due to their better efficiency. The la...
Preprint
The notion of concept drift refers to the phenomenon that the distribution, which is underlying the observed data, changes over time. We are interested in an identification of those features, that are most relevant for the observed drift. We distinguish between drift inducing features, for which the observed feature drift cannot be explained by any...
Preprint
When training automated systems, it has been shown to be beneficial to adapt the representation of data by learning a problem-specific metric. This metric is global. We extend this idea and, for the widely used family of k nearest neighbors algorithms, develop a method that allows learning locally adaptive metrics. To demonstrate important aspects...
Preprint
Full-text available
Motivation: Innovative microfluidic systems carry the promise to greatly facilitate spatio-temporal analysis of single cells under well-defined environmental conditions, allowing novel insights into population heterogeneity and opening new opportunities for fundamental and applied biotechnology. Microfluidics experiments, however, are accompanied b...
Technical Report
Full-text available
This strategic paper highlights selected research initiatives and success stories of technology transfer in the domain of artificial intelligence that have been driven by researchers in North Rhine-Westphalia (NRW). It was inspired by a round table on Artificial Intelligence (AI) initiated by the Ministry of Culture and Science (MKW) of NRW.
Chapter
Recently, machine learning techniques are often applied in real world scenarios where learning signals are provided as a stream of data points, and models need to be adapted online according to the current information. A severe problem of such settings consists in the fact that the underlying data distribution might change over time and concept dri...
Chapter
The increasing deployment of machine learning as well as legal regulations such as EU’s GDPR cause a need for user-friendly explanations of decisions proposed by machine learning models. Counterfactual explanations are considered as one of the most popular techniques to explain a specific decision of a model. While the computation of “arbitrary” co...
Chapter
The notion of concept drift refers to the phenomenon that the distribution, which is underlying the observed data, changes over time; as a consequence machine learning models may become inaccurate and need adjustment. In this paper we present a novel method to describe concept drift as a whole by means of flows, i.e. the change of direction and mag...
Preprint
With the increasing deployment of machine learning systems in practice, transparency and explainability have become serious issues. Contrastive explanations are considered to be useful and intuitive, in particular when it comes to explaining decisions to lay people, since they mimic the way in which humans explain. Yet, so far, comparably little re...
Preprint
Full-text available
Differentiable neural computers extend artificial neural networks with an explicit memory without interference, thus enabling the model to perform classic computation tasks such as graph traversal. However, such models are difficult to train, requiring long training times and large datasets. In this work, we achieve some of the computational capabi...
Conference Paper
Machine learning algorithms using deep architectures have been able to implement increasingly powerful and successful models. However, they also become increasingly more complex, more difficult to comprehend and easier to fool. So far, most methods in the literature investigate the decision of the model for a single given input datum. In this paper...
Preprint
The notion of concept drift refers to the phenomenon that the distribution, which is underlying the observed data, changes over time; as a consequence machine learning models may become inaccurate and need adjustment. While there do exist methods to detect concept drift or to adjust models in the presence of observed drift, the question of explaini...
Article
Full-text available
Convolutional neural networks (CNNs) are deep learning frameworks which are well known for their notable performance in classification tasks. Hence, many skeleton-based action recognition and segmentation (SBARS) algorithms benefit from them in their designs. However, a shortcoming of such applications is the general lack of spatial relationships b...
Preprint
Full-text available
We present a modelling framework for the investigation of supervised learning in non-stationary environments. Specifically, we model two example types of learning systems: prototype-based Learning Vector Quantization (LVQ) for classification and shallow, layered neural networks for regression tasks. We investigate so-called student teacher scenario...
Chapter
Full-text available
Convolutional neural networks have been used to achieve a string of successes during recent years, but their lack of interpretability remains a serious issue. Adversarial examples are designed to deliberately fool neural networks into making any desired incorrect classification, potentially with very high certainty. Several defensive approaches inc...