Denny Mattern
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Denny Mattern has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Adrian Paschke
Fraunhofer Institute for Open Communication Systems
3 shared publications - Marko Harasic
Fraunhofer FOKUS,Berlin,Germany
2 shared publications Agnès Voisard
Freie Universität Berlin, Institute of Computer Science, Berlin, Germany
1 shared publication- Darya Martyniuk
Fraunhofer FOKUS Berlin Germany
1 shared publication - Fabian Bergmann1 shared publication
- Felix-Sebastian Keese
Data Analytics Center, Fraunhofer Institute for Open Communication Systems, Berlin, Germany
1 shared publication
Latest Publications
- Open Access
- 25 August 2023
- Published by Springer Nature in International Journal of Data Science and Analytics
- Vol. 17 (4) , 337-357
Recent advances and future challenges in federated recommender systems
Recommender systems are an integral part of modern-day user experience. They understand their preferences and support them in discovering meaningful content by creating personalized recommendations. With governmental regulations and growing users’ privacy awareness, capturing the required data is a challenging task today. Federated learning is a novel approach for distributed machine learning, which keeps users’ privacy in mind. In federated learning, the participating peers train a global model together, but personal data never leave the device or silo. Recently, the combination of recommender systems and federated learning gained a growing interest in the research community. A new recommender type named federated recommender system was created. This survey presents a comprehensive overview of current research in that field, including federated algorithms, architectural designs, and privacy mechanisms in the federated setting. Furthermore, it points out recent challenges and interesting future directions for further research.
- 25 August 2023
- Published by Springer Nature in International Journal of Data Science and Analytics
- Vol. 17 (4) , 337-357
Open AccessRecent advances and future challenges in federated recommender systems
Recommender systems are an integral part of modern-day user experience. They understand their preferences and support them in discovering meaningful content by creating personalized recommendations. With governmental regulations and growing users’ privacy awareness, capturing the required data is a challenging task today. Federated learning is a novel approach for distributed machine learning, which keeps users’ privacy in mind. In federated learning, the participating peers train a global model together, but personal data never leave the device or silo. Recently, the combination of recommender systems and federated learning gained a growing interest in the research community. A new recommender type named federated recommender system was created. This survey presents a comprehensive overview of current research in that field, including federated algorithms, architectural designs, and privacy mechanisms in the federated setting. Furthermore, it points out recent challenges and interesting future directions for further research.
- Open Access
- 17 August 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (16) , 8239
A Review on AI for Smart Manufacturing: Deep Learning Challenges and Solutions
Artificial intelligence (AI) has been successfully applied in industry for decades, ranging from the emergence of expert systems in the 1960s to the wide popularity of deep learning today. In particular, inexpensive computing and storage infrastructures have moved data-driven AI methods into the spotlight to aid the increasingly complex manufacturing processes. Despite the recent proverbial hype, however, there still exist non-negligible challenges when applying AI to smart manufacturing applications. As far as we know, there exists no work in the literature that summarizes and reviews the related works for these challenges. This paper provides an executive summary on AI techniques for non-experts with a focus on deep learning and then discusses the open issues around data quality, data secrecy, and AI safety that are significant for fully automated industrial AI systems. For each challenge, we present the state-of-the-art techniques that provide promising building blocks for holistic industrial AI solutions and the respective industrial use cases from several domains in order to better provide a concrete view of these techniques. All the examples we reviewed were published in the recent ten years. We hope this paper can provide the readers with a reference for further studying the related problems.
- 17 August 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (16) , 8239
Open AccessA Review on AI for Smart Manufacturing: Deep Learning Challenges and Solutions
Artificial intelligence (AI) has been successfully applied in industry for decades, ranging from the emergence of expert systems in the 1960s to the wide popularity of deep learning today. In particular, inexpensive computing and storage infrastructures have moved data-driven AI methods into the spotlight to aid the increasingly complex manufacturing processes. Despite the recent proverbial hype, however, there still exist non-negligible challenges when applying AI to smart manufacturing applications. As far as we know, there exists no work in the literature that summarizes and reviews the related works for these challenges. This paper provides an executive summary on AI techniques for non-experts with a focus on deep learning and then discusses the open issues around data quality, data secrecy, and AI safety that are significant for fully automated industrial AI systems. For each challenge, we present the state-of-the-art techniques that provide promising building blocks for holistic industrial AI solutions and the respective industrial use cases from several domains in order to better provide a concrete view of these techniques. All the examples we reviewed were published in the recent ten years. We hope this paper can provide the readers with a reference for further studying the related problems.
- Open Access
Variational Quanvolutional Neural Networks with enhanced image encoding
Image classification is an important task in various machine learning applications. In recent years, a number of classification methods based on quantum machine learning and different quantum image encoding techniques have been proposed. In this paper, we study the effect of three different quantum image encoding approaches on the performance of a convolution-inspired hybrid quantum-classical image classification algorithm called quanvolutional neural network (QNN). We furthermore examine the effect of variational - i.e. trainable - quantum circuits on the classification results. Our experiments indicate that some image encodings are better suited for variational circuits. However, our experiments show as well that there is not one best image encoding, but that the choice of the encoding depends on the specific constraints of the application.
Open AccessVariational Quanvolutional Neural Networks with enhanced image encoding
Image classification is an important task in various machine learning applications. In recent years, a number of classification methods based on quantum machine learning and different quantum image encoding techniques have been proposed. In this paper, we study the effect of three different quantum image encoding approaches on the performance of a convolution-inspired hybrid quantum-classical image classification algorithm called quanvolutional neural network (QNN). We furthermore examine the effect of variational - i.e. trainable - quantum circuits on the classification results. Our experiments indicate that some image encodings are better suited for variational circuits. However, our experiments show as well that there is not one best image encoding, but that the choice of the encoding depends on the specific constraints of the application.
- Open Access
- 30 June 2020
- Published by Springer Nature in Communications Biology
- Vol. 3 (1) , 1-13
Estimating and abstracting the 3D structure of feline bones using neural networks on X-ray (2D) images
Computing 3D bone models using traditional Computed Tomography (CT) requires a high-radiation dose, cost and time. We present a fully automated, domain-agnostic method for estimating the 3D structure of a bone from a pair of 2D X-ray images. Our triplet loss-trained neural network extracts a 128-dimensional embedding of the 2D X-ray images. A classifier then finds the most closely matching 3D bone shape from a predefined set of shapes. Our predictions have an average root mean square (RMS) distance of 1.08 mm between the predicted and true shapes, making our approach more accurate than the average achieved by eight other examined 3D bone reconstruction approaches. Each embedding extracted from a 2D bone image is optimized to uniquely identify the 3D bone CT from which the 2D image originated and can serve as a kind of fingerprint of each bone; possible applications include faster, image content-based bone database searches for forensic purposes.
- 30 June 2020
- Published by Springer Nature in Communications Biology
- Vol. 3 (1) , 1-13
Open AccessEstimating and abstracting the 3D structure of feline bones using neural networks on X-ray (2D) images
Computing 3D bone models using traditional Computed Tomography (CT) requires a high-radiation dose, cost and time. We present a fully automated, domain-agnostic method for estimating the 3D structure of a bone from a pair of 2D X-ray images. Our triplet loss-trained neural network extracts a 128-dimensional embedding of the 2D X-ray images. A classifier then finds the most closely matching 3D bone shape from a predefined set of shapes. Our predictions have an average root mean square (RMS) distance of 1.08 mm between the predicted and true shapes, making our approach more accurate than the average achieved by eight other examined 3D bone reconstruction approaches. Each embedding extracted from a 2D bone image is optimized to uniquely identify the 3D bone CT from which the 2D image originated and can serve as a kind of fingerprint of each bone; possible applications include faster, image content-based bone database searches for forensic purposes.