Refine
Document Type
- Conference Proceeding (17) (remove)
Conference Type
- Konferenzartikel (13)
- Konferenz-Abstract (3)
- Sonstiges (1)
Language
- English (17) (remove)
Has Fulltext
- no (17) (remove)
Is part of the Bibliography
- yes (17) (remove)
Keywords
- machine learning (3)
- Artificial Intelligence (2)
- Deep Leaning (2)
- accountability (2)
- artificial intelligence (2)
- explainability (2)
- fairness (2)
- interactive visualization (2)
- responsibility (2)
- trust (2)
Institute
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (7)
- Fakultät Wirtschaft (W) (4)
- IMLA - Institute for Machine Learning and Analytics (3)
- Fakultät Maschinenbau und Verfahrenstechnik (M+V) (2)
- Fakultät Medien (M) (ab 22.04.2021) (2)
- INES - Institut für nachhaltige Energiesysteme (2)
- ivESK - Institut für verlässliche Embedded Systems und Kommunikationselektronik (2)
- Fakultät Elektrotechnik und Informationstechnik (E+I) (bis 03/2019) (1)
Open Access
- Diamond (17) (remove)
Convolutional neural networks (CNN) define the state-of-the-art solution on many perceptual tasks. However, current CNN approaches largely remain vulnerable against adversarial perturbations of the input that have been crafted specifically to fool the system while being quasi-imperceptible to the human eye. In recent years, various approaches have been proposed to defend CNNs against such attacks, for example by model hardening or by adding explicit defence mechanisms. Thereby, a small “detector” is included in the network and trained on the binary classification task of distinguishing genuine data from data containing adversarial perturbations. In this work, we propose a simple and light-weight detector, which leverages recent findings on the relation between networks’ local intrinsic dimensionality (LID) and adversarial attacks. Based on a re-interpretation of the LID measure and several simple adaptations, we surpass the state-of-the-art on adversarial detection by a significant m argin and reach almost perfect results in terms of F1-score for several networks and datasets. Sources available at: https://github.com/adverML/multiLID
Artificial Intelligence (AI) can potentially transform many aspects of modern society in various ways, including automation of tasks, personalization of products and services, diagnosis of diseases and their treatment, transportation, safety, and security in public spaces, etc. Recently, AI technology has been transforming the financial industry, offering new ways to analyse data and automate processes, reduce costs, increase efficiency, and provide more personalized services to customers. However, it also raised important ethical and regulatory questions that need to be addressed by the industry and society as a whole. The aim of the Erasmus+ project Transversal Skills in Applied Artificial Intelligence - TSAAI (KA220-HED - Cooperation Partnerships in higher education) has been to establish a training platform that will incorporate teaching guidelines based on a curriculum covering different areas of application of AI technology. In this work, we will focus on applying AI models in the financial and insurance sectors.
Training deep neural networks using backpropagation is very memory and computationally intensive. This makes it difficult to run on-device learning or fine-tune neural networks on tiny, embedded devices such as low-power micro-controller units (MCUs). Sparse backpropagation algorithms try to reduce the computational load of on-device learning by training only a subset of the weights and biases. Existing approaches use a static number of weights to train. A poor choice of this so-called backpropagation ratio limits either the computational gain or can lead to severe accuracy losses. In this paper we present TinyProp, the first sparse backpropagation method that dynamically adapts the back-propagation ratio during on-device training for each training step. TinyProp induces a small calculation overhead to sort the elements of the gradient, which does not significantly impact the computational gains. TinyProp works particularly well on fine-tuning trained networks on MCUs, which is a typical use case for embedded applications. For typical datasets from three datasets MNIST, DCASE2020 and CIFAR10, we are 5 times faster compared to non-sparse training with an accuracy loss of on average 1%. On average, TinyProp is 2.9 times faster than existing, static sparse backpropagation algorithms and the accuracy loss is reduced on average by 6 % compared to a typical static setting of the back-propagation ratio.
Harnessing the overall benefits of the latest advancements in artificial intelligence (AI) requires the extensive collaboration of academia and industry. These collaborations promote innovation and growth while enforcing the practical usefulness of newer technologies in real life. The purpose of this article is to outline the challenges faced during cross-collaboration between academia and industry. These challenges are also inspected with the help of an ongoing project titled “Quality Assurance of Machine Learning Applications” (Q-AMeLiA), in which three universities cooperate with five industry partners to make the product risk of AI-based products visible. Further, we discuss the hurdles and the key challenges in machine learning (ML) technology transformation from academia to industry based on robustness, simplicity, and safety. These challenges are an outcome of the lack of common standards, metrics, and missing regulatory considerations when state-of-the-art (SOTA) technology is developed in academia. The use of biased datasets involves ethical concerns that might lead to unfair outcomes when the ML model is deployed in production. The advancement of AI in small and medium sized enterprises (SMEs) requires more in terms of common tandardization of concepts rather than algorithm breakthroughs. In this paper, in addition to the general challenges, we also discuss domain specific barriers for five different domains i.e., object detection, hardware benchmarking, continual learning, action recognition, and industrial process automation, and highlight the steps necessary for successfully managing the cross-sectoral collaborations between academia and industry.
We aim to debate and eventually be able to carefully judge how realistic the following statement of a young computer scientist is: “I would like to become an ethical correctly acting offensive cybersecurity expert”. The objective of this article is not to judge what is good and what is wrong behavior nor to present an overall solution to ethical dilemmas. Instead, the goal is to become aware of the various personal moral dilemmas a security expert may face during his work life. For this, a total of 14 cybersecurity students from HS Offenburg were asked to evaluate several case studies according to different ethical frameworks. The results and particularities are discussed, considering different ethical frameworks. We emphasize, that different ethical frameworks can lead to different preferred actions and that the moral understanding of the frameworks may differ even from student to student.
The importance of machine learning has been increasing dramatically for years. From assistance systems to production optimisation to support the health sector, almost every area of daily life and industry comes into contact with machine learning. Besides all the benefits that ML brings, the lack of transparency and the difficulty in creating traceability pose major risks. While there are solutions that make the training of machine learning models more transparent, traceability is still a major challenge. Ensuring the identity of a model is another challenge. Unnoticed modification of a model is also a danger when using ML. One solution is to create an ML birth certificate and an ML family tree secured by blockchain technology. Important information about training and changes to the model through retraining can be stored in a blockchain and accessed by any user to create more security and traceability about an ML model.
In the development of new vehicles, increasing customer comfort requirements and rising safety regulations often result in an increase in weight. Nevertheless, in order to be able to meet the demand for reduced fuel consumption, it is necessary within product development process to implement complex and filigree lightweight structures. This contribution therefore addresses the potential of generatively developed components for fiber-reinforced additive manufacturing (FRAM). Currently, several commercial systems for this application are available on the market. Therefore, a comparison of the systems is first made to determine a suitable system. Then, a highly stressed and safety-relevant chassis component of a race car is generatively designed and manufactured using FRAM. A matrix with short fiber reinforcement and additional long fiber reinforcement with carbon fibers is applied. Finally, tensile tests are carried out to check the mechanical properties. In addition, relevant properties such as weight and cost are obtained in order to be able to compare them with conventionally developed and manufactured components.
Learning to Walk With Toes
(2020)
This paper explains how a model-free (with respect to the robot model and the behavior to learn) approach can facilitate learning to walk from scratch. It is applied to a simulated Nao robot with toes. Results show an improvement of 30% in speed compared to a model without toes and also compared to our model-based approach, but with less stability.
The use of artificial intelligence continues to impact a broad variety of domains, application areas, and people. However, interpretability, understandability, responsibility, accountability, and fairness of the algorithms' results - all crucial for increasing humans' trust into the systems - are still largely missing. The purpose of this seminar is to understand how these components factor into the holistic view of trust. Further, this seminar seeks to identify design guidelines and best practices for how to build interactive visualization systems to calibrate trust.
Artificial intelligence (AI), and in particular machine learning algorithms, are of increasing importance in many application areas but interpretability and understandability as well as responsibility, accountability, and fairness of the algorithms' results, all crucial for increasing the humans' trust into the systems, are still largely missing. Big industrial players, including Google, Microsoft, and Apple, have become aware of this gap and recently published their own guidelines for the use of AI in order to promote fairness, trust, interpretability, and other goals. Interactive visualization is one of the technologies that may help to increase trust in AI systems. During the seminar, we discussed the requirements for trustworthy AI systems as well as the technological possibilities provided by interactive visualizations to increase human trust in AI.