Refine
Document Type
- Conference Proceeding (75) (remove)
Conference Type
- Konferenzartikel (50)
- Konferenz-Abstract (16)
- Sonstiges (5)
- Konferenz-Poster (2)
- Konferenzband (2)
Keywords
- RoboCup (12)
- Machine Learning (8)
- Deep Leaning (4)
- Generative Adversarial Network (3)
- Robustness (3)
- Computer Vision (2)
- Heart rhythm model (2)
- Kalman Filter (2)
- Mikroelektronik (2)
- Modeling and simulation (2)
- Neural networks (2)
- Stability (2)
- accountability (2)
- artificial intelligence (2)
- atrial fibrillation (2)
- autoattack (2)
- cardiac ablation (2)
- efficient training (2)
- explainability (2)
- fairness (2)
- heart rhythm model (2)
- interactive visualization (2)
- machine learning (2)
- responsibility (2)
- trust (2)
- understandability (2)
- 3D print (1)
- 3D-Modelling (1)
- 5G (1)
- AV nodal reentry tachycardia (1)
- AV reentrant tachycardia (1)
- Adversarial Attacks (1)
- Adversarial Robustness (1)
- Aliasing (1)
- Artificial Intelligence (1)
- Bioimpedance measurement (1)
- Blockchain (1)
- CNNs (1)
- Cardiac Resynchronization Therapy (1)
- Challenges in Action Recognition (1)
- Collaboration of Academia and Industry (1)
- Cryoballoon catheter ablation (1)
- Deep Learning (1)
- Demand side flexibility (1)
- Digitale Turschilder (1)
- Digitalization (1)
- Drehstrom (1)
- E-Ink (1)
- E-Paper (1)
- EKF-SLAM (1)
- Edge AI (1)
- Eigenvalues (1)
- Embedded AI (1)
- Embedded Systems (1)
- Energy Harvesting (1)
- Energy management (1)
- Energy systems modeling (1)
- Esophageal catheter (1)
- Federated Learning (1)
- Gleichstrom (1)
- Heart Rhythm Simulation (1)
- Hemodynamic monitoring (1)
- Herzrhythmusmodell (1)
- His-Bundle Pacing (1)
- Hochspannung (1)
- InceptionTime (1)
- Kryoballonkatheter (1)
- LPWAN (1)
- Left Atrial Appendage Closure (1)
- Low-Cost Füllstandssensor (1)
- Low-Power (1)
- MLOps (1)
- Machine learning (1)
- Mode Collapse (1)
- Model Calibration (1)
- Model Search (1)
- Modellierung und Simulation (1)
- NB-IoT (1)
- NFC (1)
- Network Test (1)
- Nyquist-Shannon (1)
- Octave Convolution (1)
- Optimization and control (1)
- Pattern Recognition (1)
- Physiological Pacing (1)
- Predictive Maintenance (1)
- Pulmonalvenenisolation (1)
- Regularization (1)
- Representation Learning (1)
- ResNet (1)
- Road-Quality Prediction (1)
- Sampling (1)
- Second-order Optimization (1)
- Security (1)
- Smart Gardening (1)
- Smart Home (1)
- Spinal cord stimulation (1)
- Supraventricular tachycardia (1)
- Time-series Classification (1)
- TinyML (1)
- Traceability (1)
- Unsupervised Conditional Training (1)
- Unsupervised Learning (1)
- Variational Autoencoders (1)
- Vorhofflimmern (1)
- Wireless Sensor Nodes (1)
- adversarial (1)
- atrial flutter (1)
- attribute manipulation (1)
- autoML (1)
- benchmarking (1)
- biomechanical stimulation (1)
- cifar (1)
- cryptography (1)
- cybersecurity (1)
- deep learning (1)
- defense (1)
- echocardiography (1)
- face editing (1)
- fourier (1)
- gan (1)
- heart rhythm simulation (1)
- imagenet (1)
- impedance cardiography (1)
- lid (1)
- mahalanobis (1)
- natürliche Leistung (1)
- neural architecture search (1)
- pruning (1)
- pulmonary vein isolation (1)
- sparse backpropagation (1)
- spectral defense (1)
- spectraldefense (1)
- style transfer (1)
- ventricular tachycardia (1)
- übertragbare Wirkleistung (1)
Institute
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (75) (remove)
Open Access
- Open Access (75) (remove)
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.