Refine
H-BRS Bibliography
- yes (86)
Departments, institutes and facilities
- Fachbereich Informatik (86) (remove)
Document Type
- Conference Object (34)
- Article (20)
- Preprint (12)
- Report (7)
- Research Data (3)
- Doctoral Thesis (3)
- Book (monograph, edited volume) (2)
- Contribution to a Periodical (2)
- Master's Thesis (2)
- Working Paper (1)
Year of publication
- 2020 (86) (remove)
Keywords
- Quality diversity (3)
- Usable Security (3)
- post-buckling (3)
- ARIMA (2)
- Autoencoder (2)
- Automatic Short Answer Grading (2)
- Bayesian optimization (2)
- Black-Box Optimization (2)
- Deep Learning (2)
- Domestic Robots (2)
- Evolutionary Computation (2)
- Evolutionary computation (2)
- Human-Centered Robotics (2)
- Hyper-parameter Tuning (2)
- Learning and Adaptive Systems (2)
- Scale Tuning (2)
- computer vision (2)
- confidence level (2)
- data filtering (2)
- neural network (2)
- nonlinear stability (2)
- object detection (2)
- robotics (2)
- short-term load forecasting (2)
- 2D Level Design (1)
- 3D interfaces (1)
- AMD Family 15h (1)
- Active Learning (1)
- Aerodynamics (1)
- Algorithmen (1)
- Algorithmus (1)
- Apprenticeship Learning (1)
- Ausbreitung (1)
- Authentication (1)
- Automated design (1)
- BERT (1)
- BPMS (1)
- Basis set (1)
- Bayesian Deep Learning (1)
- Berechenbarkeit (1)
- Blockchain (1)
- CPUID instruction (1)
- Cache-independent (1)
- Calibration (1)
- Chloroquine (1)
- Clusteranalyse (1)
- Co-located Collaboration (1)
- Cognition (1)
- Collaborating industrial robots (1)
- Compliant Manipulation (1)
- Computational Fluid Dynamics (1)
- Computational fluid dynamics (1)
- Computer Vision (1)
- Computer-supported Cooperative Work (1)
- Connectivity in rural areas (1)
- Covert channel (1)
- Critical power (1)
- Cross-core (1)
- Cryptography (1)
- Deskriptive Datenanalyse (1)
- Digital common goods (1)
- Digitisation (1)
- Dimensionsreduktion (1)
- Drahtloses lokales Netz (1)
- ELMo (1)
- Embedded system (1)
- Eriodictyol (1)
- Evolutionary optimization (1)
- Executive functions (1)
- Facial Emotion Recognition (1)
- Feature Model (1)
- Filtering (1)
- Functional safety (1)
- GPT (1)
- GPT-2 (1)
- Gaussian processes (1)
- Group Behavior (1)
- Groupware (1)
- Hydroxychloroquine (1)
- IT professionals (1)
- Image Classification (1)
- Information hiding (1)
- Informationskomplexität (1)
- Instruction scheduling (1)
- Interferenz (1)
- Komplexitätsklassen (1)
- Lattice Boltzmann Method (1)
- Laufzeit-Komplexität (1)
- Learning analytics (1)
- Learning data mining (1)
- Level-of-Detail (1)
- Maker space (1)
- Multi-Solution Optimization (1)
- Multi-objective optimization (1)
- Multimodal optimization (1)
- Multithreaded and multicore architecture (1)
- NIR-point sensor (1)
- Network simulation verification (1)
- OER (1)
- Object Detection (1)
- Older adults (1)
- Open source software (1)
- Out Of Distribution (OOD) data (1)
- Password (1)
- Performance profiling (1)
- Phenotypic niching (1)
- Physical activity (1)
- Probabilistic model (1)
- Proof-of-Stake (1)
- Proof-of-Work (1)
- Quality Diversity (1)
- Re-authentication (1)
- Relative Energies (1)
- Rendering (1)
- Risk-based Authentication (1)
- Risk-based Authentication (RBA) (1)
- Robot Perception (1)
- SARS-CoV-2 (1)
- Self-motion perception (1)
- Signal (1)
- Silmitasertib (1)
- Skin detection (1)
- Smart InGaAs camera-system (1)
- Surrogate Modeling (1)
- Surrogate models (1)
- Task Frame Formalism (1)
- Transfer Learning (1)
- Two-factor Authentication (1)
- Ultrasonic array (1)
- Uncertainty Estimation (1)
- Uncertainty Quantification (1)
- Unknown parameter degradation (1)
- Usable Privacy (1)
- User Roles (1)
- Valproic acid (1)
- WWW (1)
- Web components (1)
- WiFi-based Long Distance networks (1)
- Workflow (1)
- YAWL (1)
- Young adults (1)
- asset transfer (1)
- automated sensor-screening (1)
- autonomous driving (1)
- bicausal diagnostic Bond Graphs (1)
- blockchain (1)
- caching (1)
- complete basis set limit (1)
- concrete plate (1)
- conformations (1)
- constraint relaxation (1)
- constructive process deviance (1)
- control architectures (1)
- convolutional neural networks (1)
- cooperative path planning (1)
- cryptocurrency (1)
- curved shell (1)
- deep learning (1)
- designing air flow (1)
- diversity (1)
- drugs (1)
- dynamics (1)
- energy (1)
- failure prognostic (1)
- feature discovery (1)
- felt obligations (1)
- finite element method (1)
- general plate theory (1)
- genetic neutrality (1)
- global illumination (1)
- graphene oxide powder (1)
- graphene oxide powders (1)
- haptics (1)
- high diagnostic coverage and reliability (1)
- high dynamic range resistance readout (1)
- iOER (1)
- instance segmentation (1)
- long short-term memory (1)
- mesoscopic agents (1)
- mp2 (1)
- multi-layer display (1)
- multi-objective optimization (1)
- multimodal optimization (1)
- nano-composite (1)
- navigation (1)
- neural networks (1)
- optimized geometries (1)
- parameter estimation (1)
- payment protocol (1)
- phenotypic diversity (1)
- phenotypic feature (1)
- phenotypic niching (1)
- porous material (1)
- predictive maintenance (1)
- process (1)
- propan-2-ol (1)
- refined beam theory (1)
- reinforcement learning (1)
- remaining useful life (1)
- repeated trend projection (1)
- robot action diagnosability (1)
- robot control (1)
- robot execution failures (1)
- security (1)
- semantic image seg-mentation (1)
- semiconducting metal oxide gas sensor array (1)
- shell theory (1)
- small molecule (1)
- stereoscopic vision (1)
- stiffeners (1)
- strukturelle Komplexität von Daten (1)
- surrogate assisted phenotypic niching (1)
- surrogate models (1)
- task models (1)
- telepresence (1)
- un-manned aerial vehicle (1)
- uncertainties (1)
- unmanned ground vehicle (1)
- usability (1)
- usable secure email (1)
- user interface design (1)
- water dimer (1)
- wavelet (1)
- wind nuisance threshold (1)
- Wavenet (1)
Reinforcement learning (RL) algorithms should learn as much as possible about the environment but not the properties of the physics engines that generate the environment. There are multiple algorithms that solve the task in a physics engine based environment but there is no work done so far to understand if the RL algorithms can generalize across physics engines. In this work, we compare the generalization performance of various deep reinforcement learning algorithms on a variety of control tasks. Our results show that MuJoCo is the best engine to transfer the learning to other engines. On the other hand, none of the algorithms generalize when trained on PyBullet. We also found out that various algorithms have a promising generalizability if the effect of random seeds can be minimized on their performance.
Facial emotion recognition is the task to classify human emotions in face images. It is a difficult task due to high aleatoric uncertainty and visual ambiguity. A large part of the literature aims to show progress by increasing accuracy on this task, but this ignores the inherent uncertainty and ambiguity in the task. In this paper we show that Bayesian Neural Networks, as approximated using MC-Dropout, MC-DropConnect, or an Ensemble, are able to model the aleatoric uncertainty in facial emotion recognition, and produce output probabilities that are closer to what a human expects. We also show that calibration metrics show strange behaviors for this task, due to the multiple classes that can be considered correct, which motivates future work. We believe our work will motivate other researchers to move away from Classical and into Bayesian Neural Networks.
In this paper we introduce the Perception for Autonomous Systems (PAZ) software library. PAZ is a hierarchical perception library that allow users to manipulate multiple levels of abstraction in accordance to their requirements or skill level. More specifically, PAZ is divided into three hierarchical levels which we refer to as pipelines, processors, and backends. These abstractions allows users to compose functions in a hierarchical modular scheme that can be applied for preprocessing, data-augmentation, prediction and postprocessing of inputs and outputs of machine learning (ML) models. PAZ uses these abstractions to build reusable training and prediction pipelines for multiple robot perception tasks such as: 2D keypoint estimation, 2D object detection, 3D keypoint discovery, 6D pose estimation, emotion classification, face recognition, instance segmentation, and attention mechanisms.
Dieses Buch bietet einen leicht verständlichen Einstieg in die Thematik des Data Minings und der Prädiktiven Analyseverfahren. Als Methodensammlung gedacht, bietet es zu jedem Verfahren zunächst eine kurze Darstellung der Theorie und erklärt die zum Verständnis notwendigen Formeln. Es folgt jeweils eine Illustration der Verfahren mit Hilfe von Beispielen, die mit dem Programmpaket R erarbeitet werden.
Zum Abschluss wird eine einfache Möglichkeit präsentiert, mit der die Performancewerte verschiedener Verfahren mit statistischen Mitteln verglichen werden können. Zum Einsatz kommen hierbei geeignete Grafiken und Konfidenzintervalle.
Das Buch verzichtet nicht auf Theorie, es präsentiert jedoch so wenig Theorie wie möglich, aber so viel wie nötig und ist somit optimal für Studium und Selbststudium geeignet.