Institut für Informatik und Computational Science
Refine
Has Fulltext
- no (858) (remove)
Year of publication
Document Type
- Article (556)
- Monograph/Edited Volume (133)
- Doctoral Thesis (120)
- Other (28)
- Part of a Book (12)
- Conference Proceeding (5)
- Preprint (4)
Is part of the Bibliography
- yes (858)
Keywords
- Answer set programming (10)
- answer set programming (8)
- Answer Set Programming (7)
- Machine learning (3)
- formal languages (3)
- monitoring (3)
- security (3)
- Analytical models (2)
- Automata systems (2)
- E-learning (2)
- Equilibrium logic (2)
- Event mapping (2)
- Fault tolerance (2)
- Internet (2)
- Internet of Things (2)
- Lindenmayer systems (2)
- MQTT (2)
- Machine Learning (2)
- Modeling (2)
- Non-monotonic reasoning (2)
- Optimization (2)
- Parameterized complexity (2)
- Preference Handling (2)
- Process mining (2)
- ResNet (2)
- TPACK (2)
- Theory (2)
- bioinformatics (2)
- cooperating systems (2)
- e-learning (2)
- online learning (2)
- radhard design (2)
- reliability (2)
- verification (2)
- (FPGA) (1)
- 2-tag system (1)
- 3D modeling (1)
- 3D visualization (1)
- AODV (1)
- ASIC (1)
- Abstraction (1)
- Access control (1)
- Active evaluation (1)
- Ad hoc routing (1)
- Adaptivity (1)
- Advanced Video Codec (AVC) (1)
- Aggregates (1)
- Algorithm configuration (1)
- Algorithm portfolios (1)
- Android Security (1)
- Android hybrid apps (1)
- Animal building (1)
- Answer Set Solving modulo Theories (1)
- Anti-cancer drugs (1)
- App (1)
- Apps (1)
- Argumentation structure (1)
- Artificial Neuronal Network (1)
- Augmentation (1)
- Augmented and virtual reality (1)
- Automated parallelization (1)
- Automatically controlled windows (1)
- Backdoors (1)
- Barcode (1)
- Batch processing (1)
- Benchmark testing; (1)
- Berliner Modell (1)
- Blind users (1)
- Boolean logic models (1)
- Bot Detection (1)
- Business Process (1)
- Business process intelligence (1)
- CP-Logic (1)
- Campus (1)
- Chipkarten (1)
- Circuit faults (1)
- Clock tree (1)
- Cloud (1)
- Cluster Computing (1)
- Cluster computing (1)
- Code generation (1)
- Codierungstheorie (1)
- Coherent phonons (1)
- Combinatorial multi-objective optimization (1)
- Complex optimization (1)
- Complexity (1)
- Computational complexity (1)
- Computational grid (1)
- Computer security (1)
- Computing with DNA (1)
- Conformant Planning (1)
- Conrad Hal Waddington (1)
- Constraint satisfaction (1)
- Context awareness (1)
- Contextualized learning (1)
- Continuous Testing (1)
- Continuous Versioning (1)
- Convolution (1)
- Course timetabling (1)
- Customer ownership (1)
- D-galactosamine (1)
- DMR (1)
- DNA hairpin formation (1)
- DRMAA (1)
- DRMS (1)
- Data federation (1)
- Database (1)
- Deal of the Day (1)
- Debugging (1)
- Decidability (1)
- Declarative Problem Solving (1)
- Declare (1)
- Deep Learning (1)
- Deep learning (1)
- Denotational semantics (1)
- Design (1)
- Design for testability (DFT) (1)
- Deutschland (1)
- Digitale Medien (1)
- Digitalization (1)
- Double cell upsets (DCUs) (1)
- Dynamical X-ray theory (1)
- E-teaching (1)
- EDC (1)
- EEG (1)
- Edge Computing (1)
- Educational game (1)
- Educational timetabling (1)
- Encoding (1)
- Engines (1)
- Enterprise Architecture (1)
- Entity Linking (1)
- Epigenetic landscape (1)
- Epistemic Logic Programs (1)
- Erklärbarkeit (1)
- Evaluation (1)
- Evolution (1)
- Experimentation (1)
- Explainability (1)
- Explicit negation (1)
- Explore-first Programming (1)
- Extensibility (1)
- Extreme Model-Driven Development (1)
- FEDC (1)
- FPGA (1)
- Fault Localization (1)
- Fault tolerant systems (1)
- Feature extraction (1)
- Fehlererkennung (1)
- Field programmable gate arrays (1)
- Finite automata (1)
- Flip-flops (1)
- Forgetting (1)
- Framework (1)
- Freshmen (1)
- GERBIL (1)
- Geschäftsprozess (1)
- Gesture input (1)
- Graph Convolutional Neural Networks (1)
- Graph Embedding (1)
- Green computing (1)
- Grounded theory (1)
- Grounding Theory (1)
- H.264 (1)
- Hairpin completions (1)
- Hairpin reductions (1)
- Hardware accelerator (1)
- Heat diffusion (1)
- Hierarchically configurable mask register (1)
- Histograms (1)
- Hochschul-Apps (1)
- Hochschul-Cloud (1)
- Hochschullehre (1)
- Https traffic (1)
- Human Factors (1)
- Hurricane Sandy (1)
- Hybrid App (1)
- IaaS (1)
- Identifiers (1)
- Image and video stylization (1)
- Image resolution (1)
- Imperative calculi (1)
- Improving classroom (1)
- Incoherent phonons (1)
- Incremental answer set programming (1)
- Industrie 4.0 (1)
- Industry 4.0 (1)
- Inference (1)
- Information federation (1)
- Information integration (1)
- Information retrieval (1)
- Information security (1)
- Insurance industry (1)
- Integrated circuit modeling (1)
- Interpretability (1)
- Interpretierbarkeit (1)
- Job monitoring (1)
- Job submission (1)
- Kernel (1)
- Kernelization (1)
- Key input (1)
- Knowledge (1)
- Knowledge Management (1)
- Knowledge representation (1)
- Kommunismus (1)
- Künstliche Neuronale Netzwerke (1)
- L systems (1)
- LBA problem (1)
- Landmark visibility (1)
- Learning (1)
- Lehre (1)
- Lernen (1)
- Literature mining (1)
- Load Balancing (1)
- Localization (1)
- Location awareness (1)
- Logic programming (1)
- Low Latency (1)
- Loyalty (1)
- M2M (1)
- Markov processes (1)
- Masking of X-values (1)
- Massenklausuren (1)
- Media in education (1)
- Meta-Programming (1)
- Metric learning (1)
- Minimal perturbation problems (1)
- Mobile Campus Application (1)
- Mobile Learning (1)
- Mobile application (1)
- Mobile devices (1)
- Mobile learning (1)
- Model checking (1)
- Modellierung (1)
- Modelling (1)
- Multi-objective optimization (1)
- Multi-sided platforms (1)
- Multimedia (1)
- Multiple interpretation scheme (1)
- N-temperature model (1)
- NFC (1)
- Nash equilibrium (1)
- Natural language processing (1)
- Natural ventilation (1)
- Network (1)
- Network security (1)
- Neural networks (1)
- Non-Monotonic (1)
- Nonmonotonic reasoning (1)
- OBI (1)
- OCCI (1)
- OSSE (1)
- Open Badge Infrastructure (1)
- Open Badges (1)
- Operation problem (1)
- Optimierung (1)
- Parallel SAT solving (1)
- Parallel job execution time estimation (1)
- Pedagogical issues (1)
- Pedestrian navigation (1)
- Peer-Review (1)
- Performance Evaluation (1)
- Personal Learning Environment (1)
- Personalization (1)
- Pervasive computing (1)
- Pervasive game (1)
- Pervasive learning (1)
- Planar tactile display (1)
- Polarization (1)
- Privacy Protection (1)
- Process (1)
- Process Management (1)
- Process model analysis (1)
- Product lifecycle management (1)
- Professionalisierung (1)
- Programming (1)
- Programming by optimization (1)
- Prototyping (1)
- Prozess (1)
- Prozessmanagement (1)
- Prüfungsoptimierung (1)
- REST (1)
- RSA triangle (1)
- Random access memory (1)
- Ranking (1)
- Reasoning (1)
- Reflexion (1)
- Region of Interest (1)
- Reversibility (1)
- SAMR (1)
- SOA (1)
- SWOT (1)
- SaaSAbstract (1)
- Scalability (1)
- Scale-invariant feature transform (SIFT) (1)
- Scientific images (1)
- Screen reader (1)
- Seamless learning (1)
- Search problems (1)
- Security (1)
- Semantic Interoperability (1)
- Semantic data (1)
- Semantic web (1)
- Semilinearity property (1)
- Sequence embeddings (1)
- Service orientation (1)
- Service-oriented Architecture (1)
- Service-oriented architecture (1)
- Sharing (1)
- Signal processing (1)
- Signaling transduction networks (1)
- Simulation (1)
- Simulations (1)
- Single event effect (1)
- Single event upsets (1)
- Single-event transient (SET) (1)
- Social Media Analysis (1)
- Speicher (1)
- Splicing (1)
- Splicing processor (1)
- Static Analysis (1)
- Statistical relational learning (1)
- Stochastic relational process (1)
- Strong equivalence (1)
- Structural equation modeling (1)
- Studieneinstieg (1)
- Studienorganisation (1)
- Systems biology (1)
- Systems of parallel communicating (1)
- TMR (1)
- Teilnehmerzertifikate (1)
- Temporal Answer Set Solving (1)
- Theory formation (1)
- Thermoelasticity (1)
- Time series (1)
- Tools (1)
- Tracking (1)
- Traffic data (1)
- Tree decomposition (1)
- Treewidth (1)
- Treewidth-aware reductions (1)
- Triple modular redundancy (TMR) (1)
- Tumor types (1)
- Turing machine (1)
- Type and effect systems (1)
- UAV imagery (1)
- UX (1)
- Ubiquitous learning (1)
- Ultrafast dynamics (1)
- Unary languages (1)
- Uniform Access Principle (1)
- University Service Bus (1)
- Usability testing (1)
- User submission pattern (1)
- User-centred design (1)
- Value network (1)
- Verification (1)
- Virtual reality (1)
- Visual metaphor (1)
- Webanwendung (1)
- Wireless Sensor Networks (1)
- Wissen (1)
- Wissensmanagement (1)
- Word embeddings (1)
- X-masking (1)
- X-values (1)
- accepting grammars (1)
- action and change (1)
- activities (1)
- activity (1)
- acute liver failure (1)
- acyclicity properties (1)
- adversarial classification (1)
- algorithm schedules (1)
- algorithms (1)
- analysis (1)
- anti-cancer drugs (1)
- anxiety (1)
- approximate model counting (1)
- architecture (1)
- argument mining (1)
- arousal (1)
- artistic rendering (1)
- asynchrounous design (1)
- authentication (1)
- autism (1)
- automata (1)
- automated driving (1)
- automated guided vehicle routing (1)
- automated planning (1)
- automatic feedback (1)
- behavioral (1)
- behavioral abstraction (1)
- belief merging (1)
- belief revision (1)
- benchmark (1)
- bibliometric analysis (1)
- block representation (1)
- bootstrapping (1)
- brain-computer interface (1)
- bundled data (1)
- camera sensor (1)
- car assembly operations (1)
- cellular automata (1)
- circuit Faults (1)
- citation analysis (1)
- click controller (1)
- clocks (1)
- co-citation analysis (1)
- co-occurrence analysis (1)
- code generation (1)
- coherence relation (1)
- collaborative learning (1)
- combinatorial optimization problems (1)
- combined task and motion planning (1)
- common spatial patterns (1)
- competition (1)
- complex networks (1)
- compliance (1)
- computer science education (1)
- computer vision (1)
- concession (1)
- concurrent checking (1)
- conductive argument (1)
- connective (1)
- connectivity (1)
- consistency (1)
- consistency checking (1)
- consistency measures (1)
- context-free grammar (1)
- context-sensitive (1)
- continuous (1)
- contrast (1)
- controlled vocabularies (1)
- corpus analysis (1)
- correlated errors (1)
- course timetabling (1)
- craters (1)
- crop (1)
- decidability questions (1)
- declarative problem solving (1)
- deep learning (1)
- deep neural networks (1)
- deep residual networks (1)
- degree of non-context-freeness (1)
- degree of non-regularity (1)
- degree of non-regulation (1)
- depression (1)
- design flow (1)
- determinism (1)
- detrending (1)
- developmental systems (1)
- diagnosis (1)
- domain-specific APIs (1)
- drug discovery (1)
- drug-sensitivity prediction (1)
- dynamic service binding (1)
- eLectures (1)
- economic ripples (1)
- edge computing (1)
- educational timetabling (1)
- embedded systems (1)
- emission factor (1)
- endothelin (1)
- endothelin-converting enzyme (1)
- ensemble kalman filter (1)
- ensemble methods (1)
- error propagation (1)
- evaluation (1)
- event-related desynchronization (1)
- evolution (1)
- external ambiguity (1)
- extreme weather (1)
- face tracking (1)
- facial expression (1)
- fault tolerance (1)
- field-programmable gate array (1)
- finite model computation (1)
- finite state sequential transducers (1)
- firmware update (1)
- formal (1)
- formal argumentation systems (1)
- gait (1)
- gap-filling (1)
- geovisualization (1)
- gradient boosting (1)
- grammar (1)
- graph analysis (1)
- greenhouse gas (1)
- hardware accelerator (1)
- hardware architecture (1)
- higher education (1)
- hybrid solving (1)
- ice harboring (1)
- image classification (1)
- image processing (1)
- image recognition (1)
- impacts (1)
- incremental SVM (1)
- informal logic (1)
- information flow control (1)
- internal ambiguity (1)
- intrusion detection (1)
- joint lab (1)
- kidney cancer (1)
- knowledge representation and nonmonotonic reasoning (1)
- knowledge representation and reasoning (1)
- latches (1)
- leftmost derivations (1)
- lesson planning (1)
- lesson preparation (1)
- linear programming (1)
- locomotion (1)
- logic programming (1)
- logic-based modeling (1)
- loop formulas (1)
- loose programming (1)
- loss propagation (1)
- lunar exploration (1)
- machine learning (1)
- machine learning algorithms (1)
- manipulation planning (1)
- measure development (1)
- media (1)
- metabolic network (1)
- metabolism (1)
- metabolomics (1)
- metadata (1)
- metastasis (1)
- mobile Applikationen (1)
- natural disasters (1)
- natural language generation (1)
- neighborhood (1)
- neural networks (1)
- neutral endopeptidase (1)
- nonphotorealistic rendering (NPR) (1)
- o-ambiguity (1)
- on-farm evaluation (1)
- oneM2M Ontology (1)
- parallel processing (1)
- parallel rewriting (1)
- parity aggregate operator (1)
- parsing (1)
- pdf forms (1)
- perception (1)
- perception differences (1)
- physical computing (1)
- planning (1)
- plug-ins (1)
- policy evaluation (1)
- portfolio-based solving (1)
- predictive models (1)
- premise acceptability (1)
- process model alignment (1)
- process modeling (1)
- program encodings (1)
- programmed grammars (1)
- projection (1)
- proof complexity (1)
- pruritus (1)
- quality of life (1)
- quantum (1)
- random forest (1)
- real arguments (1)
- real-time (1)
- real-time mapping (1)
- real-walking (1)
- reference (1)
- referential effectiveness (1)
- regression (1)
- regular language (1)
- relevance (1)
- reliability analysis (1)
- resources (1)
- restricted parallelism (1)
- risk analysis (1)
- safety (1)
- satisfiability (1)
- selective fault tolerance (1)
- self-adaptive multiprocessing system (1)
- self-checking (1)
- semantic web (1)
- simplicity (1)
- single event upset (1)
- single event upsets (1)
- single-trial-analysis (1)
- site-specific weed management (1)
- sleep quality (1)
- smart farming (1)
- smartphone (1)
- soft errors (1)
- solar particle event (1)
- space missions (1)
- stable model semantics (1)
- state complexity (1)
- static analysis (1)
- static prediction games (1)
- strong equivalence (1)
- sufficiency (1)
- suicidal ideations (1)
- supply chains (1)
- support system (1)
- support vector machines (1)
- tableau calculi (1)
- teacher training (1)
- teaching (1)
- technical notes and rapid communications (1)
- tele-teaching (1)
- test response compaction (1)
- theory of computation (1)
- timing (1)
- tools (1)
- transient Faults (1)
- transient analysis (1)
- triangulated irregular networks (1)
- triple modular redundancy (1)
- unfounded sets (1)
- unidirektionale Fehler (1)
- user experience (1)
- video annotation (1)
- virtual mobility (1)
- wheat crops (1)
- work productivity (1)
- xAPI (1)
- yellow rust (1)
Institute
- Institut für Informatik und Computational Science (858)
- Institut für Physik und Astronomie (2)
- Department Erziehungswissenschaft (1)
- Department Linguistik (1)
- Extern (1)
- Hasso-Plattner-Institut für Digital Engineering gGmbH (1)
- Institut für Biochemie und Biologie (1)
- Universitätsbibliothek (1)
- Zentrum für Qualitätsentwicklung in Lehre und Studium (ZfQ) (1)
Answer Set Programming (ASP) allows us to address knowledge-intensive search and optimization problems in a declarative way due to its integrated modeling, grounding, and solving workflow. A problem is modeled using a rule based language and then grounded and solved. Solving results in a set of stable models that correspond to solutions of the modeled problem. In this thesis, we present the design and implementation of the clingo system---perhaps, the most
widely used ASP system. It features a rich modeling language originating from the field of knowledge representation and reasoning, efficient grounding algorithms based on database evaluation techniques, and high performance solving algorithms based on Boolean satisfiability (SAT) solving technology.
The contributions of this thesis lie in the design of the modeling language, the design and implementation of the grounding algorithms, and the design and implementation of an Application Programmable Interface (API) facilitating the use of ASP in real world applications and the implementation of complex forms of reasoning beyond the traditional ASP workflow.
Large-scale databases that report the inhibitory capacities of many combinations of candidate drug compounds and cultivated cancer cell lines have driven the development of preclinical drug-sensitivity models based on machine learning. However, cultivated cell lines have devolved from human cancer cells over years or even decades under selective pressure in culture conditions. Moreover, models that have been trained on in vitro data cannot account for interactions with other types of cells. Drug-response data that are based on patient-derived cell cultures, xenografts, and organoids, on the other hand, are not available in the quantities that are needed to train high-capacity machine-learning models. We found that pre-training deep neural network models of drug sensitivity on in vitro drug-sensitivity databases before fine-tuning the model parameters on patient-derived data improves the models’ accuracy and improves the biological plausibility of the features, compared to training only on patient-derived data. From our experiments, we can conclude that pre-trained models outperform models that have been trained on the target domains in the vast majority of cases.
Das Promotionsvorhaben verfolgt das Ziel, die Zuverlässigkeit der Datenspeicherung und die Speicherdichte von neu entwickelten Speichern (Emerging Memories) mit Multi-Level-Speicherzellen zu verbessern bzw. zu erhöhen. Hierfür werden Codes zur Erkennung von unidirektionalen Fehlern analysiert, modifiziert und neu entwickelt, um sie innerhalb der neuen Speicher anwenden zu können. Der Fokus liegt dabei auf sog. Berger-Codes und m-aus-n-Codes. Da Multi-Level-Speicherzellen nicht mehr binär, sondern mit mehreren Leveln arbeiten, können bisher verwendete Codes nicht mehr verwendet werden, bzw. müssen entsprechend angepasst werden. Auf Basis der Berger-Codes und m-aus-n-Codes werden in dieser Arbeit neue Codes abgeleitet, welche in der Lage sind, Daten auch in mehrwertigen Systemen zu schützen.
Answer Set Programming (ASP) is a paradigm for modeling and solving problems for knowledge representation and reasoning. There are plenty of results dedicated to studying the hardness of (fragments of) ASP. So far, these studies resulted in characterizations in terms of computational complexity as well as in fine-grained insights presented in form of dichotomy-style results, lower bounds when translating to other formalisms like propositional satisfiability (SAT), and even detailed parameterized complexity landscapes. A generic parameter in parameterized complexity originating from graph theory is the socalled treewidth, which in a sense captures structural density of a program. Recently, there was an increase in the number of treewidth-based solvers related to SAT. While there are translations from (normal) ASP to SAT, no reduction that preserves treewidth or at least keeps track of the treewidth increase is known. In this paper we propose a novel reduction from normal ASP to SAT that is aware of the treewidth, and guarantees that a slight increase of treewidth is indeed sufficient. Further, we show a new result establishing that, when considering treewidth, already the fragment of normal ASP is slightly harder than SAT (under reasonable assumptions in computational complexity). This also confirms that our reduction probably cannot be significantly improved and that the slight increase of treewidth is unavoidable. Finally, we present an empirical study of our novel reduction from normal ASP to SAT, where we compare treewidth upper bounds that are obtained via known decomposition heuristics. Overall, our reduction works better with these heuristics than existing translations. (c) 2021 Elsevier B.V. All rights reserved.
The highly structured nature of the educational sector demands effective policy mechanisms close to the needs of the field. That is why evidence-based policy making, endorsed by the European Commission under Erasmus+ Key Action 3, aims to make an alignment between the domains of policy and practice. Against this background, this article addresses two issues: First, that there is a vertical gap in the translation of higher-level policies to local strategies and regulations. Second, that there is a horizontal gap between educational domains regarding the policy awareness of individual players. This was analyzed in quantitative and qualitative studies with domain experts from the fields of virtual mobility and teacher training. From our findings, we argue that the combination of both gaps puts the academic bridge from secondary to tertiary education at risk, including the associated knowledge proficiency levels. We discuss the role of digitalization in the academic bridge by asking the question: which value does the involved stakeholders expect from educational policies? As a theoretical basis, we rely on the model of value co-creation for and by stakeholders. We describe the used instruments along with the obtained results and proposed benefits. Moreover, we reflect on the methodology applied, and we finally derive recommendations for future academic bridge policies.
Continuous verification of network security compliance is an accepted need. Especially, the analysis of stateful packet filters plays a central role for network security in practice. But the few existing tools which support the analysis of stateful packet filters are based on general applicable formal methods like Satifiability Modulo Theories (SMT) or theorem prover and show runtimes in the order of minutes to hours making them unsuitable for continuous compliance verification. In this work, we address these challenges and present the concept of state shell interweaving to transform a stateful firewall rule set into a stateless rule set. This allows us to reuse any fast domain specific engine from the field of data plane verification tools leveraging smart, very fast, and domain specialized data structures and algorithms including Header Space Analysis (HSA). First, we introduce the formal language FPL that enables a high-level human-understandable specification of the desired state of network security. Second, we demonstrate the instantiation of a compliance process using a verification framework that analyzes the configuration of complex networks and devices - including stateful firewalls - for compliance with FPL policies. Our evaluation results show the scalability of the presented approach for the well known Internet2 and Stanford benchmarks as well as for large firewall rule sets where it outscales state-of-the-art tools by a factor of over 41.
Computational drug sensitivity models have the potential to improve therapeutic outcomes by identifying targeted drug components that are likely to achieve the highest efficacy for a cancer cell line at hand at a therapeutic dose. State of the art drug sensitivity models use regression techniques to predict the inhibitory concentration of a drug for a tumor cell line. This regression objective is not directly aligned with either of these principal goals of drug sensitivity models: We argue that drug sensitivity modeling should be seen as a ranking problem with an optimization criterion that quantifies a drug's inhibitory capacity for the cancer cell line at hand relative to its toxicity for healthy cells. We derive an extension to the well-established drug sensitivity regression model PaccMann that employs a ranking loss and focuses on the ratio of inhibitory concentration and therapeutic dosage range. We find that the ranking extension significantly enhances the model's capability to identify the most effective anticancer drugs for unseen tumor cell profiles based in on in-vitro data.
The use of neural networks is considered as the state of the art in the field of image classification. A large number of different networks are available for this purpose, which, appropriately trained, permit a high level of classification accuracy. Typically, these networks are applied to uncompressed image data, since a corresponding training was also carried out using image data of similar high quality. However, if image data contains image errors, the classification accuracy deteriorates drastically. This applies in particular to coding artifacts which occur due to image and video compression. Typical application scenarios for video compression are narrowband transmission channels for which video coding is required but a subsequent classification is to be carried out on the receiver side. In this paper we present a special H.264/Advanced Video Codec (AVC) based video codec that allows certain regions of a picture to be coded with near constant picture quality in order to allow a reliable classification using neural networks, whereas the remaining image will be coded using constant bit rate. We have combined this feature with the ability to run with lowest latency properties, which is usually also required in remote control applications scenarios. The codec has been implemented as a fully hardwired High Definition video capable hardware architecture which is suitable for Field Programmable Gate Arrays.
Deep metric learning employs deep neural networks to embed instances into a metric space such that distances between instances of the same class are small and distances between instances from different classes are large. In most existing deep metric learning techniques, the embedding of an instance is given by a feature vector produced by a deep neural network and Euclidean distance or cosine similarity defines distances between these vectors. This paper studies deep distributional embeddings of sequences, where the embedding of a sequence is given by the distribution of learned deep features across the sequence. The motivation for this is to better capture statistical information about the distribution of patterns within the sequence in the embedding. When embeddings are distributions rather than vectors, measuring distances between embeddings involves comparing their respective distributions. The paper therefore proposes a distance metric based on Wasserstein distances between the distributions and a corresponding loss function for metric learning, which leads to a novel end-to-end trainable embedding model. We empirically observe that distributional embeddings outperform standard vector embeddings and that training with the proposed Wasserstein metric outperforms training with other distance functions.