Refine
Year of publication
Document Type
- Conference Proceeding (164) (remove)
Conference Type
- Konferenzartikel (94)
- Konferenzband (64)
- Konferenz-Abstract (3)
- Sonstiges (2)
- Konferenz-Poster (1)
Has Fulltext
- yes (164) (remove)
Keywords
- Mikroelektronik (62)
- Communication Systems (3)
- Information Systems (3)
- Sound Synthesis (3)
- Biologische Methanisierung (2)
- Deep Learning (2)
- Generative Art (2)
- Improvisation (2)
- Simulation-based Interaction (2)
- VR (2)
- artificial dancer (2)
- cardiac ablation (2)
- dance and technology (2)
- deep learning (2)
- heart rhythm model (2)
- motion synthesis (2)
- 1.5-Degree target (1)
- 3D virtual reality (1)
- AI aided Innovation (1)
- AR (1)
- AV nodal reentry tachycardia (1)
- AV reentrant tachycardia (1)
- Analog-Schaltkreis (1)
- Android (1)
- Anti-Windup (1)
- Anwenderschaltkreise (1)
- Artistic Research (1)
- Audiovisual Performance (1)
- AudiovisualPerformance (1)
- Automated Ideation (1)
- Automation (1)
- Bauteilfestigkeit (1)
- Biogas (1)
- Biomassenutzung (1)
- Biomedizin (1)
- Blended Learning (1)
- Building energy efficiency (1)
- CCD-Kamera (1)
- CRC (1)
- Climate change (1)
- Coal phase-out (1)
- Computer (1)
- Creativity (1)
- Demand side flexibility (1)
- Design Methods (1)
- Digitale Turschilder (1)
- Digitaler Zwilling (1)
- Digitalization (1)
- Dimension 3 (1)
- Diskretisierung (1)
- Drehstrom (1)
- Druck (1)
- E-Ink (1)
- E-Learning (1)
- E-Paper (1)
- Ecercises (1)
- Edge AI (1)
- Embedded AI (1)
- Embedded Systems (1)
- Energiemanagement (1)
- Energiewirtschaft (1)
- Energy Harvesting (EH) (1)
- Energy Market (1)
- Energy Planning (1)
- Energy Storage Systems (1)
- Energy System Analysis (1)
- Energy System Optimization (1)
- Energy management (1)
- Energy policy (1)
- Energy systems modeling (1)
- Engineering Creativity (1)
- FPGA (1)
- Fault detection (1)
- Fertigungsautomatisierung (1)
- Finite-Differenzen Methode (1)
- GPS-Empfänger (1)
- Gamification (1)
- Gebäude (1)
- Gedruckte Elektronik (PE) (1)
- Gleichstrom (1)
- Grid Integration (1)
- Hardmakros (1)
- Hochspannung (1)
- Holzpresssaft (1)
- InceptionTime (1)
- Innovation (1)
- Intellectual Properties (1)
- Intelligent Buildings (1)
- Intelligentes Stromnetz (1)
- Interactive Film (1)
- LCA-Microcontroller (1)
- Lernumgebung (1)
- Logic-Cell-Array (1)
- Lottozahlengenerators (1)
- Low-Power (1)
- Low-Power-SoC-Systeme (1)
- M-learning (1)
- Machine Learning (1)
- Makespan (1)
- Maschinenbaustudium (1)
- Mentor-Graphics (1)
- Microelectronics (1)
- Mikroprozessorkernels (1)
- Mobile Learning (1)
- Movement (1)
- NFC (1)
- Neural networks (1)
- New Product Development (1)
- Online simulation (1)
- Optimization and control (1)
- Physiotherapy (1)
- Plant commissioning (1)
- Produktion (1)
- Prozessorkern (1)
- Rehabilitation (1)
- ResNet (1)
- Road-Quality Prediction (1)
- Russian Ukrainian war (1)
- Schaltkreis (1)
- Schaltungsdesign (1)
- Schlatungen (1)
- Soft- und Hardcore-Prozessoren (1)
- Software (1)
- Stromregelung (1)
- Stromzustandsregler (1)
- Synchronmaschine (1)
- System-on-Chip (1)
- TRIZ Inventive Principles (1)
- TRIZ methodology (1)
- Thermologger (1)
- Thermomechanische Ermüdung (1)
- Time-series Classification (1)
- Transistor (1)
- Urformen (1)
- Virtual Reality (1)
- Virtuelle Realität (1)
- Virtuelles Laboratorium (1)
- Wishbone (1)
- Zellbibliothek (1)
- accuracy (1)
- atrial flutter (1)
- benchmarking (1)
- business applications (1)
- cryptography (1)
- curricular concepts (1)
- cybersecurity (1)
- data architecture (1)
- data migration (1)
- data model (1)
- digital twin (1)
- e-learning (1)
- eLearning (1)
- efficient training (1)
- elektronischer Würfel (1)
- equivalent circuit model (1)
- flexible job shop (1)
- generation Y (1)
- generation Z (1)
- grey-box model (1)
- heart rhythm simulation (1)
- heating and cooling (1)
- iSign (1)
- industry (1)
- laser triangulation (1)
- learning scenarios (1)
- lithium-ion battery (1)
- load profiles (1)
- local electricity markets (1)
- m-learning (1)
- maintenance scheduling (1)
- master data (1)
- measurement (1)
- media tyechnolog (1)
- metaverse (1)
- natürliche Leistung (1)
- neural ordinary differential equations (1)
- new product development (1)
- optics and photonics (1)
- optimization (1)
- peer-to-peer energy trading (1)
- railway system (1)
- reference data (1)
- remanufacturing (1)
- remote laboratory (1)
- remote model-based laboratory (1)
- repeatability (1)
- research-oriented education (1)
- robotics (1)
- scheduling (1)
- simulation (1)
- synthetical profiles (1)
- taxonomy (1)
- ventricular tachycardia (1)
- virtual lab (1)
- virtual worlds (1)
- übertragbare Wirkleistung (1)
Institute
- Fakultät Elektrotechnik und Informationstechnik (E+I) (bis 03/2019) (104)
- Fakultät Maschinenbau und Verfahrenstechnik (M+V) (26)
- INES - Institut für nachhaltige Energiesysteme (14)
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (11)
- Fakultät Medien (M) (ab 22.04.2021) (8)
- ivESK - Institut für verlässliche Embedded Systems und Kommunikationselektronik (8)
- Fakultät Medien und Informationswesen (M+I) (bis 21.04.2021) (5)
- Fakultät Wirtschaft (W) (5)
- ACI - Affective and Cognitive Institute (2)
- POIM - Peter Osypka Institute of Medical Engineering (2)
Open Access
- Open Access (159)
- Bronze (118)
- Diamond (10)
- Grün (7)
- Closed (4)
- Gold (3)
- Closed Access (1)
- Hybrid (1)
In 2015, Google engineer Alexander Mordvintsev presented DeepDream as technique to visualise the feature analysis capabilities of deep neural networks that have been trained on image classification tasks. For a brief moment, this technique enjoyed some popularity among scientists, artists, and the general public because of its capability to create seemingly hallucinatory synthetic images. But soon after, research moved on to generative models capable of producing more diverse and more realistic synthetic images. At the same time, the means of interaction with these models have shifted away from a direct manipulation of algorithmic properties towards a predominance of high level controls that obscure the model's internal working. In this paper, we present research that returns to DeepDream to assess its suit-ability as method for sound synthesis. We consider this research to be necessary for two reasons: it tackles a perceived lack of research on musical applications of DeepDream, and it addresses DeepDream's potential to combine data driven and algorithmic approaches. Our research includes a study of how the model architecture, choice of audio data-sets, and method of audio processing influence the acoustic characteristics of the synthesised sounds. We also look into the potential application of DeepDream in a live-performance setting. For this reason, the study limits itself to models consisting of small neural networks that process time-domain representations of audio. These models are resource-friendly enough to operate in real time. We hope that the results obtained so far highlight the attractiveness of Deep-Dream for musical approaches that combine algorithmic investigation with curiosity driven and open ended exploration.