1.8k citations
- KTH Royal Institute of TechnologySE30 papers
- Thinfilm (Sweden)SE27 papers
- Centre National de la Recherche ScientifiqueFR20 papers
- Lund UniversitySE20 papers
- Chalmers University of TechnologySE16 papers
- National University of Science and TechnologyRU13 papers
- Uppsala UniversitySE13 papers
- Budapest University of Technology and EconomicsHU12 papers
- HUN-REN Wigner Research Centre for PhysicsHU12 papers
- University of LiverpoolGB12 papers
- Norwegian University of Science and TechnologyNO11 papers
- University of OsloNO11 papers
15 papers · 1 filter
Continuous-Flow Data-Rate-Aware CNN Inference on FPGA
Tobias Habermann, Michael Mecik, Zhenyu Wang +3
Among hardware accelerators for deep-learning inference, data flow implementations offer low latency and high throughput capabilities. In these architectures, each neuron is mapped…
Gradient Flow Equations for Deep Linear Neural Networks: A Survey from a Network Perspective
Joel Wendin, Claudio Altafini
The paper surveys recent progresses in understanding the dynamics and loss landscape of the gradient flow equations associated to deep linear neural networks, i.e., the gradient de…
Interactive Double Deep Q-network: Integrating Human Interventions and Evaluative Predictions in Reinforcement Learning of Autonomous Driving
Alkis Sygkounas, Ioannis Athanasiadis, Andreas Persson +2
Integrating human expertise with machine learning is crucial for applications demanding high accuracy and safety, such as autonomous driving. This study introduces Interactive Doub…
Multi-field Visualization: Trait design and trait-induced merge trees
Danhua Lei, Jochen Jankowai, Petar Hristov +4
Feature level sets (FLS) have shown significant potential in the analysis of multi-field data by using traits defined in attribute space to specify features in the domain. In this…
Counterfactual Explanation for Auto-Encoder Based Time-Series Anomaly Detection
Abhishek Srinivasan, Varun Singapuri Ravi, Juan Carlos Andresen +1
The complexity of modern electro-mechanical systems require the development of sophisticated diagnostic methods like anomaly detection capable of detecting deviations. Conventional…
Predicting Pedestrian Crossing Behavior in Germany and Japan: Insights into Model Transferability
Chi Zhang, Janis Sprenger, Zhongjun Ni +1
Predicting pedestrian crossing behavior is important for intelligent traffic systems to avoid pedestrian-vehicle collisions. Most existing pedestrian crossing behavior models are t…