S
Stefan Wermter
Researcher at University of Hamburg
Publications - 521
Citations - 9490
Stefan Wermter is an academic researcher from University of Hamburg. The author has contributed to research in topics: Artificial neural network & Computer science. The author has an hindex of 39, co-authored 468 publications receiving 6878 citations. Previous affiliations of Stefan Wermter include Technical University of Dortmund & Birkbeck, University of London.
Papers
More filters
Journal ArticleDOI
Continual lifelong learning with neural networks: A review.
TL;DR: This review critically summarize the main challenges linked to lifelong learning for artificial learning systems and compare existing neural network approaches that alleviate, to different extents, catastrophic forgetting.
Journal ArticleDOI
An analysis of Convolutional Long Short-Term Memory Recurrent Neural Networks for gesture recognition
TL;DR: This research shows that CNNLSTM learns the temporal evolution of the gestures classifying correctly their meaningful part, known as Kendons stroke phase, and shows that the network learns to detect the most intense body motion.
BookDOI
Hybrid neural systems
Stefan Wermter,Ron Sun +1 more
TL;DR: An overview of Hybrid Neural Systems and Lessons from Past, Current Issues, and Future Research Directions in Extracting the Knowledge Embedded in Artificial Neural Networks are presented.
Book
Connectionist, Statistical and Symbolic Approaches to Learning for Natural Language Processing
TL;DR: Embedded machine learning systems for natural language processing: Acquiring and updating hierarchical knowledge for machine translation based on a clustering technique and applying an existing machine learning algorithm to text categorization.
Hybrid neural systems: from simple coupling to fully integrated neural networks
TL;DR: An overview and evaluation of the state of the art of several hybrid neural systems for rule-based processing of neural/symbolic techniques within a hybrid system.