What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
His main research concerns Artificial intelligence, Artificial neural network, Computer vision, Topology and Manifold.
His study in the fields of Feature extraction and Vector quantization under the domain of Artificial intelligence overlaps with other disciplines such as Neural gas and Relevant information.
His work in the fields of Artificial neural network, such as Self-organizing map and Cellular neural network, intersects with other areas such as Information system, Scheduling and Information and Communications Technology.
His research in Topology intersects with topics in Synaptic weight, Delaunay triangulation, Self-organization and Image processing.
His Manifold research is multidisciplinary, incorporating elements of Quasi-open map, Neighbourhood and Nonlinear system.
His research integrates issues of Hebbian theory, Submanifold, Path and Computational geometry, Proximity problems in his study of Topology.
His most cited work include:
- 'Neural-gas' network for vector quantization and its application to time-series prediction (1308 citations)
- Topology representing networks (788 citations)
- Topology representing networks (788 citations)
What are the main themes of his work throughout his whole career to date?
Artificial intelligence, Pattern recognition, Computer vision, Artificial neural network and Support vector machine are his primary areas of study.
Thomas Martinetz performs multidisciplinary study in the fields of Artificial intelligence and Neural gas via his papers.
Thomas Martinetz interconnects Contextual image classification and Feature in the investigation of issues within Pattern recognition.
His studies in Computer vision integrate themes in fields like Salient and Eye movement.
Thomas Martinetz has included themes like Control engineering, Robotic arm and Control theory in his Artificial neural network study.
His Support vector machine research integrates issues from Algorithm, Iterative method and Perceptron.
He most often published in these fields:
- Artificial intelligence (53.74%)
- Pattern recognition (24.67%)
- Computer vision (22.91%)
What were the highlights of his more recent work (between 2013-2021)?
- Artificial intelligence (53.74%)
- Pattern recognition (24.67%)
- Convolutional neural network (5.73%)
In recent papers he was focusing on the following fields of study:
Thomas Martinetz focuses on Artificial intelligence, Pattern recognition, Convolutional neural network, Deep learning and Neuroscience.
He has researched Artificial intelligence in several fields, including Machine learning, Relation, Computer vision and Relational reasoning.
His biological study spans a wide range of topics, including Manifold and Key.
His work deals with themes such as Salient and Visualization, which intersect with Manifold.
His Convolutional neural network study combines topics in areas such as Feature, Segmentation, Artificial neural network, Contextual image classification and Discriminative model.
His study in the field of Electroencephalography and Stimulation is also linked to topics like Sleep.
Between 2013 and 2021, his most popular works were:
- Driving Sleep Slow Oscillations by Auditory Closed-Loop Stimulation—A Self-Limiting Process (101 citations)
- Classifiers for Ischemic Stroke Lesion Segmentation: A Comparison Study (98 citations)
- Deep convolutional neural networks as generic feature extractors (62 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
His primary areas of investigation include Artificial intelligence, Neuroscience, Pattern recognition, Non-rapid eye movement sleep and Electroencephalography.
He performs integrative study on Artificial intelligence and Data acquisition.
In the subject of general Neuroscience, his work in Stimulation is often linked to Sleep, thereby combining diverse domains of study.
The Pattern recognition study combines topics in areas such as Deep learning and Feature.
His Non-rapid eye movement sleep research is multidisciplinary, relying on both Amplitude, Statistical physics and Orbit.
His biological study deals with issues like Sleep Stages, which deal with fields such as Wakefulness and Closed loop stimulation.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
