What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Quantum mechanics
- Machine learning
His primary scientific interests are in Artificial neural network, Artificial intelligence, Machine learning, Algorithm and Nonlinear system.
His Artificial neural network research is multidisciplinary, incorporating elements of Classifier, Handwriting recognition and Speech recognition.
The study of Artificial intelligence is intertwined with the study of Pattern recognition in a number of ways.
His research integrates issues of Local learning and Feed forward in his study of Algorithm.
His Nonlinear system study combines topics from a wide range of disciplines, such as Discretization, Knowledge base and Differential equation.
His studies examine the connections between Time delay neural network and genetics, as well as such issues in Deep learning, with regards to Types of artificial neural networks and Feedforward neural network.
His most cited work include:
- Single-layer learning revisited: a stepwise procedure for building and training a neural network (686 citations)
- Neural Networks: Methodology and Applications (401 citations)
- Collective computational properties of neural networks: New learning mechanisms. (273 citations)
What are the main themes of his work throughout his whole career to date?
Artificial intelligence, Artificial neural network, Speech recognition, Machine learning and Electret are his primary areas of study.
His Artificial intelligence research incorporates elements of Computer vision and Pattern recognition.
Gérard Dreyfus has included themes like Classifier, Algorithm and Nonlinear system in his Artificial neural network study.
His studies in Speech recognition integrate themes in fields like Feature extraction and Electroencephalography.
His research investigates the connection with Electroencephalography and areas like Blind signal separation which intersect with concerns in Wavelet.
His Electret research incorporates themes from Optoelectronics, Charge, Electrode and Electrical engineering, Voltage.
He most often published in these fields:
- Artificial intelligence (34.36%)
- Artificial neural network (28.19%)
- Speech recognition (16.30%)
What were the highlights of his more recent work (between 2009-2020)?
- Artificial intelligence (34.36%)
- Speech recognition (16.30%)
- Electroencephalography (7.49%)
In recent papers he was focusing on the following fields of study:
Gérard Dreyfus focuses on Artificial intelligence, Speech recognition, Electroencephalography, Brain–computer interface and Computer vision.
Gérard Dreyfus combines subjects such as Machine learning and Pattern recognition with his study of Artificial intelligence.
When carried out as part of a general Speech recognition research project, his work on Silent speech interface, Vocal tract and Hidden Markov model is frequently linked to work in Post-laryngectomy voice, therefore connecting diverse disciplines of study.
Gérard Dreyfus interconnects Steady state, Visual evoked potentials and Cognition in the investigation of issues within Electroencephalography.
In the field of Computer vision, his study on Tracking overlaps with subjects such as Noise.
His biological study spans a wide range of topics, including Graph, Implantable defibrillator and Biological system.
Between 2009 and 2020, his most popular works were:
- Neural Networks: Methodology and Applications (401 citations)
- Development of a silent speech interface driven by ultrasound and optical images of the tongue and lips (117 citations)
- Bimodal BCI Using Simultaneously NIRS and EEG (69 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Quantum mechanics
- Machine learning
Gérard Dreyfus mostly deals with Artificial intelligence, Electroencephalography, Computer vision, Speech recognition and GSM.
His studies deal with areas such as Machine learning and Pattern recognition as well as Artificial intelligence.
His study in the field of Multilayer perceptron also crosses realms of Full band.
His work on Tracking and Silent speech interface as part of general Computer vision research is frequently linked to Noise, thereby connecting diverse disciplines of science.
His research in Speech recognition intersects with topics in Feature extraction and Phonetics.
His Autoencoder study, which is part of a larger body of work in Artificial neural network, is frequently linked to Process, bridging the gap between disciplines.
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.
