His primary areas of study are Artificial intelligence, Algorithm, Pattern recognition, Entropy and Mathematical optimization. Much of his study explores Artificial intelligence relationship to Machine learning. His Algorithm research incorporates elements of Stability, Kernel density estimation, Speech recognition and Signal processing.
The study incorporates disciplines such as Data mining and Blind signal separation in addition to Pattern recognition. Deniz Erdogmus combines subjects such as Mean squared error, Infomax, Information theory and Estimator with his study of Entropy. Deniz Erdogmus interconnects Gradient descent, Principle of maximum entropy, Maximum entropy probability distribution and Entropy power inequality in the investigation of issues within Mathematical optimization.
Artificial intelligence, Pattern recognition, Algorithm, Speech recognition and Electroencephalography are his primary areas of study. His research integrates issues of Machine learning and Computer vision in his study of Artificial intelligence. Deniz Erdogmus works mostly in the field of Pattern recognition, limiting it down to concerns involving Kernel density estimation and, occasionally, Density estimation, Probability density function and Kernel.
His Algorithm study combines topics in areas such as Entropy, Mathematical optimization, Blind signal separation and Signal processing. His Entropy research integrates issues from Estimator and Adaptive system. In his study, Language model is inextricably linked to Brain–computer interface, which falls within the broad field of Speech recognition.
The scientist’s investigation covers issues in Artificial intelligence, Pattern recognition, Deep learning, Retinopathy of prematurity and Electroencephalography. His Artificial intelligence study frequently links to related topics such as Machine learning. His studies deal with areas such as Image and Pose as well as Pattern recognition.
His work deals with themes such as Convolutional neural network, Image processing, Radiology, Range and Geodesic, which intersect with Deep learning. His study in the field of Childhood blindness and Plus disease is also linked to topics like Informatics, Pediatrics and Disease. His study focuses on the intersection of Electroencephalography and fields such as Speech recognition with connections in the field of Brain–computer interface.
His main research concerns Artificial intelligence, Pattern recognition, Deep learning, Retinopathy of prematurity and Convolutional neural network. His Artificial intelligence research focuses on subjects like Machine learning, which are linked to Inference. His research in Pattern recognition intersects with topics in Pose, Statistical model, Gesture and Medical imaging.
His Deep learning research includes themes of Range, Brain segmentation, Geodesic and Image processing. In general Retinopathy of prematurity, his work in Childhood blindness is often linked to Disease, Informatics, Radiology and Clinical diagnosis linking many areas of study. The concepts of his Convolutional neural network study are interwoven with issues in Ranking, Motion planning and Medical diagnosis.
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.
An error-entropy minimization algorithm for supervised training of nonlinear adaptive systems
D. Erdogmus;J.C. Principe.
IEEE Transactions on Signal Processing (2002)
The Future of Human-in-the-Loop Cyber-Physical Systems
G. Schirner;D. Erdogmus;K. Chowdhury;T. Padir.
IEEE Computer (2013)
Tversky loss function for image segmentation using 3D fully convolutional deep networks
Seyed Sadegh Mohseni Salehi;Seyed Sadegh Mohseni Salehi;Deniz Erdogmus;Ali Gholipour.
International Workshop on Machine Learning in Medical Imaging (2017)
Guest Editorial: Independent Component Analysis and Blind Source Separation
Allan Kardec Barros;José Carlos Príncipe;Deniz Erdogmus.
Signal Processing (2007)
Automated Diagnosis of Plus Disease in Retinopathy of Prematurity Using Deep Convolutional Neural Networks
James M. Brown;J. Peter Campbell;Andrew Beers;Ken Chang.
JAMA Ophthalmology (2018)
Generalized information potential criterion for adaptive system training
D. Erdogmus;J.C. Principe.
IEEE Transactions on Neural Networks (2002)
Optimizing the P300-based brain–computer interface: current status, limitations and future directions
J N Mak;Y Arbel;J W Minett;L M McCane.
Journal of Neural Engineering (2011)
Locally Defined Principal Curves and Surfaces
Umut Ozertem;Deniz Erdogmus.
Journal of Machine Learning Research (2011)
Blind source separation using Renyi's mutual information
K.E. Hild;D. Erdogmus;J. Principe.
IEEE Signal Processing Letters (2001)
Feature extraction using information-theoretic learning
K.E. Hild;D. Erdogmus;K. Torkkola;J.C. Principe.
IEEE Transactions on Pattern Analysis and Machine Intelligence (2006)
If you think any of the details on this page are incorrect, let us know.
We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below: