What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
His scientific interests lie mostly in Artificial intelligence, Pattern recognition, Machine learning, Handwriting recognition and Classifier.
As part of his studies on Artificial intelligence, Robert Sabourin frequently links adjacent subjects like Signature.
He interconnects Feature and Biometrics in the investigation of issues within Pattern recognition.
His work is dedicated to discovering how Machine learning, Data mining are connected with Oracle, Overfitting, Generalization error and Training set and other disciplines.
His Handwriting recognition research integrates issues from Image segmentation, Natural language processing, Speech recognition, Signature recognition and Intelligent character recognition.
The Classifier study combines topics in areas such as k-nearest neighbors algorithm, Decision level, Data pre-processing and Word error rate.
His most cited work include:
- From dynamic classifier selection to dynamic ensemble selection (264 citations)
- An HMM-based approach for off-line unconstrained handwritten word modeling and recognition (207 citations)
- Automatic recognition of handwritten numerical strings: a recognition and verification strategy (205 citations)
What are the main themes of his work throughout his whole career to date?
His primary scientific interests are in Artificial intelligence, Pattern recognition, Machine learning, Classifier and Handwriting recognition.
His Artificial intelligence study combines topics from a wide range of disciplines, such as Signature, Speech recognition and Data mining.
As a member of one scientific family, Robert Sabourin mostly works in the field of Pattern recognition, focusing on Artificial neural network and, on occasion, Fuzzy logic.
His Machine learning study frequently draws parallels with other fields, such as Facial recognition system.
Robert Sabourin combines subjects such as Ensemble learning, Contextual image classification and Oracle with his study of Classifier.
His work carried out in the field of Handwriting recognition brings together such families of science as Context, Feature selection and Natural language processing.
He most often published in these fields:
- Artificial intelligence (81.37%)
- Pattern recognition (52.89%)
- Machine learning (36.19%)
What were the highlights of his more recent work (between 2015-2021)?
- Artificial intelligence (81.37%)
- Machine learning (36.19%)
- Classifier (25.70%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Artificial intelligence, Machine learning, Classifier, Pattern recognition and Ensemble selection.
The study incorporates disciplines such as Context and Signature in addition to Artificial intelligence.
His Signature research is multidisciplinary, incorporating perspectives in Pattern recognition and Biometrics.
His Machine learning study integrates concerns from other disciplines, such as Training set and Radiomics.
His studies in Classifier integrate themes in fields like Data stream, Classifier, Data mining and Support vector machine.
His research in Pattern recognition intersects with topics in Representation, Set, Feature and Word error rate.
Between 2015 and 2021, his most popular works were:
- Dynamic classifier selection (162 citations)
- Learning features for offline handwritten signature verification using deep convolutional neural networks (123 citations)
- Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses (82 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
Robert Sabourin spends much of his time researching Artificial intelligence, Pattern recognition, Machine learning, Classifier and Convolutional neural network.
His research on Artificial intelligence often connects related areas such as Signature.
His Segmentation study, which is part of a larger body of work in Pattern recognition, is frequently linked to Novelty, bridging the gap between disciplines.
His research investigates the link between Machine learning and topics such as Oracle that cross with problems in Overfitting.
His Classifier research incorporates elements of Probabilistic logic, Data mining, Data pre-processing and Support vector machine.
His Convolutional neural network research includes themes of Artificial neural network, Feature learning and Word error rate.
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.
