Pascal Frossard mostly deals with Artificial intelligence, Robustness, Algorithm, Theoretical computer science and Computer network. His Artificial intelligence research is multidisciplinary, incorporating perspectives in Machine learning and Pattern recognition. His Robustness research focuses on Curvature and how it relates to Classifier.
His Algorithm research integrates issues from Upper and lower bounds, Recurrence relation and Mathematical optimization. He has researched Theoretical computer science in several fields, including Data modeling, Graph theory, Signal processing and Graph. Pascal Frossard studied Contextual image classification and Convolutional neural network that intersect with Transformation geometry.
Pascal Frossard mainly investigates Artificial intelligence, Algorithm, Computer vision, Computer network and Decoding methods. Pascal Frossard combines subjects such as Machine learning and Pattern recognition with his study of Artificial intelligence. His studies deal with areas such as Graph, Mathematical optimization and Theoretical computer science as well as Algorithm.
His study brings together the fields of Signal processing and Theoretical computer science. The various areas that he examines in his Computer network study include Distributed computing, Overlay network and Video quality. The Network packet study which covers Real-time computing that intersects with Scheduling.
Pascal Frossard mostly deals with Artificial intelligence, Graph, Algorithm, Graph and Theoretical computer science. The concepts of his Artificial intelligence study are interwoven with issues in Machine learning, Computer vision and Pattern recognition. His Algorithm research includes themes of Pixel, Laplacian matrix and Signal processing.
Pascal Frossard works mostly in the field of Theoretical computer science, limiting it down to concerns involving Node and, occasionally, Feature vector. His studies in Robustness integrate themes in fields like Contextual image classification, Deep learning, Curvature and Decision boundary. His work carried out in the field of Artificial neural network brings together such families of science as Classifier and Adversarial system.
Pascal Frossard spends much of his time researching Artificial intelligence, Algorithm, Graph, Robustness and Theoretical computer science. The Artificial intelligence study combines topics in areas such as Computer vision and Complex network. His work deals with themes such as Depth map, Quadratic programming, Color image, Manifold and Transformation geometry, which intersect with Algorithm.
His research in the fields of Topological graph theory, Laplacian matrix and Graph neural networks overlaps with other disciplines such as Mathematical theory. His Robustness research incorporates elements of Artificial neural network, Deep learning, Curvature and Decision boundary. His Theoretical computer science research incorporates themes from Data modeling, Vertex, Linear combination and Dimensionality reduction.
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.
DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks
Seyed-Mohsen Moosavi-Dezfooli;Alhussein Fawzi;Pascal Frossard.
computer vision and pattern recognition (2016)
The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains
David I Shuman;Sunil K. Narang;Pascal Frossard;Antonio Ortega.
IEEE Signal Processing Magazine (2013)
Universal Adversarial Perturbations
Seyed-Mohsen Moosavi-Dezfooli;Alhussein Fawzi;Omar Fawzi;Pascal Frossard.
computer vision and pattern recognition (2017)
Graph Signal Processing: Overview, Challenges, and Applications
Antonio Ortega;Pascal Frossard;Jelena Kovacevic;Jose M. F. Moura.
Proceedings of the IEEE (2018)
Dictionary Learning
Ivana Tošić;Pascal Frossard.
IEEE Signal Processing Magazine (2011)
Dictionary learning: What is the right representation for my signal?
Ivana Tosic;Pascal Frossard.
IEEE Signal Processing Magazine (2011)
Learning Laplacian Matrix in Smooth Graph Signal Representations
Xiaowen Dong;Dorina Thanou;Pascal Frossard;Pierre Vandergheynst.
IEEE Transactions on Signal Processing (2016)
Analysis of classifiers’ robustness to adversarial perturbations
Alhussein Fawzi;Omar Fawzi;Pascal Frossard.
Machine Learning (2018)
Robustness of classifiers: from adversarial to random noise
Alhussein Fawzi;Seyed-Mohsen Moosavi-Dezfooli;Pascal Frossard.
neural information processing systems (2016)
Clustering on Multi-Layer Graphs via Subspace Analysis on Grassmann Manifolds
Xiaowen Dong;Pascal Frossard;Pierre Vandergheynst;Nikolai Nefedov.
ieee global conference on signal and information processing (2013)
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:
École Polytechnique Fédérale de Lausanne
New Jersey Institute of Technology
York University
University of Southern California
Instituto Superior Técnico
Hong Kong Polytechnic University
Queen Mary University of London
Hong Kong University of Science and Technology
Technical University of Berlin
University of Science and Technology of China
Queensland University of Technology
The University of Texas at Austin
IBM (United States)
University of California, San Diego
University of Strasbourg
Carnegie Mellon University
University of California, Santa Barbara
Sorbonne University
Université Savoie Mont Blanc
University of Massachusetts Medical School
Carnegie Mellon University
University of Tokyo
University of Potsdam
Texas A&M University at Galveston
University College London
University of Toronto