What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Statistics
- Algorithm
Rémi Gribonval mainly investigates Sparse approximation, Source separation, Artificial intelligence, Algorithm and Pattern recognition.
His studies deal with areas such as Discrete mathematics, Combinatorics, Inpainting, Greedy algorithm and Sparse matrix as well as Sparse approximation.
His Source separation study combines topics from a wide range of disciplines, such as Audio signal processing, Estimation theory and Blind signal separation.
His Wavelet study, which is part of a larger body of work in Artificial intelligence, is frequently linked to Envelope detector, bridging the gap between disciplines.
His Algorithm research is mostly focused on the topic Matching pursuit.
His work in the fields of Continuous wavelet transform overlaps with other areas such as Gaussian process.
His most cited work include:
- Performance measurement in blind audio source separation (1896 citations)
- Wavelets on graphs via spectral graph theory (1139 citations)
- Sparse representations in unions of bases (877 citations)
What are the main themes of his work throughout his whole career to date?
Rémi Gribonval spends much of his time researching Artificial intelligence, Algorithm, Sparse approximation, Pattern recognition and Source separation.
His work in Algorithm covers topics such as Mathematical optimization which are related to areas like Inverse problem and Convex optimization.
Rémi Gribonval combines subjects such as Matching pursuit, Sparse matrix, Theoretical computer science and Signal processing with his study of Sparse approximation.
His work on Mixture model as part of general Pattern recognition study is frequently connected to Gaussian process, therefore bridging the gap between diverse disciplines of science and establishing a new relationship between them.
His Source separation research is multidisciplinary, incorporating elements of Audio signal processing, Covariance function and Blind signal separation.
His Blind signal separation research incorporates elements of Estimation theory and Independent component analysis.
He most often published in these fields:
- Artificial intelligence (31.56%)
- Algorithm (30.33%)
- Sparse approximation (25.00%)
What were the highlights of his more recent work (between 2016-2021)?
- Artificial intelligence (31.56%)
- Algorithm (30.33%)
- Machine learning (7.38%)
In recent papers he was focusing on the following fields of study:
The scientist’s investigation covers issues in Artificial intelligence, Algorithm, Machine learning, Estimator and Discrete mathematics.
His studies in Artificial intelligence integrate themes in fields like User interface and Pattern recognition.
Rémi Gribonval focuses mostly in the field of Pattern recognition, narrowing it down to matters related to White noise and, in some cases, Speech recognition.
His Algorithm research includes elements of k-means clustering, Sparse matrix and Fourier transform.
His Discrete mathematics study incorporates themes from Harmonic wavelet transform, Fractional Fourier transform and Monotone polygon.
A large part of his Sparse approximation studies is devoted to K-SVD.
Between 2016 and 2021, his most popular works were:
- Approximate Fast Graph Fourier Transforms via Multilayer Sparse Approximations (35 citations)
- Training with Quantization Noise for Extreme Model Compression (31 citations)
- Approximation spaces of deep neural networks (29 citations)
In his most recent research, the most cited papers focused on:
- Statistics
- Artificial intelligence
- Algorithm
Rémi Gribonval spends much of his time researching Algorithm, Estimator, Quantization, Regularization and Contextual image classification.
He interconnects Sparse matrix, k-means clustering, Cluster analysis and Operator in the investigation of issues within Algorithm.
His Estimator study integrates concerns from other disciplines, such as Scale, Probability distribution, Outcome and Applied mathematics.
His work deals with themes such as Flow, Model compression and Noise, which intersect with Quantization.
The study incorporates disciplines such as Domain, Optimization problem and Second-order cone programming in addition to Regularization.
Contextual image classification is closely attributed to Compression in his study.
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.
