Antoine Souloumiac
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Antoine Souloumiac has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Julien Béguinot
LTCI, Télécom Paris, Institut Polytechnique de Paris
2 shared publications - Olivier Rioul
LTCI, Télécom Paris, Institut Polytechnique de Paris
2 shared publications - Anthony Larue
LIST, CEA, Gif-sur-Yvette, France
1 shared publication - Bertrand Rivet
Commissariat à l'Energie Atomique (CEA), Saclay; Bât. 451, 91191 Gif-Sur-Yvette France
1 shared publication - Cédric Gouy-Pailler
Institut LIST CEA Université Paris-Saclay F-91120 Palaiseau France
1 shared publication Idris Delsol
LTCI Télécom Paris Institut Polytechnique de Paris 91120 Palaiseau France
1 shared publication
Latest Publications
- Open Access
An Information Theoretic Condition for Perfect Reconstruction
A new information theoretic condition is presented for reconstructing a discrete random variable X based on the knowledge of a set of discrete functions of X. The reconstruction condition is derived from Shannon’s 1953 lattice theory with two entropic metrics of Shannon and Rajski. Because such a theoretical material is relatively unknown and appears quite dispersed in different references, we first provide a synthetic description (with complete proofs) of its concepts, such as total, common, and complementary information. The definitions and properties of the two entropic metrics are also fully detailed and shown to be compatible with the lattice structure. A new geometric interpretation of such a lattice structure is then investigated, which leads to a necessary (and sometimes sufficient) condition for reconstructing the discrete random variable X given a set of elements in the lattice generated by X. Intuitively, the components of the original source of information X should not be globally “too far away” from X in the entropic distance in order that X is reconstructable. In other words, these components should not overall have too low of a dependence on X; otherwise, reconstruction is impossible. These geometric considerations constitute a starting point for a possible novel “perfect reconstruction theory”, which needs to be further investigated and improved along these lines. Finally, this condition is illustrated in five specific examples of perfect reconstruction problems: the reconstruction of a symmetric random variable from the knowledge of its sign and absolute value, the reconstruction of a word from a set of linear combinations, the reconstruction of an integer from its prime signature (fundamental theorem of arithmetic) and from its remainders modulo a set of coprime integers (Chinese remainder theorem), and the reconstruction of the sorting permutation of a list from a minimal set of pairwise comparisons.Open AccessAn Information Theoretic Condition for Perfect Reconstruction
A new information theoretic condition is presented for reconstructing a discrete random variable X based on the knowledge of a set of discrete functions of X. The reconstruction condition is derived from Shannon’s 1953 lattice theory with two entropic metrics of Shannon and Rajski. Because such a theoretical material is relatively unknown and appears quite dispersed in different references, we first provide a synthetic description (with complete proofs) of its concepts, such as total, common, and complementary information. The definitions and properties of the two entropic metrics are also fully detailed and shown to be compatible with the lattice structure. A new geometric interpretation of such a lattice structure is then investigated, which leads to a necessary (and sometimes sufficient) condition for reconstructing the discrete random variable X given a set of elements in the lattice generated by X. Intuitively, the components of the original source of information X should not be globally “too far away” from X in the entropic distance in order that X is reconstructable. In other words, these components should not overall have too low of a dependence on X; otherwise, reconstruction is impossible. These geometric considerations constitute a starting point for a possible novel “perfect reconstruction theory”, which needs to be further investigated and improved along these lines. Finally, this condition is illustrated in five specific examples of perfect reconstruction problems: the reconstruction of a symmetric random variable from the knowledge of its sign and absolute value, the reconstruction of a word from a set of linear combinations, the reconstruction of an integer from its prime signature (fundamental theorem of arithmetic) and from its remainders modulo a set of coprime integers (Chinese remainder theorem), and the reconstruction of the sorting permutation of a list from a minimal set of pairwise comparisons. - Open Access
An information theoretic necessary condition for perfect reconstruction
A new information theoretic condition is presented for reconstructing a discrete random variable $X$ based on the knowledge of a set of discrete functions of $X$. The reconstruction condition is derived from Shannon's 1953 lattice theory with two entropic metrics of Shannon and Rajski. Because such a theoretical material is relatively unknown and appears quite dispersed in different references, we first provide a synthetic description (with complete proofs) of its concepts, such as total, common and complementary informations. Definitions and properties of the two entropic metrics are also fully detailed and shown compatible with the lattice structure. A new geometric interpretation of such a lattice structure is then investigated that leads to a necessary (and sometimes sufficient) condition for reconstructing the discrete random variable $X$ given a set $\{ X_1,\ldots,X_{n} \}$ of elements in the lattice generated by $X$. Finally, this condition is illustrated in five specific examples of perfect reconstruction problems: reconstruction of a symmetric random variable from the knowledge of its sign and absolute value, reconstruction of a word from a set of linear combinations, reconstruction of an integer from its prime signature (fundamental theorem of arithmetic) and from its remainders modulo a set of coprime integers (Chinese remainder theorem), and reconstruction of the sorting permutation of a list from a minimal set of pairwise comparisons.Open AccessAn information theoretic necessary condition for perfect reconstruction
A new information theoretic condition is presented for reconstructing a discrete random variable $X$ based on the knowledge of a set of discrete functions of $X$. The reconstruction condition is derived from Shannon's 1953 lattice theory with two entropic metrics of Shannon and Rajski. Because such a theoretical material is relatively unknown and appears quite dispersed in different references, we first provide a synthetic description (with complete proofs) of its concepts, such as total, common and complementary informations. Definitions and properties of the two entropic metrics are also fully detailed and shown compatible with the lattice structure. A new geometric interpretation of such a lattice structure is then investigated that leads to a necessary (and sometimes sufficient) condition for reconstructing the discrete random variable $X$ given a set $\{ X_1,\ldots,X_{n} \}$ of elements in the lattice generated by $X$. Finally, this condition is illustrated in five specific examples of perfect reconstruction problems: reconstruction of a symmetric random variable from the knowledge of its sign and absolute value, reconstruction of a word from a set of linear combinations, reconstruction of an integer from its prime signature (fundamental theorem of arithmetic) and from its remainders modulo a set of coprime integers (Chinese remainder theorem), and reconstruction of the sorting permutation of a list from a minimal set of pairwise comparisons. - Open Access
Multivariate Temporal Dictionary Learning for EEG
This article addresses the issue of representing electroencephalographic (EEG) signals in an efficient way. While classical approaches use a fixed Gabor dictionary to analyze EEG signals, this article proposes a data-driven method to obtain an adapted dictionary. To reach an efficient dictionary learning, appropriate spatial and temporal modeling is required. Inter-channels links are taken into account in the spatial multivariate model, and shift-invariance is used for the temporal model. Multivariate learned kernels are informative (a few atoms code plentiful energy) and interpretable (the atoms can have a physiological meaning). Using real EEG data, the proposed method is shown to outperform the classical multichannel matching pursuit used with a Gabor dictionary, as measured by the representative power of the learned dictionary and its spatial flexibility. Moreover, dictionary learning can capture interpretable patterns: this ability is illustrated on real data, learning a P300 evoked potential.
Open AccessMultivariate Temporal Dictionary Learning for EEG
This article addresses the issue of representing electroencephalographic (EEG) signals in an efficient way. While classical approaches use a fixed Gabor dictionary to analyze EEG signals, this article proposes a data-driven method to obtain an adapted dictionary. To reach an efficient dictionary learning, appropriate spatial and temporal modeling is required. Inter-channels links are taken into account in the spatial multivariate model, and shift-invariance is used for the temporal model. Multivariate learned kernels are informative (a few atoms code plentiful energy) and interpretable (the atoms can have a physiological meaning). Using real EEG data, the proposed method is shown to outperform the classical multichannel matching pursuit used with a Gabor dictionary, as measured by the representative power of the learned dictionary and its spatial flexibility. Moreover, dictionary learning can capture interpretable patterns: this ability is illustrated on real data, learning a P300 evoked potential.
- 1 August 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
- Vol. 2007 (1094687X) , 5071-5074
Subspace estimation approach to P300 detection and application to Brain-Computer Interface
Brain-computer interface (BCI) is a system for direct communication between brain and computer. In this work, a new unsupervised algorithm is introduced for P300 subspace estimation: the raw EEG are thus enhanced by projection on the estimated subspace. Moreover a simple scheme to detect the P300 potentials in the human EEG by dimension reduction and linear support vector machine (SVM) is proposed to build a BCI based on the P300 speller. The proposed algorithm is finally tested with dataset from the BCI Competition 2003 and gives results that compare favourably to the state of the art.
- 1 August 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
- Vol. 2007 (1094687X) , 5071-5074
Subspace estimation approach to P300 detection and application to Brain-Computer Interface
Brain-computer interface (BCI) is a system for direct communication between brain and computer. In this work, a new unsupervised algorithm is introduced for P300 subspace estimation: the raw EEG are thus enhanced by projection on the estimated subspace. Moreover a simple scheme to detect the P300 potentials in the human EEG by dimension reduction and linear support vector machine (SVM) is proposed to build a BCI based on the P300 speller. The proposed algorithm is finally tested with dataset from the BCI Competition 2003 and gives results that compare favourably to the state of the art.