English
Signal processing tutorial - part 2
Virtualconference
Auteurs : Oudre, Laurent (Auteur de la Conférence)
CIRM (Editeur )
94A12 - Signal theory (characterization, reconstruction, filtering, etc.)
CIRM (Editeur )
Loading the player...
|
Résumé :
Processing signals presents many challenges by the quantity, structure, faults, heterogeneity of sensor data recorded over time. Supporting decisions using prediction or detection based on data streams naturally calls Machine Learning techniques (and theory!) for backup. The latter field has witnessed a tremendous development since the publication of Vladimir Vapnik's best-seller 'The Nature of Statistical Learning' and the invention of Support Vector Machines, Bagging, Boosting and Random Forests between 1995 and 1999 until the latest technological breakthroughs based on Deep Learning. However, most of its reference frameworks and methods consider vector observations which are essentially invariant up to a permutation of the indices of vector components. Beyond the obvious approach of featurization (or embedding) time series into vectors of characteristics (features), there are other more subtle interactions between the two fields of SP and ML but they first need to address some fundamental questions such as:
- how to monitor the lack of stationarity in time
- dependent data - how to supervise such data
- what is the objective of learning (prediction goal) in this context, and more generally what can be learned with signals
- how to account for additional structure in signals
- how Signal Processing as a field may benefit from modern optimization techniques
The purpose of this course is to offer an overview on some Signal Processing problems from the angle of Machine Learning philosophy and techniques in order to develop insights on the fundamental questions formulated above. In other terms, this is not a standard course on Signal Processing and we may skip some of the very fundamental concepts that would belong to such a course.
The topics presented in this doctoral course will include:
- local stationarity
- event detection methodology
- prediction problems with signals
- representation learning
- graph signal processing
In the practical sessions, a concrete example in the context of precision medicine will be developed. In particular, the central issues of segmentation, quantification, representation will be addressed with code.
Codes MSC : - how to monitor the lack of stationarity in time
- dependent data - how to supervise such data
- what is the objective of learning (prediction goal) in this context, and more generally what can be learned with signals
- how to account for additional structure in signals
- how Signal Processing as a field may benefit from modern optimization techniques
The purpose of this course is to offer an overview on some Signal Processing problems from the angle of Machine Learning philosophy and techniques in order to develop insights on the fundamental questions formulated above. In other terms, this is not a standard course on Signal Processing and we may skip some of the very fundamental concepts that would belong to such a course.
The topics presented in this doctoral course will include:
- local stationarity
- event detection methodology
- prediction problems with signals
- representation learning
- graph signal processing
In the practical sessions, a concrete example in the context of precision medicine will be developed. In particular, the central issues of segmentation, quantification, representation will be addressed with code.
94A12 - Signal theory (characterization, reconstruction, filtering, etc.)
|
Informations sur la Vidéo
Réalisateur : Hennenfent, GuillaumeLangue : Anglais Date de publication : 22/02/2021 Date de captation : 27/01/2021 Sous collection : Research School arXiv category : Computer Science ; Optimization and Control Domaine : Computer Science ; Control Theory & Optimization Format : MP4 (.mp4) - HD Durée : 01:08:16 Audience : Researchers Download : https://videos.cirm-math.fr/2021-01-27_Oudre_2.mp4 
|
Informations sur la Rencontre
Nom de la rencontre : Mathematics, Signal Processing and Learning / Mathématiques, traitement du signal et apprentissageOrganisateurs de la rencontre : Anthoine, Sandrine ; Chaux, Caroline ; Mélot, Clothilde ; Richard, Frédéric Dates : 25/01/2021 - 29/01/2021 Année de la rencontre : 2021 URL Congrès : https://conferences.cirm-math.fr/2472.html
Données de citation
DOI : 10.24350/CIRM.V.19705503Citer cette vidéo: Oudre, Laurent (2021). Signal processing tutorial - part 2. CIRM. Audiovisual resource. doi:10.24350/CIRM.V.19705503 URI : http://dx.doi.org/10.24350/CIRM.V.19705503 |
Voir aussi
- [Multi angle] Teasing poster: mathematics, signal processing and learning / Auteur de la Conférence Antonsanti, Pierre-Louis ; Auteur de la Conférence Belotto Da Silva, André ; Auteur de la Conférence Cano, Cyril ; Auteur de la Conférence Cohen, Jeremy ; Auteur de la Conférence Doz, Cyprien ; Auteur de la Conférence Lazzaretti, Marta ; Auteur de la Conférence Pilavci, Yusuf Yigit ; Auteur de la Conférence Rodriguez, Willy ; Auteur de la Conférence Stergiopoulou, Vasiliki ; Auteur de la Conférence Kaloga, Yacouba ; Auteur de la Conférence Safaa, Al-Ali.
- [Virtualconference] Optimization - lecture 4 / Auteur de la Conférence Pustelnik, Nelly.
- [Virtualconference] Optimization - lecture 3 / Auteur de la Conférence Pustelnik, Nelly.
- [Virtualconference] Optimization - lecture 2 / Auteur de la Conférence Pustelnik, Nelly.
- [Virtualconference] Optimization - lecture 1 / Auteur de la Conférence Pustelnik, Nelly.
- [Multi angle] One signal processing view on deep learning - lecture 2 / Auteur de la Conférence Oyallon, Edouard.
- [Multi angle] One signal processing view on deep learning - lecture 1 / Auteur de la Conférence Oyallon, Edouard.
- [Virtualconference] Signal processing tutorial - part 1 / Auteur de la Conférence Oudre, Laurent.
- [Virtualconference] Reinforcement learning - lecture 4 / Auteur de la Conférence Lazaric, Allesandro.
- [Virtualconference] Reinforcement learning - lecture 3 / Auteur de la Conférence Lazaric, Allesandro.
- [Virtualconference] Reinforcement learning - lecture 2 / Auteur de la Conférence Lazaric, Allesandro.
- [Virtualconference] Reinforcement learning - lecture 1 / Auteur de la Conférence Lazaric, Allesandro.
- [Multi angle] Basics in machine learning - practical session 2 / Auteur de la Conférence Clausel, Marianne.
- [Multi angle] Basics in machine learning - practical session 1 / Auteur de la Conférence Clausel, Marianne.
- [Multi angle] Basics in machine learning - lecture 2 / Auteur de la Conférence Clausel, Marianne.
- [Multi angle] Basics in machine learning - lecture 1 / Auteur de la Conférence Clausel, Marianne.
Bibliographie
- TRUONG, Charles, OUDRE, Laurent, et VAYATIS, Nicolas. Selective review of offline change point detection methods. Signal Processing, 2020, vol. 167, p. 107299. - https://doi.org/10.1016/j.sigpro.2019.107299
- LE BARS, Batiste, HUMBERT, Pierre, KALOGERATOS, Argyris, et al. Learning the piece-wise constant graph structure of a varying Ising model. In : International Conference on Machine Learning. PMLR, 2020. p. 675-684. - http://proceedings.mlr.press/v119/bars20a.html
- TRUONG, Charles, BARROIS-MÜLLER, Rémi, MOREAU, Thomas, et al. A data set for the study of human locomotion with inertial measurements units. Image Processing On Line, 2019, vol. 9, p. 381-390. - https://doi.org/10.5201/ipol.2019.265
- MOREAU, Thomas, OUDRE, Laurent, et VAYATIS, Nicolas. Dicod: Distributed convolutional coordinate descent for convolutional sparse coding. In : International Conference on Machine Learning. PMLR, 2018. p. 3626-3634. - http://proceedings.mlr.press/v80/moreau18a.html
- TRUONG, C., ruptures: a Python package for changepoint detection, 2019 - https://centre-borelli.github.io/ruptures-docs
