BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
BEGIN:VEVENT
UID:586@lincs.fr
DTSTART;TZID=Europe/Paris:20201207T140000
DTEND;TZID=Europe/Paris:20201207T170000
DTSTAMP:20201204T092009Z
URL:https://www.lincs.fr/events/thesis-defense-contributions-to-the-repres
 entation-of-multivariate-time-series-and-graphs/
SUMMARY:Thesis defense "Contributions to the representation of multivariate
 time series and graphs"
DESCRIPTION:Machine learning (ML) algorithms are designed to learn models
 that have the ability to take decisions or make predictions from data\, in
 a large panel of tasks like classification of images or monitoring of
 mechanical systems. In general\, the learned models are statistical
 approximations of the true/optimal unknown decision models. The efficiency
 of a learning algorithm depends on an equilibrium between model richness\,
 complexity of the data distribution and complexity of the task to solve
 from data. Nevertheless\, for computational convenience\, the statistical
 decision models often adopt simplifying assumptions about the data (e.g.
 linear separability\, independence of the observed variables\, etc.).
 However\, when data distribution is complex (e.g. high-dimensional with
 nonlinear interactions between observed variables)\, the simplifying
 assumptions can be counterproductive. In this situation\, a solution is to
 feed the model with an alternative representation of the data. The
 objective of data representation is to separate the relevant information
 with respect to the task to solve from the noise\, in particular if the
 relevant information is hidden (latent)\, in order to help the statistical
 model. Until recently and the rise of modern ML\, many standard
 representations consisted in an expert-based handcrafted preprocessing of
 data. Recently\, a branch of ML called deep learning (DL) completely
 shifted the paradigm. DL uses neural networks (NNs)\, a family of powerful
 parametric functions\, as learning data representation pipelines. These
 recent advances outperformed most of the handcrafted data in many
 domains.\n\nIn this thesis\, we are interested in learning representations
 of multivariate time series (MTS) and graphs. MTS and graphs are particular
 objects that do not directly match standard requirements of ML algorithms.
 They can have variable size and non-trivial alignment\, such that comparing
 two MTS or two graphs with standard metrics is generally not relevant.
 Hence\, particular representations are required for their analysis using ML
 approaches. The contributions of this thesis consist of practical and
 theoretical results presenting new MTS and graphs representation learning
 frameworks.\n\nTwo MTS representation learning frameworks are dedicated to
 the ageing detection of mechanical systems. First\, we propose a
 model-based MTS representation learning framework called Sequence-to-graph
 (Seq2Graph). Seq2Graph assumes that the data we observe has been generated
 by a model whose graphical representation is a causality graph. It then
 represents\, using an appropriate neural network\, the sample on this
 graph. From this representation\, when it is appropriate\, we can find
 interesting information about the state of the studied mechanical system.
 Second\, we propose a generic trend detection method called Contrastive
 Trend Estimation (CTE). CTE learns to classify pairs of samples with
 respect to the monotony of the trend between them. We show that using this
 method\, under few assumptions\, we identify the true state underlying the
 studied mechanical system\, up-to monotone scalar transform.\n\nTwo graph
 representation learning frameworks are dedicated to the classification of
 graphs. First\, we propose to see graphs as sequences of nodes and create a
 framework based on recurrent neural networks to represent and classify
 them. Second\, we analyze a simple baseline feature for graph
 classification: the Laplacian spectrum. We show that this feature matches
 minimal requirements to classify graphs when all the meaningful information
 is contained in the structure of the graphs.\n\nHere's the streaming link:
 https://safran-group.webex.com/safran-group-fr/j.php?MTID=mfda124766b7a93fc
 255f3da5a14ab4ec
CATEGORIES:PhD Defense
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20201025T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR