Scientific direction Development of key enabling technologies
Transfer of knowledge to industry

PhD : selection by topics

Blending intuition with reasoning ? Deep learning augmented with algorithmic logic and abstraction

Département Ingénierie Logiciels et Systèmes (LIST)

Labo.conception des système embarqués et autonomes



Within machine learning, deep learning, based on neural networks, is a subfield that has gained much traction since several high-profile success stories. Unlike classical computer reasoning, the statistical method by which a neural network solves a problem can be seen as a very primitive form of intuition, as opposite to classical computer reasoning. However, so far the only real success of deep learning has been its ability to self-tune its geometric logic that lets it transform data represented as points in n-dimension, to data represented as points in m-dimension, if we provide enough training data. Unlike a human being, a neural network does not have the ability to reason through algorithmic logic. Furthermore, although neural networks are tremendously powerful for a given task, since they have no ability to achieve global generalization, any deviation in the input data may give unpredicted results, which limits their reusability. Considering the significant cost associated with neural network development, integrating such systems is not always economically viable. It is therefore necessary to abstract, encapsulate, reuse and compose neural networks. Although lacking in deep learning, algorithmic logic and abstraction are today innate to classical software engineering, through programming primitives, software architecture paradigms, and mature methodological patterns like Model-Driven Engineering. Therefore, in this thesis, we propose to blend reusable algorithmic intelligence, providing the ability to reason, with reusable geometric intelligence, providing the ability of intuition. To achieve such an objective, we can explore some ideas like integrating programming control primitives in neural networks, applying software architecture paradigms in neural networks models, and assembling modular systems using libraries containing both algorithmic modules and geometric modules. The results of this thesis will be a stepping stone towards helping companies assemble AI systems for their specific problems, by limiting the costs in expertise, effort, time, and data necessary to integrate neural networks.

Tunable Metasurface

Département Systèmes

Laboratoire Antennes, Propagation, Couplage Inductif



Metamaterials have been studied by the scientific community for several years with a particular focus on 2D or 3D meta shapes. In the antenna field, these structured materials have been mainly used as magnetic surfaces, filtering surfaces for surface waves or the antenna itself. The main disadvantage of these materials is its narrow band behaviour. Recent research has shown that it is possible to modify the response of metasurfaces by adding a film sensitive to a control voltage to the patterns or by arranging the active components between them. More recently, CEA Leti has developed a new approach, through a thesis, to modify the performance of a metasurface, by inserting control devices on its rear surface as well as on the feeder. The proposal, made here, is in line with the continuity of this work, initiated within the LAPCI laboratory, with a specific development around massively tunable metasurfaces. Indeed, it has been demonstrated that the metasurface/feeder pair should be jointly designed/optimized when the metasurface and/or feeder were compact or even miniature. The purpose of this thesis is to study this interaction through the notion of load impedance and to realize a final demonstrator of a reconfigurable metasurface of several hundred active elements. The main interest is to consider the use of ultra-compact adjustable metamaterials in order to miniaturize the size of an antenna placed near a reflecting plane. The second major point concerns the possibility of frequency-dependent control of the complete device (by nature very narrow band) over a frequency band of several tens of percent. During this thesis, the candidate will develop the theoretical modeling of the proposed device and validate the expected performances through 2D and/or 3D electromagnetic simulation campaigns. He/she will be in charge of having the selected demonstrators carried out and will carry out measurements of the devices in the test facilities of CEA-Leti and/or CNES (anechoic chamber). The candidate will be integrated into the Antenna, Propagation and Inductive Coupling Laboratory in Grenoble. He/she will be part of the research team (permanent, doctoral and non-permanent) and will be supervised by a research engineer from the laboratory. The candidate will be required to present his or her work at national and international conferences and symposiums.

Miniature and directive antenna design with frequency agility over several octaves

Département Systèmes

Laboratoire Antennes, Propagation, Couplage Inductif



The 'New Space' sector pushes for innovative solutions concerning on board micro-satellites antenna design. With smaller satellites, the miniaturization of directive and extremely wide band antenna represents a solution to fill the requirements of a lot of services. The double circular polarization needs to be ensure properly over more than 2 octaves. The CEA Leti antenna laboratory proposes to skirt the classical antenna physical limitation (bandwidth / miniaturization) by tuning the antenna on a smaller instant sub-band that can be shifted with reconfigurable RF components. This is the concept of antenna aperture tuning. The novelty of the PhD subject is to extend the tuning range over several octaves thanks to tunable capacitors developed at CEA Leti. The challenge consists to optimize the miniaturization of the antenna structure while limiting the impact of losses introduced by the tunable capacitors and get a performance stability over several octaves. Prototypes will be realized and measured in the CEA Leti or CNES anechoic chamber.

Study of new solutions for the security of embedded systems

Département Systèmes

Laboratoire Sécurité des Objets et des Systèmes Physiques



In recent years, the number of connected systems has increased exponentially and is expected to reach several tens of billions by 2020. Most of these devices integrate seldom, if ever, security and can create massive attacks involving a large number of objects. In the embedded systems used in IOT and I-IOT, hardware and software solutions currently exist and provide cryptographic primitives to secure a communication interface or data storage. However, these solutions are not always correctly implemented and didn't deal with all the issues of security. Based on the study of existing attack scenarios, standards and regulatory documents, this thesis will define the needs in terms of security of an embedded system throughout its life cycle. Particular attention should be paid to threat detection, hardware and software integrity, system resilience, and the definition of a new commissioning interface. New solutions will be studied and developed in order to address issues not integrated in current embedded devices. The implementation of these new solutions will be the first step in the development of a new component called a security supervisor. One day, this component could be integrated in most of embedded systems in order to strengthen defence in depth.

Wireless Communication Relying on Artificial Intelligence

Département Systèmes

Laboratoire Sans fils Haut Débit



In wireless communications, we are used to design transmit signals that enable straightforward algorithms for symbol detection for a variety of statistical channel and system models. In practice, real systems have many impairments (non-linear power amplifiers, antennae coupling effects, finite resolution quantization) that cannot be fully captured by tractable models. Artificial Intelligence-based approaches could be a disruptive but yet promising alternative. More precisely one can expect benefits of IA based approach in case of complex communication scenarii and when mathematical models are intractable. The first challenge of this PhD project is to assess the potential of IA in the design of a signal processing algorithms. The second challenge is to develop tailored learning methods that exploit a dataset to enable future communication systems to be self-configurable regarding its environment.

Flexible nanosensors matrix for impact detection on sensitive surface

Département Systèmes

Laboratoire Autonomie et Intégration des Capteurs



The aim of the PhD thesis is to implement a matrix of flexible piezoelectric nanosensors, which enable the 3D reconstruction of a force or deformation field. The nanosensors based on GaN nanowires obtained by directed growth are fabricated and assembled at CEA. The candidate will tackle experimental aspects, which include the fabrication and the assembly of sensors and sensor networks (matrix) via controlled growth and deposition processes, first-level flexible electronic layers (interconnects), system integration on an object (mechatronics) and finally signal collection and processing through a dedicated reading electronics, to be designed based on the competences present in our laboratory. In parallel, the candidate will carry out studies at the fundamental level, such as investigating the mechanical transfer between the nanowire and its environment and its effect on the generated signal under deformation, or the study of the piezoelectric / pyroelectric coupling intrinsic to GaN nanowires. For this purpose, the candidate will have access to multi-physics simulation tools. Finally, investigations on the choice of materials and the characterisation thereof (structural, mechanical, thermal, optical, electrical) will be pertinent and may pursued. More generally, this PhD thesis will also provide the opportunity to develop applicable solutions in various fields such as deformation and impacts detectors for predictive maintenance, sensitive surfaces or electronic skin.

100 Results found (Page 5 of 17)
first   previous  3 - 4 - 5 - 6 - 7  next   last

Voir toutes nos offres