All opportunities

Offers : 14

Privacy in embedding-based neural networks by means of homomorphic encryption

Mail Sélection

Start date : 1 January 2020

offer n° PsD-DRT-20-0021

AI presently emerges as the killer application of homomorphic encryption or FHE. Indeed, this kind of cryptography, which allows to perform general calculations directly over encrypted data, has the potential of bringing privacy-by-construction for either or both user or model data, depending on the application scenario. In the longer term, FHE may also help protect training data, unleashing new usages in training data sharing and collaborative AI model building. In this context, the present postdoctoral offer aims at investigating the practical relevance of homomorphic encryption in the case of a specific kind of neural networks, the so-called embedding-based networks, which, for intrinsic reasons, both are favorable to good homomorphic execution performances and enjoy a wide spectrum of applications. Thus, this postdoctorate will study the theoretical and practical aspects cropping up in several FHE integration scenarios and will also lead to prototyping work on a best-in-class open-source speech recognition system using an embedding-based network.

  • Keywords : Engineering sciences, Computer science and software, DACLE, Leti
  • Laboratory : DACLE / Leti
  • CEA code : PsD-DRT-20-0021
  • Contact : renaud.sirdey@cea.fr

Scalable digital architecture for Qubits control in Quantum computer

Mail Sélection

Start date : 1 January 2021

offer n° PsD-DRT-20-0116

Scaling Quantum Processing Units (QPU) to hundreds of Qubits leads to profound changes in the Qubits matrix control: this control will be split between its cryogenic part and its room temperature counterpart outside the cryostat. Multiple constraints coming from the cryostat (thermal or mechanical constraints for example) or coming from Qubits properties (number of Qubits, topology, fidelity, etc…) can affect architectural choices. Examples of these choices include Qubits control (digital/analog), instruction set, measurement storage, operation parallelism or communication between the different accelerator parts for example. This postdoctoral research will focused on defining a mid- (100 to 1,000 Qubits) and long-term (more than 10,000 Qubits) architecture of Qubits control at room temperature by starting from existing QPU middlewares (IBM QISKIT for example) and by taking into account specific constraints of the QPU developed at CEA-Leti using solid-state Qubits.

  • Keywords : Engineering sciences, Technological challenges, Electronics and microelectronics - Optoelectronics, New computing paradigms, circuits and technologies, incl. quantum, DACLE, Leti
  • Laboratory : DACLE / Leti
  • CEA code : PsD-DRT-20-0116
  • Contact : eric.guthmuller@cea.fr

Simulation and electrical characterization of an innovative logic/memory CUBE for In-Memory-Computing

Mail Sélection

Start date : 1 January 2020

offer n° PsD-DRT-20-0029

For integrated circuits to be able to leverage the future “data deluge” coming from the cloud and cyber-physical systems, the historical scaling of Complementary-Metal-Oxide-Semiconductor (CMOS) devices is no longer the corner stone. At system-level, computing performance is now strongly power-limited and the main part of this power budget is consumed by data transfers between logic and memory circuit blocks in widespread Von-Neumann design architectures. An emerging computing paradigm solution overcoming this “memory wall” consists in processing the information in-situ, owing to In-Memory-Computing (IMC).

However, today’s existing memory technologies are ineffective to In-Memory compute billions of data items. Things will change with the emergence of three key enabling technologies, under development at CEA-LETI: non-volatile resistive memory, new energy-efficient nanowire transistors and 3D-monolithic integration. At LETI, we will leverage the aforementioned emerging technologies towards a functionality-enhanced system with a tight entangling of logic and memory.

The post-doc will perform electrical characterizations of CMOS transistors and Resistive RAMs in order to calibrate models and run TCAD/spice simulations to drive the technology developments and enable the circuit designs.

  • Keywords : Engineering sciences, Technological challenges, Electronics and microelectronics - Optoelectronics, New computing paradigms, circuits and technologies, incl. quantum, DCOS, Leti
  • Laboratory : DCOS / Leti
  • CEA code : PsD-DRT-20-0029
  • Contact : francois.andrieu@cea.fr

Design of innovative time-domain microphone readout using Injection Locked Oscillators

Mail Sélection

Start date : 1 January 2020

offer n° PsD-DRT-20-0023

Nowadays, Voice Activity Detection is a hot research topic. This application needs the design of high linearity, high dynamic ( > 100 dBSpl) and low noise (< 25 dBSpl) microphones putting stringent requirement on both the transducer and the readout electonics. State of the art microphone readouts are based on a classical amplifier and sigma delta conversion. They fulfill the needs in term of dynamic and noise but at the expense of a high power consumption (1 mW) not compliant with mobile applications.

CEA-LETI is currently working on an innovative transducer design that fulfills the needs in terms of dynamic and noise. To go along with the transducer development, CEA-LETI is searching for a PostDoc whose mission will be to study an Ultra Low Power architecture of readout circuits working in the time-domain and based on Injection Locked Oscillators. The post doc work will consist in an architecture study and its evaluation in term of expected performances. In a second time an optimized chip should be designed and fabricated. Evaluation of the solution will be made by a thorough measurement of the test chip.

  • Keywords : Engineering sciences, Technological challenges, Cyber physical systems - sensors and actuators, Electronics and microelectronics - Optoelectronics, DACLE, Leti
  • Laboratory : DACLE / Leti
  • CEA code : PsD-DRT-20-0023
  • Contact : franck.badets@cea.fr

Nano-optomechanical silicon accelerometer for high performance applications

Mail Sélection

Start date : 1 June 2020

offer n° PsD-DRT-20-0035

Inertial sensors (accelerometers and gyrometers) are at the heart of a large number of consumer-and low-cost applications such as smartphones and tablets, but also higher added value, higher-performance applications such as navigation for autonomous vehicles, aeronautics or space. Silicon microsystems (MEMS) are today a very mature technology and several millions are sold each year. However, they are today unable to address high-performance applications.

LETI has been pioneering the development of optomechanical sensors “on-chip”: light is guided in thin silicon layers in a similar way to photonics techniques. This light interacts with an object in motion such as a mechanical resonator or a seismic mass. This displacement modulates the intensity of the measured light, which allows the determination of the object’s acceleration. This technology was developed in the 2000s in fundamental research, and in particular enabled gravitational wave detectors. LETI is developing this technology on-chip at the nanoscale, with displacement sensitivities several orders of magnitude better than electrical transductions.

First optomechanical accelerometers were designed and fabricated in LETI’s quasi-industrial clean rooms for initial characterization tests. The hired fellow with have to become familiar with these devices, to confirm the first optical results, and then most importantly to assess their performances under acceleration: a test setup will have to be realized for this purpose. She or he will have to provide feedback on the modeling and the design from the measurements in order to ensure the comprehension of all phenomena at play. Finally, the postdoctoral fellow will have to propose new designs aimed at the expected high performances. These devices will be fabricated by the clean room, tested by the fellow and and compared to the expected performance.

  • Keywords : Technological challenges, Cyber physical systems - sensors and actuators, DCOS, Leti
  • Laboratory : DCOS / Leti
  • CEA code : PsD-DRT-20-0035
  • Contact : sebastien.hentz@cea.fr
More information
X