The striking progress of statistical learning over the past decade has led to wild expectations about the ability of machines to reproduce human behavior.
The Artificial Intelligence lab designs solutions to address issues in future networks, computer vision, cyberdefense, and e-health. Designing embedded imaging and radio communication applications, anomaly detection or classification, system resilience, human factor management, pathology prediction, and reliable diagnostics are the main challenges being tackled. To do so, the lab relies on traditional disciplines of automated language, signal, image processing, 3D vision, and dynamic programming, whose potential has been compounded by statistical learning. It can also count on its skills in hardware/software engineering and a legal team. Its methodological approach makes its algorithms explainable and robust so as to facilitate their certification.
With current learning techniques, we can automate tasks as varied as interpreting text, mapping space, generating realistic images, predicting behaviors, and planning actions.
11.23.2023
Distributed Function Cache for Heterogeneous Serverless Cloud
Serverless computing relies on the composition of short-lived stateless functions that are executed following events such as HTTP requests. These functions are mostly deployed in containers called ”replicas”. Scaling a FaaS application, i.e. to maintain a consistent level of performance, consists in growing or shrinking the pool of function replicas following load peaks. When a function is…
read the publication
12.20.2022
Channel charting based beamforming
Channel charting (CC) is an unsupervised learning method allowing to locate users relative to each other without reference. From a broader perspective, it can be viewed as a way to discover a low-dimensional latent space charting the channel manifold. In this paper, this latent modeling vision is leveraged together with a recently proposed location-based beamforming (LBB) method to show that…
read the publication
12.09.2021
mpNet: variable depth unfolded neural network for massive MIMO channel estimation
Massive multiple-input multiple-output (MIMO) communication systems have a huge potential both in terms of data rate and energy efficiency, although channel estimation becomes challenging for a large number of antennas. Using a physical model allows to ease the problem by injecting a priori information based on the physics of propagation. However, such a model rests on simplifying assumptions and…
read the publication
12.27.2021
DEEP LEARNING FOR LOCATION BASED BEAMFORMING WITH NLOS CHANNELS
Massive MIMO systems are highly efficient but critically rely on accurate channel state information (CSI) at the base station in order to determine appropriate precoders. CSI acquisition requires sending pilot symbols which induce an important overhead. In this paper, a method whose objective is to determine an appropriate precoder from the knowledge of the user's location only is proposed. Such…
read the publication
