Sort by
Refine Your Search
-
Inria, the French national research institute for the digital sciences | Palaiseau, le de France | France | 26 days ago
data compression in physics simulations (communication/computation time/cost, quality of the solution...). The benchmark will be realized with benchopt [3] and will benefit from the distributed coding
-
implementations for compression, heterogeneous quantization, etc - reproduce state of the art network parameters with extreme quantization and compression of parameters - design and implement next-generation
-
mechanisms. The project will combine experimental studies with advanced signal processing and AI techniques (compressed sensing), aiming to detect early signs of failure and enable predictive maintenance
-
6-24): Construction of autoencoders for compression of high-dimensional fields. Sparse identification (SINDy) or genetic programming (GEP) for derivation of explicit, interpretable control laws