Zobrazeno 1 - 10
of 368
pro vyhledávání: '"Youcef-Toumi, Kamal"'
We introduce an Invertible Symbolic Regression (ISR) method. It is a machine learning technique that generates analytical relationships between inputs and outputs of a given dataset via invertible maps (or architectures). The proposed ISR method natu
Externí odkaz:
http://arxiv.org/abs/2405.06848
In this work, we present an adjoint-based method for discovering the underlying governing partial differential equations (PDEs) given data. The idea is to consider a parameterized PDE in a general form and formulate a PDE-constrained optimization pro
Externí odkaz:
http://arxiv.org/abs/2401.17177
Perception serves as a critical component in the functionality of autonomous agents. However, the intricate relationship between perception metrics and robotic metrics remains unclear, leading to ambiguity in the development and fine-tuning of percep
Externí odkaz:
http://arxiv.org/abs/2312.07744
Human motion prediction is an essential step for efficient and safe human-robot collaboration. Current methods either purely rely on representing the human joints in some form of neural network-based architecture or use regression models offline to f
Externí odkaz:
http://arxiv.org/abs/2310.03314
We introduce MESSY estimation, a Maximum-Entropy based Stochastic and Symbolic densitY estimation method. The proposed approach recovers probability density functions symbolically from samples using moments of a Gradient flow in which the ansatz serv
Externí odkaz:
http://arxiv.org/abs/2306.04120
Identifying the mathematical relationships that best describe a dataset remains a very challenging problem in machine learning, and is known as Symbolic Regression (SR). In contrast to neural networks which are often treated as black boxes, SR attemp
Externí odkaz:
http://arxiv.org/abs/2205.15569
Publikováno v:
Reliability Engineering & System Safety, January 2023, Volume 229, 108811
While deep neural networks are highly performant and successful in a wide range of real-world problems, estimating their predictive uncertainty remains a challenging task. To address this challenge, we propose and implement a loss function for regres
Externí odkaz:
http://arxiv.org/abs/2109.08213
Differentiable ARchiTecture Search (DARTS) is one of the most trending Neural Architecture Search (NAS) methods. It drastically reduces search cost by resorting to weight-sharing. However, it also dramatically reduces the search space, thus excluding
Externí odkaz:
http://arxiv.org/abs/2108.09306
Effective dipole moment method has been widely accepted as the de facto technique in predicting the dielectrophoretic force due to the non-uniform electric field. In this method, a finite-particle is modeled as an equivalent point-dipole that would i
Externí odkaz:
http://hdl.handle.net/1721.1/29834
During the last decade, large and costly instruments are being replaced by system based on microfluidic devices. Microfluidic devices hold the promise of combining a small analytical laboratory onto a chip-sized substrate to identify, immobilize, sep
Externí odkaz:
http://hdl.handle.net/1721.1/7464