Search Results for author: Kamal Youcef-Toumi

Found 7 papers, 2 papers with code

Enhanced Human-Robot Collaboration using Constrained Probabilistic Human-Motion Prediction

no code implementations5 Oct 2023 Aadi Kothari, Tony Tohme, Xiaotong Zhang, Kamal Youcef-Toumi

We propose a novel human motion prediction framework that incorporates human joint constraints and scene constraints in a Gaussian Process Regression (GPR) model to predict human motion over a set time horizon.

GPR Human motion prediction +2

MESSY Estimation: Maximum-Entropy based Stochastic and Symbolic densitY Estimation

no code implementations7 Jun 2023 Tony Tohme, Mohsen Sadr, Kamal Youcef-Toumi, Nicolas G. Hadjiconstantinou

We find that the addition of a symbolic search for basis functions improves the accuracy of the estimation at a reasonable additional computational cost.

Density Estimation Symbolic Regression

GSR: A Generalized Symbolic Regression Approach

no code implementations31 May 2022 Tony Tohme, Dehong Liu, Kamal Youcef-Toumi

Identifying the mathematical relationships that best describe a dataset remains a very challenging problem in machine learning, and is known as Symbolic Regression (SR).

regression Symbolic Regression

Reliable Neural Networks for Regression Uncertainty Estimation

no code implementations16 Sep 2021 Tony Tohme, Kevin Vanslette, Kamal Youcef-Toumi

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.

Ensemble Learning regression

D-DARTS: Distributed Differentiable Architecture Search

1 code implementation20 Aug 2021 Alexandre Heuillet, Hedi Tabia, Hichem Arioui, Kamal Youcef-Toumi

This approach is accompanied by a novel metric that measures the distance between architectures inside our custom search space.

Neural Architecture Search

Instance Semantic Segmentation Benefits from Generative Adversarial Networks

1 code implementation26 Oct 2020 Quang H. Le, Kamal Youcef-Toumi, Dzmitry Tsetserukou, Ali Jahanian

Rethinking reconstruction networks as a generator, we define the problem of predicting masks as a GANs game framework: A segmentation network generates the masks, and a discriminator network decides on the quality of the masks.

Autonomous Driving Instance Segmentation +5

Cyclic Graph Dynamic Multilayer Perceptron for Periodic Signals

no code implementations25 Sep 2019 Mikio Furokawa, Erik Gest, Takayuki Hirano, Kamal Youcef-Toumi

However, it is difficult to perfectly control the collection timing of the measurements.

Cannot find the paper you are looking for? You can Submit a new open access paper.