Search Results for author:
Found 9 papers, 4 papers with code
Hamiltonian Adaptive Importance Sampling
Importance sampling (IS) is a powerful Monte Carlo (MC) methodology for approximating integrals, for instance in the context of Bayesian inference.
Deep Learning Applications for Lung Cancer Diagnosis: A systematic review
This research is superior to other review articles in this field due to the complete review of relevant articles and systematic write up.
Vector Transport Free Riemannian LBFGS for Optimization on Symmetric Positive Definite Matrix Manifolds
Riemannian LBFGS (RLBFGS) is an extension of this method to Riemannian manifolds.
A Framework to Enhance Generalization of Deep Metric Learning methods using General Discriminative Feature Learning and Class Adversarial Neural Networks
To address this limitation, we propose a framework to enhance the generalization power of existing DML methods in a Zero-Shot Learning (ZSL) setting by general yet discriminative representation learning and employing a class adversarial neural network.
Accurate and fast matrix factorization for low-rank learning
In this paper, we tackle two important problems in low-rank learning, which are partial singular value decomposition and numerical rank estimation of huge matrices.
Matrix Factorization / Decomposition
Riemannian optimization
Neural Generalization of Multiple Kernel Learning
By this interpretation, we propose a Neural Generalization of Multiple Kernel Learning (NGMKL), which extends the conventional multiple kernel learning framework to a multi-layer neural network with nonlinear activation functions.
Sparse Bayesian approach for metric learning in latent space
Also, the present work is extended for learning in the feature space induced by an RKHS kernel.
RELF: Robust Regression Extended with Ensemble Loss Function
Ensemble techniques are powerful approaches that combine several weak learners to build a stronger one.
On Extending Neural Networks with Loss Ensembles for Text Classification
Ensemble techniques are powerful approaches that combine several weak learners to build a stronger one.
