activity
20162019
most citedTraining recurrent neural networks robust to incomplete data: application to Alzheimer's disease progression modeling

142 citations · 186 across the 3 of their papers we have counts for

collaborators

6 papers

cs.LG201913 cited

On the Initialization of Long Short-Term Memory Networks

Mostafa Mehdipour Ghazi, Mads Nielsen, Akshay Pai +4

Weight initialization is important for faster convergence and stability of deep neural networks training. In this paper, a robust initialization method is developed to address the…

stat.AP2019

Robust parametric modeling of Alzheimer's disease progression

Mostafa Mehdipour Ghazi, Mads Nielsen, Akshay Pai +4

Quantitative characterization of disease progression using longitudinal data can provide long-term predictions for the pathological stages of individuals. This work studies the rob…

cs.CV2019142 cited

Training recurrent neural networks robust to incomplete data: application to Alzheimer's disease progression modeling

Mostafa Mehdipour Ghazi, Mads Nielsen, Akshay Pai +4

Disease progression modeling (DPM) using longitudinal data is a challenging machine learning task. Existing DPM algorithms neglect temporal dependencies among measurements, make pa…

cs.CV2018

Robust training of recurrent neural networks to handle missing data for disease progression modeling

Mostafa Mehdipour Ghazi, Mads Nielsen, Akshay Pai +4

Disease progression modeling (DPM) using longitudinal data is a challenging task in machine learning for healthcare that can provide clinicians with better tools for diagnosis and…

cs.CV201731 cited

Visual Speech Recognition Using PCA Networks and LSTMs in a Tandem GMM-HMM System

Marina Zimmermann, Mostafa Mehdipour Ghazi, Hazım Kemal Ekenel +1

Automatic visual speech recognition is an interesting problem in pattern recognition especially when audio data is noisy or not readily available. It is also a very challenging tas…

cs.CV2016

A Comprehensive Analysis of Deep Learning Based Representation for Face Recognition

Mostafa Mehdipour Ghazi, Hazim Kemal Ekenel

Deep learning based approaches have been dominating the face recognition field due to the significant performance improvement they have provided on the challenging wild datasets. T…