Aryan Mobiny
Houston Ubiquitous Learning Algorithms (HULA) Laboratory, Ph.D. Student
amobiny at uh.edu

Biography

I am an ECE Ph.D. student at the University of Houston, currently working as a research assistant at HULA Lab and fellow at the Center for Advanced Computing and Data Science (CACDS). My research is mainly focused on Machine Learning, Deep Learning, Reinforcement Learning and their applications in Computer Vision and Natural Language Processing. To find more information about my research topics and other experiences, see my Resume.

NEWS

  • Our workshop on "TensorFlow for Biomedical Research" will be held on January 18th, 2019 in UH-CACDS. Thanks to out sponsor Helwett-Packard Enterprise . More info
  • Our paper titled "Fast CapsNet for Lung Cancer Screening" is accepted to top conference in medical imaging (MICCAI'2018).
  • Our mini-workshop named "Deep Learning in TensorFlow" will be held on April 30th at the Center for Advanced Computing and Data Science (CACDS). More info.
  • Our workshop "TensorFlow in Deep Learning Research" will be held on February 2nd till March 16th. This is a joint workshop in collaboration with Math Department. Please register through information provided in this link.

Fall 2017 - Present
Fellow at Center for Advanced Computing and Data Science (CACDS)
Fall 2015 - Present
Ph.D. student in Electrical and Computer Engineering at University of Houston
Fall 2017 - Present
Co-founder at Easy-TensorFlow
Fall 2011 - Spring 2014
M.S. in Electical and Computer Engineering from University of Tehran
Fall 2006 - Spring 2011
B.S. in Electrical and Computer Engineering from Iran University of Science and Technology (IUST)

Selected Publications

(Check out my Resume for the full list of publications.)

Assaying neural patterns using scalp electroencephalography from children in a naturally engaging unconstrained video game playing experience


Developing neural networks are likely to be endowed with functionally important variability across context, age, gender and other, as yet unknown, variables. To examine how neural responses vary across such factors, we assayed neural activity of children at baseline and while they played a videogame at the Children’s Museum of Houston.

Joint work with University of Houston Brain-Machine Interface Systems Team.

Fast CapsNet for Lung Cancer Screening


This paper investigates the use of capsule networks (CapsNets) as an alternative to CNNs. We show that CapsNets significantly outperforms CNNs when the number of training samples is small. To increase the computational efficiency, our paper proposes a consistent dynamic routing mechanism that results in 3x speedup of CapsNet. Finally, we show that the original image reconstruction method of CapNets performs poorly on lung nodule data. We propose an efficient alternative, called convolutional decoder, that yields lower reconstruction error and higher classification accuracy.

Joint work with Hien Van Nguyen.

Lung Cancer Screening Using Adaptive Memory-Augmented Recurrent Networks
ArXiv 2017


we investigate the effectiveness of deep learning techniques for lung nodule classification in computed tomography scans. Our paper also proposes a novel framework for rapidly adapting deep networks to the radiologists' feedback, or change in the data due to the shift in sensor's resolution or patient population. Finally, we propose using inconsistency density function, computed by a recurrent network, as a way to discover potentially noisy labels in lung data.

Joint work with Hien Van Nguyen and Supratik K. Moulik.

Text-Independent Speaker Verification Using Long Short-Term Memory Networks
ArXiv 2018

In this paper, an architecture based on Long Short-Term Memory Networks has been proposed for the text-independent scenario which is aimed to capture the temporal speaker-related information by operating over traditional speech features. An LSTM architecture is trained to create a discrimination space for validating the match and non-match pairs for speaker verification.

Joint work with Mohammad Najarian.

Radiologist-Friendly and Automatic Lung Cancer Screening Using Memory Recurrent Networks
Submitted to IEEE Transactions on Medical Imaging

Most of existing computer aided diagnosis (CAD) systems follow a rigid paradigm where the classifier’s decision function is optimized during the training phase, and fixed during the test phase. These systems are often perceived as unfriendly as they do not allow clinicians to provide input. They are also unable to cope with the perpetual changes in data distribution caused by different sensing technologies, imaging protocols, and patient populations. To address these shortcomings, this paper proposes a novel CAD model capable of incorporating expert domain knowledge in real-time to improve its decision function.

Joint work with Hien Van Nguyen, Supratik K. Moulik, Naveen Garg and Carol C. Wu..

Projects



Easy-TensorFlow is an open source project which is aimed to provide simple and ready-to-use tutorials for TensorFlow.

This project has been GitHub trending repository of the month and currentlu has more than 2.5K followers on GitHub.

Joint work with Jahandar Jahanipour and Mohammad Najarian.

Semantic Segmentation of the Mouse Brain


In this research, we designed and implemented a novel fully denesly connected 3D convolutional network to model the cellular and vascular structure in the mouse brain.

Joint work with Leila Saadatifard, Pavel Govyadinov, Hien Van Nguyen and David Mayerich.

Cell Liveness Detection

Immunotherapy is a type of cancer treatment that boosts the body's natural defenses to fight cancer. Detecting and Tracking the effector and target cells is a demanding task which can push the immunuterapy research forward.

In this project, we designed a pipeline to detect cells using Faster RCNN, and a mixture of Capsule Network and Bidirectional LSTM to classify the cells and check if each cell is dead/alive during time.

Joint work with Hengyang Lu.

Semantic Segmentation of Organs from CT Scans

We're working on a novel 3D fully-convolutional network for automatic segmentation of anatomical structures on 3D CT images.

The proposed architecture accomplishes an end-to-end, voxel-wise multiple-class classification to map each voxel in a CT image directly to an anatomical label using very few samples. This is often a necessity in biomedical domain where data collection and annotation is expensive and time-consuming.

Joint work with MD Anderson Cancer Center.

DropConnect for Model Uncertainty Estimation

Popular deep learning models created today produce a point estimate but not an uncertainty value. In classification models, the probability vector obtained at the end of the pipeline (the softmax output) is often erroneously interpreted as model confidence. However, a model can be uncertain in its predictions even with a high softmax output. Understanding if the model is under-confident or falsely over-confident can help reasoning about the model.

In this project, we introduce "Sampling DropConnect" as a practical method to estimate model uncertainty: what the model doesn't know due to lack of training data.

Joint work with Hien Van Nguyen.

Last updated December 12th, 2018.