I am a Computer Science Ph.D. Candidate at the University of California, Los Angeles. My research is focused on the intersection of machine learning and health informatics. I like to design, improve, and utilize deep learning inference pipelines, especially for practical problems in the medical domain and advancing healthcare systems.
Ph.D. in Computer Science
University of California, Los Angeles
M.Sc. in Computer Science, 2020
University of California, Los Angeles
B.Sc. in Computer Science, 2017
Sharif University of Technology
B.Sc. in Electrical Engineering, 2017
Sharif University of Technology
Graduate Student Researcher in eHealth and Data Analytics lab, focusing on deep representation learning and healthcare AI
Selected Research
Teaching
Major: Artificial Intelligence
Minor 1: Data Science Computing
Minor 2: Computer Vision
Selected Coursework: Deep Learning Topics (A+), Machine Learning in Natural Language Processing (A), Bayesian Networks (A), Probabilistic Programming and Relational Learning (A), Probabilistic Graphical Models (A), Learning from Text (A)
Computer Science Thesis: Semi-supervised Indoor Layout Estimation using Fully Convolutional Neural Networks
Electrical Engineerinng Thesis: Cuffless Blood Pressure Estimation using iPPG and Eulerian Video Magnification and Constrained Local Neural Fields
Selected Coursework: Statistics (A+), Computer Vision (A+), Image Processing (A+), Stochastic Processes (A), Information Theory (A+), Cryptography (A+), Data Structures (A+), Algorithm Design (A+)
Unsupervised Universal Patient Representation:
Clinical Note Generation and Representation: Task-specific Representation Learning and Generative Modeling for Radiology Reports
Visualization and Monitoring Dashboard: Interactive Visualizations and Statistical Analysis of High-Dimensional Data and Exploring Task Metric Spaces with Neural Network
Research
Teaching
PaperView - going over the paper -> “Schick, Timo, et al. ‘Toolformer- Language models can teach themselves to use tools.’ arXiv preprint arXiv:2302.04761 (2023).”
PaperView - going over the paper -> “Paul, Mansheej, Surya Ganguli, and Gintare Karolina Dziugaite. “Deep learning on a data diet - Finding important examples early in training.” Advances in Neural Information Processing Systems 34 (2021) - 20596-20607.”
PaperView - going over the paper -> “Gomes, Diana, et al. When Are Graph Neural Networks Better Than Structure-Agnostic Methods?. I Can’t Believe It’s Not Better Workshop - Understanding Deep Learning Through Empirical Falsification.”
PaperView - going over the paper -> “Misra, Diganta. “Mish - A self regularized non-monotonic activation function.” arXiv preprint arXiv:1908.08681 (2019).”
PaperView - going over the paper -> “Windsor, R., Jamaludin, A., Kadir, T. and Zisserman, A., 2021. Self-supervised multi-modal alignment for whole body medical imaging. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2021, 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part II 24 (pp. 90-101). Springer International Publishing.”
Previous works have demonstrated the importance of considering different modalities on molecules, each of which provide a varied granularity of information for downstream property prediction tasks. Our method combines variants of the recent TransformerM architecture with Transformer, GNN, and ResNet backbone architectures. Models are trained on the 2D data, 3D data, and image modalities of molecular graphs. We ensemble these models with a HuberRegressor. The models are trained on 4 different train/validation splits of the original train + valid datasets. This yields a winning solution to the 2\textsuperscript{nd} edition of the OGB Large-Scale Challenge (2022) on the PCQM4Mv2 molecular property prediction dataset. Our proposed method achieves a test-challenge MAE of and a validation MAE of . Total inference time for our solution is less than 2 hours.
Analyzing and inspecting bone marrow cell cytomorphology is a critical but highly complex and time-consuming component of hematopathology diagnosis. Recent advancements in artificial intelligence have paved the way for the application of deep learning algorithms to complex medical tasks. Nevertheless, there are many challenges in applying effective learning algorithms to medical image analysis, such as the lack of sufficient and reliably annotated training datasets and the highly class-imbalanced nature of most medical data. Here, we improve on the state-of-the-art methodologies of bone marrow cell recognition by deviating from sole reliance on labeled data and leveraging self-supervision in training our learning models. We investigate our approach’s effectiveness in identifying bone marrow cell types. Our experiments demonstrate significant performance improvements in conducting different bone marrow cell recognition tasks compared to the current state-of-the-art methodologies.
This paper processes and combines an extensive collection of publicly available datasets to provide a unified information source for representing geographical regions with regards to their pandemic-related behavior. The features are grouped into various categories to account for their impact based on the higher-level concepts associated with them. This work uses several correlation analysis techniques to observe value and order relationships between features, feature groups, and COVID-19 occurrences. Dimensionality reduction techniques and projection methodologies are used to elaborate on individual and group importance of these representative features. In addition, a specific RNN-based inference pipeline called DoubleWindowLSTM-CP is designed in this work for predictive event modeling, thus utilizing sequential patterns as well as enabling concise record representation.
Electrocardiogram (ECG) can be reliably used as a measure to monitor the functionality of the cardiovascular system. Recently, there has been a great attention towards accurate categorization of heartbeats. While there are many commonalities between different ECG conditions, the focus of most studies has been classifying a set of conditions on a dataset annotated for that task rather than learning and employing a transferable knowledge between different tasks. In this paper, we propose a method based on deep convolutional neural networks for the classification of heartbeats which is able to accurately classify five different arrhythmias in accordance with the AAMI EC57 standard. Furthermore, we suggest a method for transferring the knowledge acquired on this task to the myocardial infarction (MI) classification task. We evaluated the proposed method on PhysionNet’s MIT-BIH and PTB Diagnostics datasets. According to the results, the suggested method is able to make predictions with the average accuracies of 93.4% and 95.9% on arrhythmia classification and MI classification, respectively.