Abdullah Mamun

Graduate Research Associate

Arizona State University

About Me

I am a Ph.D. student at Arizona State University. I work as a Graduate Research Associate at Embedded Machine Intelligence Lab (EMIL) under the supervision of Dr. Hassan Ghasemzadeh. Visit my website at abdullah-mamun.com.

Currently, my work includes building and optimizing deep learning models for time-series data. My works have been published in EMBC'22, BSN'22, and BSN'23 conferences and I have multiple journal and confernce submissions under review. I also actively peer-review conference and journal submissions.

I am conducting a user study at ASU where we collect activity and stress data for machine learning algorithm design. If you are willing to participate, visit here.

Latest

A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
Domain-Informed Label Fusion Surpasses LLMs in Free-Living Activity Classification
Large Language Models are Zero-Shot Reasoners
Reinforcement Learning for Solving the Vehicle Routing Problem
Random Erasing Data Augmentation
Poster: HydraSense: Personalized Hydration Monitoring with Wearables and Machine Learning [Abstract]
Scaling MLPs: A Tale of Inductive Bias
U-Net: Convolutional Networks for Biomedical Image Segmentation
Binary imbalanced data classification based on diversity oversampling by generative models
A Survey of Methods for Time Series Change Point Detection
Open-World Semi-Supervised Learning
Towards A Rigorous Science of Interpretable Machine Learning
Neonatal Risk Modeling and Prediction
Neonatal Risk Modeling and Prediction
Self-Supervised Adversarial Distribution Regularization for Medication Recommendation
Invited talk: Time-Series Wearable Activity Forecasting
Time Series Data Augmentation for Deep Learning: A Survey
Language Models are Few-Shot Learners
Masked Autoencoders Are Scalable Vision Learners
Reinforcement Learning for Solving the Vehicle Routing Problem
Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks
Multimodal Time-Series Activity Forecasting for Adaptive Lifestyle Intervention Design
Multimodal Time-Series Activity Forecasting for Adaptive Lifestyle Intervention Design
ViViT: A Video Vision Transformer
A Review of Approximate Dynamic Programming and Feature-based Aggregation
Multiagent Rollout Algorithms and Reinforcement Learning
Designing Deep Neural Networks Robust to Sensor Failure in Mobile Health Environments
From Known to Unknown: Knowledge-guided Transformer for Time-Series Sales Forecasting in Alibaba
Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models
Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
Modeling Long and Short-Term Temporal Patterns with Deep Neural Networks
The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies
GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism.