Mohammad Mahmudul Alam
University of Maryland, Baltimore CountyBiography
Mohammad Mahmudul Alam is a Ph.D. candidate in Computer Science at the University of Maryland, Baltimore County (UMBC). His ongoing research involves neuro-symbolic representations and their applications to deep learning. He is currently working as Graduate Research Assistant (GRA) in the Cognition, Robotics, and Learning (CORAL) lab at UMBC where he is advised by Professor Dr. Tim Oates and Dr. Edward Raff. He has completed his B.Sc. in Electrical and Electronic Engineering (EEE) from the Bangladesh University of Engineering and Technology (BUET).
Interests
- Deep Learning
- Natural Language Processing
- Neuro-symbolic Representations
Education
-
Ph.D. candidate in Computer Science 2024 (Expected)
University of Maryland, Baltimore County
Maryland, USA
-
BSc in Electrical and Electronic Engineering 2019
Bangladesh University of Engineering and Technology
Dhaka, Bangladesh
Selected Publications
Recent News
Oct 20, 2022
NeurIPS Workshop Paper!
New paper in NeurIPS Workshop on I Can’t Believe It’s Not Better (ICBINB): Understanding Deep Learning Through Empirical Falsification
June 16, 2022
HRR Python Package!
A python library developed for neuro-symbolic computations such as binding and unbinding of vector symbolic architecture known as Holographic Reduced Representations supports PyTorch, TensorFlow, Jax, and Flax.
May 15, 2022
Paper in ICML 2022!
Paper accepted titled "Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representations" in 39th International Conference on Machine Learning (ICML), July 2022, Baltimore, MD, USA.