Scholar
Abdullah Al Imran
Google Scholar ID: _oWyQ2UAAAAJ
Applied AI Researcher | Data/AI Scientist
Citations & Impact
Citations
402
H-index
12
i10-index
14
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Publications:
- - "FourierKAN outperforms MLP on Text Classification Head Fine-tuning" (arXiv preprint arXiv:2408.08803, 2024)
- - "BaitBuster-Bangla: A Comprehensive Dataset for Clickbait Detection in Bangla with Multi-Feature and Multi-Modal Analysis" (Data in Brief, 2024)
- - "Large-scale Probabilistic Forecasting of Consumer Engagement of CPG Products using Heterogeneous Web Data" (Procedia Computer Science, 2024)
Research Experience
- In resource constraint settings, adaptation to downstream classification tasks involves fine-tuning the final layer of a classifier (i.e., classification head) while keeping the rest of the model weights frozen. Investigated the efficacy of KAN and its variant, Fourier KAN (FR-KAN), as alternative text classification heads. Experiments revealed that FR-KAN significantly outperformed MLPs with an average improvement of 10% in accuracy and 11% in F1-score across seven pre-trained transformer models and four text classification tasks. Additionally, constructed a large multi-modal Bangla YouTube clickbait dataset consisting of 253,070 data points.
Background
- Born and raised in the city of mosques, Dhaka, Bangladesh. I am a passionate programmer, Data Science/Machine Learning professional, and a researcher. I help companies make impactful data-driven decisions through utilizing and productionalizing AI and Data Science technologies. I’m a goal-oriented seasoned Data Science and Machine Learning professional with deep affection for data and proven expertise in developing and deploying end-to-end, highly scalable ML models and services. Predicting unknowns, discovering patterns, and revealing useful insights from data excites me the most. I’m dynamic in personality and a rapid learner who is always desperate for knowledge and wisdom.
Miscellany
- Technical Skills:
- - Data Science & AI Aficionado
- - Wisdom Seeker
Co-authors