Interests
Prospective doctoral research areas
Within Artificial Intelligence (AI), I am particularly interested in Machine Learning (ML) and its role in developing systems that can generalize, adapt, and solve complex tasks.
I would like to investigate Generative AI, particularly Large Language Models (LLMs) and multimodal systems; Agentic AI, with an emphasis on planning, tool use, and collaboration between agents; and Reinforcement Learning (RL) for adaptive decision-making.
Across these areas, I am interested in generalization, learning efficiency, and reliability. Evaluation and Model Selection remain part of this broader interest, informed by my undergraduate research.
TOS, a relative metric for model selection
First-author publication, IEEE RAAICON 2021
TOS: A Relative Metric Approach for Model Selection in Machine Learning Solutions
R. Shaha, D. Talukder, M. A. Iqbal and M. M. Haque. 2021 IEEE International Conference on Robotics, Automation, Artificial-Intelligence and Internet-of-Things (RAAICON), pages 26 to 31, 2021.
TOS combines standardized accuracy and error measures. Both are standardized across the candidate models being compared:
In the landslide comparison, the two measures are cross-validated accuracy and false-negative rate. Specifying both makes the selection criterion explicit. It does not, by itself, establish the appropriate cost of either error for a deployment.
Origin: the landslide thesis
Undergraduate research at CUET
My undergraduate thesis built a landslide susceptibility model for the Rangamati Hill Tracts (a district within Chattogram division, Bangladesh). When it came time to choose between the candidate models, several of them sat within one standard deviation of each other on accuracy. That made a choice based only on the highest mean accuracy difficult to justify.
Accuracy also counts a missed landslide and a false alarm equally. I wanted the comparison to account explicitly for missed landslides, which led to the TOS paper and my continuing interest in evaluation.
Limitation: candidate-pool dependence
How the comparison set affects the ranking
TOS is not independent of irrelevant alternatives
Because the z-scores are computed across the pool, adding a candidate that can never win may still reorder the candidates above it. The score is a property of the field as well as of the models.
On the thesis data, adding a most-frequent-class baseline leaves the winner unchanged but swaps two mid-ranked candidates. A ranking produced this way is therefore only meaningful when reported alongside the pool it was computed over.
The candidate-pool experiment reproduces this change. I want to study which ranking properties a relative criterion should preserve and when its dependence on the pool is acceptable.
Current direction
My prospective research directions include improving reasoning and tool use in language models, studying how agents learn from interaction and feedback, and adapting generative models to new tasks. I am open to refining these interests into a focused doctoral research programme, building on my experience with model evaluation.