I am a Ph.D. student at the Northeastern University, Boston. I am fortunate to be advised by Prof. David Bau. At the Interpretable Neural Networks lab we are doing exciting research on understanding the internal structure of large language models.
I received my B.Sc. in Computer Science and Engineering from Shahjalal University of Science and Technology. I worked as a research assistant at the SUST NLP lab during my final two semesters. I worked at the Samsung R&D institute at Bangladesh for a year after graduation. There I worked on optimizing the chromium engine for the browser application in Samsung wearables. I was also part of a robotics project that won 3rd place at the Samsung ROBOT Hackathon-2018. I came back to SUST to join as a Lecturer in the Computer Science department. There I was involved in multiple collaborative research works in NLP and Data Science.
Kevin Meng, Arnab Sen Sharma, Alex Andonian, Yonatan Belinkov, and David Bau. Submitted in ICLR 2023.
Arnab Sen Sharma, Mohammad Ruhul Amin, and Muztaba Fuad.
Nauros Romim, Mosahed Ahmed, Md Saiful Islam, Arnab Sen Sharma, Hriteshwar Talukder, Mohammad Ruhul Amin. “BD-SHS A Benchmark Dataset for Learning to Detect Online Bangla Hate Speech in Different Social Contexts”. Prested as a poster in LREC 2022
Md. Enamul Hoque, Md. Shariful Islam, Arnab Sen Sharma, Rashedul Islam, and Mohammad Ruhul Amin. 2021. “Challenges in Tracking the Risk of COVID-19 in Bangladesh; Evaluation of A Novel Method”. In Proceedings of August 15 (KDD Workshop on Data-driven Humanitarian Mapping, 27th ACM SIGKDD Conference). ACM, New York, NY, USA.
Sharma, A. S., Roy, T., Rifat, S. A. & Mridul, M. A. (2021). Presenting a Larger Up-to-Date Movie Dataset and Investigating the Effects of Pre-Released Attributes on Gross Revenue. Journal of Computer Science, 17(10), 870-888. https://doi.org/10.3844/jcssp.2021.870.888
A. S. Sharma, M. A. Mridul and M. S. Islam, “Automatic Detection of Satire in Bangla Documents; A CNN Approach Based on Hybrid Feature Extraction Model”, 2019 International Conference on Bangla Speech and Language Processing (ICBSLP), Sylhet, Bangladesh, 2019, pp. 1-5, doi:10.1109/ICBSLP47725.2019.201517. [IEEE Best Paper Award, awarded by ICBSLP, 2019]
A. Sen Sharma, M. Ahmed Mridul, M. Jannat and M. Saiful Islam, “A Deep CNN Model for Student Learning Pedagogy Detection Data Collection Using OCR,” 2018 International Conference on Bangla Speech and Language Processing (ICBSLP), Sylhet, 2018, pp. 1-6, doi:10.1109/ICBSLP.2018.8554701.
July, 2019 - Present, Sylhet
Kindly checkout my faculty profile at SUST here.
August, 2019 - Present, Sylhet
B.Sc.(Engg) in Computer Science & EngineeringCGPA: 3.91 out of 4.00 (Topper in my class)Taken Courses Include
Extracurricular Activities
| |||||||||||
Moulvibazar Govt. High School2003-2010 Secondary School CertificateGPA: 5 out of 5 |
An interactive website built with ReactJS and Flask to showcase our work on tracking and forecasting COVID‐19 situation in Bangladesh. The site is live at erdos.dsm.fordham.edu:3000. Please check the site from a desktop/laptop/tab. The site is not optimized for vertical smartphone screens.
Calculating the attention score of an online class based on students’ gaze tracking, under supervision of Dr. Mohammad Ruhul Amin, Assistant Professor, Fordham University.
Experimented with Siamese Neural Network architecture to calculate a similarity score between 2 sentence written in Bangla.
A desktop application aiming to help newbie competitive programmers to get a basic understanding of vastly used basic algorithms, data structures and different kinds of sorting techniques.
An arcade game for android platforms.
A web application aiming to help tourists to find hotels and restaurants near tourist spots.
An online audio sharing and listening platform.
A web application aiming to help instructors in making and sharing tutorials.
Prepared a huge new dataset by scraping different sites. Performed statistical analysis to find out how revenue generated in box-office is related to different pre-released attributes.
This competition allowed participants to work with freshly manufactured lines of robots by Samsung. I participated in that competition with an idea called BFF Robot as part of the team SRBD_Hyperbola. The idea was that a robot would become the daily companion of a child, adapting to the child as s/he grows; eventually, the child and the robot would become Best Friends Forever! We secured 3rd place with the global participation of more than 500 teams, and won a prize money worth of 1000 USD.
Internal capability certification of Samsung Electronics. Attained professional certificate at my second try. I was the only one who attained the certificate in the test held on 24 November, 2018.
In this course I learned,
In this course I learned,
In this course I learned,
1st part of Mathematics for Machine Learning series. In this course I learned about the basics of Linear Algebra and how to apply these concepts to Machine Learning. I learned about Eigenvalues and Eigenvectors, Transformation Matrix, the workings of simple Page-Ranking algorithms etc. in this course.
Grade achieved: 96%
2nd part of Mathematics for Machine Learning series. In this course I learned about basics of Linear Regression, Vector Calculus, Multivariable Calculus, Gradient Descent etc.
Grade achieved: 96.75%
Learned the steps involved in coding facial feature detection, representing a face as a set of measurements, and encoding faces. Also learned how to repurpose and adjust pre-existing systems.
Was required to implement an iOS application for iPhones for sensor data collection when I was working at SRBD. Also implemented/translated some modules of existing android apps for iOS.
Was required to implement an iOS application for iPhones for sensor data collection when I was working at SRBD. Also implemented/translated some modules of existing android apps for iOS.
Took this course when I was understanding the code-flow of V8 engine, the module of chromium browsers that compiles JavaScript. Refreshed my knowledge about c++ pointers.
Took this course out of self-interest.
Took this course out of self-interest.
