I am Soumya Tarafder, a pre final year student at Indian Institute of Technology Kharagpur, India. As an undergraduate, I have balanced a rigorous academic curriculum encompassing a diverse field of studies ranging from full stack development and data science to machine learning and artificial intelligence. Besides sound understanding of the machine learning models, I also possess strong analytical skill, an affinity for problem solving and hand-on experience with various statistical models and machine learning algorithms
Find out my curriculum vitae here
Frontend (HTML, CSS, JavaScript, React, Angular) | Backend (Node.js, PHP) | Database Management (SQL, MongoDB) | Version Control (Git, GitHub) | Deployment and DevOps (AWS, Docker)
Data Mining and Exploration | Data Manipulation (Python, R) | Data Visualization (Power BI, Matplotlib in Python) | Database Querying (SQL)
Machine Learning Model Development (Python, R, Scikit-Learn, TensorFlow) | Deep Learning (Python, TensorFlow, Keras) | Natural Language Processing (Python, NLTK, spaCy)
Find out some of my projects below. Also You can check this link to view my GSoC'23 related works!
Architectural synthesis has gained rapid dominance in the design flows of application specific computing. Exploring an optimal design point during architectural synthesis is a tedious task owing to the orthogonal issues of reducing exploration time and enhancing design quality as well as resolving the conflicting parameters of power and performance. Therefore, worked in a paper that represents a novel design space exploration (DSE) methodology multi-objective particle swarm exploration MO-PSE, based on the particle swarm optimization (PSO) for designing application specific processor (ASP).
Prepared a web application to perform Tower of London Test. Tower of London was developed by Tim Shallice to measure planning and problem solving skill is various users. Technically there are three ribs of different heights and three balls to achieve the target configuration. But the user has to achieve the target configuration in minimum number of moves. And after getting the input from the users we can analyze the entire data provided by them. Initially one had to download PEBL software for this experiment. But a web application can make the entire process more spontaneous.