Milan Ghimire
B.E. in Computer Engineering
I hold a bachelor's degree in Computer Engineering and intend to pursue a master's in Computer Science. My primary research interests lie in artificial intelligence and machine learning, areas I actively explore through independent study and hands-on projects.
Projects
Handwriting Recognition using PyTorch
A deep learning project that trains a Convolutional Neural Network (CNN) in PyTorch to recognise handwritten digits from the MNIST dataset, tracked end-to-end with TensorBoard.
Movie Recommendation System using TMDB Dataset
A content-based movie recommendation system using TF-IDF vectorization and cosine similarity on TMDB metadata.
Experience
Python Programming Instructor
Skill Spark Pvt. Ltd.
Taught Python fundamentals including data structures, logic building, and problem-solving. Focused on developing analytical thinking and programming foundations relevant to data science.
Web Developer
Marpa Infotech Pvt. Ltd.
Working on hosting infrastructure and CMS-based deployment systems using WHM and WHMCS. Involved in building and maintaining a web hosting service platform.
Full Stack Development Intern
Yuwasoft Technologies Pvt. Ltd.
Contributed to full-stack application development with focus on structured data handling, API integration, and backend logic. Worked with data flow between frontend and backend systems.
Epochs
My notes on the things I'm learning — reinforcement learning, the maths behind models, and more. Each epoch is one more pass of understanding.
Learning Pandas: Working with Tabular Data
My notes on pandas - the Series and DataFrame, how indexing really works, and the groupby split-apply-combine pattern that finally made data wrangling click.
Learning NumPy: Arrays and Vectorization
My notes on NumPy - the ndarray, why vectorization beats Python loops, and how broadcasting lets arrays of different shapes work together.
Learning PyTorch: Tensors, Autograd & the Training Loop
My notes on PyTorch - tensors as NumPy-with-gradients, how autograd builds the backward pass for you, and the five steps every training loop repeats.