Debargho Basak's Projects
Small notebook with code to scrape Disney movie data from Wikipedia and save in different formats (JSON, CSV, Pickle (Binary))
This is a german text corpus from Wikipedia. It is cleaned, preprocessed and sentence splitted. It's purpose is to train NLP embeddings like fastText or ELMo Deep contextualized word representations.
Sign up page for my newsletter
The personal website/portfolio template by Hashir Shoaib. Built using React and Bootstrap.
Pawan Kumar Portfolio
This is an image classifier using a convolutional neural network (using keras library, tensorflow backend) in which the dependent variable is binary (can be explained by two classes)
Training/Implementing a BERT model from scratch on the works of my favorite philosopher Immanuel Kant
Udemy Angela Yu Web Dev Bootcamp -Simon Game Challenge
Keras documentation, hosted live at keras.io
LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation
Solutions and learning resources for popular Leetcode problems.
LLM-based Conversational Recommendation System
š§® A collection of resources to learn mathematics for machine learning
Supervised Learning task to perform 3D object segmentation of organs
This repository is an unoffical PyTorch implementation of Medical segmentation in 2D and 3D.
https://huyenchip.com/ml-interviews-book/
Multi^2OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT (Findings of ACL: EMNLP 2020)
Creating a recommender system that will recommend new musical artists to a user based on their listening history. Suggesting different songs or musical artists to a user is important to many music streaming services, such as Pandora and Spotify. In addition, this type of recommender system could also be used as a means of suggesting TV shows or movies to a user (e.g., Netflix).
Sign up page for my newsletter