Popular GitHub Repositories for Datacleaning

Worked on a dataset of high entropy alloys which is used to design materials for additive manufacturing. Being responsible for Performing Data Analysis and constructing Machine learning algorithms, including neural networks, Gradient boosting for carrying predictions useful for advanced material invention.

distill large scale web page text

Machine translation refers to translating phrases across languages using deep learning and specifically with RNN (Recurrent Neural Nets). Most of these are complex system that is they are combined system of various algorithms. But, at its core, NMT uses sequence-to-sequence ( seq2seq ) RNN cells. Such models could be character level but word level models remain common. ??????

A method for multi-step content filtering for real-time retrieval enhancement, which involves pseudo-answer generation based on large language models and document reordering

Data Preprocessing, Data Cleaning, Fine-tuning the Hyperparameters,

Building a decoder-only (GPT-style) LLM from scratch using PyTorch and training it for text generation.

This repository showcases a Convolutional Neural Network (CNN) module developed on Jupyter and an AutoML module implemented on Google Cloud Platform (GCP) through VertexAI

my graduation project in Epsilon AI Institute (kaggle competition)

Repository for Raspberry Pi-based object detection with TinyML models like TensorFlow Lite, PyTorch Nano, including data gathering, mAP evaluation, and image data preparation in Jupyter notebooks.

In this project we will practice some machine learning workflow to predict a car's market price using its attributes.