Kalpesh Mulye's Projects
Code repository for supporting the paper "Atlas Few-shot Learning with Retrieval Augmented Language Models",(https//arxiv.org/abs/2208.03299)
An Academic project to apply knowledge of Feature engineering, Feature Selection, Data Cleaning and Detecting Outliers, Model Tuning & Confidence Interval Calculation.
Repository of all my work in ETL, Automation & Backup.
:mag: Haystack is an open source NLP framework that leverages Transformer models. It enables developers to implement production-ready neural search, question answering, semantic document search and summarization for a wide range of applications.
Image Captioning using RNN & Transformer: A Comparative Analysis
In this project Flikr8K dataset was used to train an Image Captioning model Using Hugging face Transformer.
An Information Retrival pipeline for searching relevant documents Using Customized Weighted TFIDF and Haystack Question Answering Model using Bert Base model integrated with Elastic Search for fast document retrival
Jeff Heaton's Kaggle Utilities
Moodle - the world's open source learning platform WITH HEROKU COMPATIBILITY off MOODLE_34_STABLE branch
The objective of this project is to build a text classification model that analyses the headlines of the news papers and classifies them as sarcastic or not. The model uses a complex deep learning model to build an embedding layer followed by a classification algorithm.
This was an academic project. The objective of the project is to learn how to implement a simple image classification pipeline based on the k-Nearest Neighbour and a deep neural network.
The objective of this project is to build a face recognition system, which includes building a face detector to locate the position of a face in an image and a face identification model to recognize whose face it is by matching it to the existing database of faces.
This project involved building recommendation systems for Amazon products. A popularity-based model and a collaborative Filtering model were used and evaluated to recommend top-10 products for a user.
In this capstone project, we will build a classifier that can by analysing text in the incidents and classify incidents to right functional groups can help organizations to reduce the resolving time of the issue.
Build a unique model to extract comments from images and classify them on the basis of excessive content
This Code will help you give different weights to the words in important sections of the documents like Title, Index or any other part of the document.