Rutuja Shinde's repositories
AI-Self-learning-Chatbot
A neural network-based AI chatbot has been designed that uses LSTM as its training model for both encoding and decoding. The chatbot works like an open domain chatbot that can answer day-to-day questions involved in human conversations. Words embeddings are the most important part of designing a neural network-based chatbot. Glove Word Embedding and Skip-Gram models have been used for this task.
Default-Credit-Data-Analysis-and-Prediction-Using-Big-Data
Credit defaulting results in a large profit loss to banks and other credit lenders. The success of the banking industry results in the ability to understand risk. This project uses big data technologies like Mapreduce, HDFS along with PySpark and AWS for analysis of credit history and its prediction
Natural-Language-Processing
This repository contains various small Natural Language Processing based projects including text summarization using Spacy and N-grams, along with word predictions.
Deep-Fake-Image-Classification-using-Deep-Convolutional-GAN
As the crime rates have increased due to fake images and videos, it has become the need of the hour today to build technologies that could identify these threats and protect us from any potential scams. This project aims to implement a DCGAN (Deep Convolutional Generative Adversarial Network) to generate "fake" images based on an existing dataset. The generated images can then be used to build a classifier that can identify an image as real vs fake. GANs like a DCGAN have been used widely to create Deep Fakes. The aim is to use DCGAN to build high-quality deep fakes.
Python_public
Public repository for all python code
Visceral-Fat-and-Lung-Cancer
This project is a result of the requirements by Allwyn Corporation. It is an image processing and deep-learning based project focused on healthcare data . The project aims to perform image processing on CT Scans images of L3 slice and extract the various fats areas using Deep Learning to calculate the Visceral Fat Index.