A machine learning model for generating song lyrics using advanced neural network techniques. This model leverages Bi-directional LSTM to create coherent and creative lyrics in various styles.

Repo for Implementing Research Papers & Projects related to Machine Learning

Master thesis project - a hybrid Neural Network-Decision Tree system and dataset for classical music form recognition and analysis.

Enhancing Explainability in Fake News Detection uses SHAP and BiLSTM models to improve the transparency and interpretability of detecting fake news, providing insights into the model's decision-making process.

Engineered an advanced deep learning model to automate the classification of financial documents, including Balance Sheets, Cash Flow and Income Statements using Bidirectional LSTM and TensorFlow. The model achieved an impressive accuracy of 96.2%, enhancing efficiency and reducing errors in document management for the finance and banking sectors.

Extracting Actionable Insights from User Feedback

Bidirectional RNNs are used to analyze the sentiment (positive, negative, neutral) of movie reviews. .

ToxiDetect is an AI-powered model for detecting toxic comments using deep learning. It classifies comments into various toxicity categories and features a Gradio web app for real-time scoring.

Predict emotions (happiness, anger, sadness) from WhatsApp chat data using machine learning and deep learning models. Includes text normalization, vectorization (TF-IDF, BoW, Word2Vec, GloVe), and model evaluation.

🗨️ This repository contains a collection of notebooks and resources for various NLP tasks using different architectures and frameworks.

This project conducts a thorough analysis of weather time series data using diverse statistical and deep learning models. Each model was rigorously applied to the same weather time series data to assess and compare their forecasting accuracy. Detailed results and analyses are provided to delineate the strengths and weaknesses of each approach.

The repository focuses on developing a comprehensive business opportunity analysis system that uses geospatial data, sentiment analysis, and topic modeling. The objective is to leverage these techniques to identify and evaluate potential business opportunities in area of interest.

The repository focuses on developing a comprehensive business opportunity analysis system that uses geospatial data, sentiment analysis, and topic modeling. The objective is to leverage these techniques to identify and evaluate potential business opportunities in area of interest.

A bangla chatbot using bidirectional lstm

The Sea Ice Extent of 5 Arctic and Antarctic regions is forecasted using CNN+LSTM, Bidirectional LSTM and Standalone LSTM.

This project employs a deep neural network architecture for the classification of toxic comments, utilizing the Kaggle competition dataset from the Jigsaw Toxic Comment Classification Challenge.

Sentiment analysis on IMDB movie reviews using Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) cells for binary classification of positive and negative sentiments.

The primary objective of this project is to develop a robust system capable of accurately classifying patient conditions solely based on their reviews. By leveraging advanced NLP techniques, the project aims to streamline the categorization process and provide valuable insights into patient health status.

Repo containing Channel Quality Indicator (CQI) data from real car routes in Greece. It contains a reproducable notebook with the implementation of a Bidirectional LSTM Neural Network for real-time CQI forecasting in heterogeneous ultra-dense beyond-5G networks.