Welcome to my collection of machine learning projects! These repositories showcase a range of machine learning and deep learning techniques applied to solve real-world problems, visualize data, and create robust models. Each project is detailed below with its purpose and relevant technologies.
A dynamic visualizer for understanding how neural networks operate, with an implementation to predict handwritten digits using a trained model. The project combines visualization techniques with interactive tools to demystify neural network layers.
Developed for NASA's Space Apps Hackathon 2020, this project explores innovative solutions to COVID-19-related challenges, leveraging machine learning models and data analytics for meaningful insights.
A deep learning-based approach to analyze sentiment in text data, classifying emotions as positive, negative, or neutral. Techniques include LSTM and GRU models for improved sentiment prediction accuracy.
This project focuses on detecting emotions such as happiness, anger, and sadness in text using advanced deep learning architectures. Practical applications include chatbots and customer feedback analysis.
A robust deep learning pipeline for classifying user intent from text inputs. This project is ideal for enhancing conversational AI systems by improving intent detection and response accuracy.
An implementation of Named Entity Recognition (NER) models to extract entities like names, locations, and organizations from text. The project demonstrates how deep learning can streamline NER tasks for NLP applications.
A user-friendly web application built with Streamlit to demonstrate various machine learning models in action. It provides an intuitive interface for model selection, predictions, and performance visualization.
A regression-based model predicting taxi fares in New York City using datasets with geospatial and temporal features. This project showcases data preprocessing, feature engineering, and model optimization techniques.
Coursework assignments from the "Neural Networks and Deep Learning" specialization on Coursera. These assignments provide hands-on implementation of neural network concepts, including forward and backward propagation.
Feel free to explore the repositories and gain insights into the methodologies and technologies used. Contributions, feedback, and discussions are always welcome!