I am Ravjot Singh, a data science enthusiast with a strong passion for ML, DL, NLP, and GenAI. Currently pursuing my Master of Science in Data Analytics at San Jose State University, I am eager to contribute to innovative projects and push the boundaries of what's possible with data science and AI.
Feel free to explore the repositories, use the code, and get in touch if you have any questions or collaborations in mind. Happy coding!
E-Mail: [email protected]
This repository is a comprehensive collection of my work and explorations in the fields of Machine Learning (ML), Deep Learning (DL), Natural Language Processing (NLP), and Generative AI (GenAI). Here, you will find a mix of conceptual explanations and practical projects that demonstrate the application of various algorithms and techniques.
Concepts: Detailed overviews of generative models including GANs, VAEs, and transformer-based architectures like GPT and BERT.
Projects: Exciting projects involving text generation, image synthesis, and prompt engineering. Includes my Flask-based text generator using Google Generative AI and the Google Gemini model.
Concepts: Detailed explanations of core ML concepts including regression, classification, clustering, and ensemble methods.
Projects: Hands-on projects showcasing the implementation of ML models on real-world datasets. Example projects include customer segmentation, predictive modeling, and recommendation systems.
Concepts: In-depth discussions on neural networks, convolutional neural networks (CNNs), recurrent neural networks (RNNs), and other advanced DL architectures.
Projects: Practical projects demonstrating the use of DL for image recognition, natural language understanding, and more. Highlights include projects on image classification, object detection, and sentiment analysis.
Concepts: Comprehensive guides to NLP techniques including tokenization, stemming, lemmatization, named entity recognition, and more.
Projects: Real-world applications of NLP such as text classification, language translation, and question-answering systems.
Concepts: Detailed coverage of financial concepts such as portfolio optimization, risk management, and quantitative analysis.
Concepts: In-depth exploration of time series analysis with python.
Concepts: In-depth coverage of data cleaning, transformation, and analysis techniques using Python libraries like Pandas and NumPy.
Projects: Practical projects on exploratory data analysis (EDA), feature engineering, and statistical analysis.
Concepts: Comprehensive guides to data visualization techniques using tools like Matplotlib, Seaborn, Plotly, and Tableau.
Projects: Projects demonstrating the visualization of complex datasets, creating interactive dashboards, and storytelling with data.
Concepts: Detailed explanations of image processing techniques including filtering, edge detection, and morphological operations.
Projects: Projects demonstrating image enhancement, restoration, and segmentation using libraries like OpenCV.
Concepts: Comprehensive guides to computer vision techniques such as object detection, image classification, and image generation.
Projects: Real-world applications in areas like facial recognition.
Concepts: In-depth exploration of web scraping techniques using libraries like BeautifulSoup and Selenium.
Projects: Practical projects on extracting data from websites.