IBM AI Engineering Course Projects

Welcome to my repository of projects from the IBM AI Engineering course on Coursera! This repository contains all the Jupyter Notebook (.ipynb) files that I have developed throughout the course, covering a variety of topics in Artificial Intelligence and Machine Learning.

Table of Contents

1. Introduction
2. Technologies Used
   • Keras, TensorFlow, and PyTorch
   • RAG and LangChain
   • LLMs and NLP
   • Image Processing
3. Additional Topics
4. How to Use this Repository
5. Acknowledgments

Introduction

This repository showcases my journey through IBM's AI Engineering course, where I gained hands-on experience in various AI technologies and methodologies. Each Jupyter Notebook contains code snippets, explanations, and results for different projects that I've completed.

Technologies Used

Keras, TensorFlow, and PyTorch

• Keras: Implemented neural networks and built deep learning models using Keras, focusing on tasks like classification and regression.
• TensorFlow: Leveraged TensorFlow for model training, evaluation, and optimization, with a particular emphasis on creating custom layers and loss functions.
• PyTorch: Explored PyTorch for building dynamic computational graphs and performing advanced model training.

RAG and LangChain

• RAG (Retrieval-Augmented Generation): Applied RAG techniques to enhance the performance of generative models by incorporating external knowledge bases.
• LangChain: Utilized LangChain to build complex NLP workflows seamlessly, integrating various language models for enhanced natural language processing capabilities.

LLMs and NLP

• LLMs (Large Language Models): Gained practical experience in working with LLMs, understanding their architectures, and utilizing them for tasks like text generation and summarization.
• NLP (Natural Language Processing): Implemented various NLP techniques, including tokenization, sentiment analysis, and named entity recognition, using both traditional and deep learning methods.

Image Processing

• Explored image processing techniques using popular libraries like OpenCV and PIL, focusing on tasks such as image classification, object detection, and image augmentation.

Additional Topics

In addition to the core subjects, this course also covered:

• Model evaluation and selection techniques.
• Hyperparameter tuning and model optimization strategies.
• Deployment of machine learning models using tools like Flask and Docker.

Acknowledgments

Special thanks to IBM and Coursera for providing comprehensive courses on AI and Machine Learning. This repository would not have been possible without the knowledge gained from these resources.