Introduction to TensorFlow Programming Framework

This assignment introduces TensorFlow as a programming framework for building and training simple machine learning models.
It is part of Week 3 (Course 2: Improving Deep Neural Networks – Hyperparameter Tuning, Regularization, and Optimization) from the Deep Learning Specialization by Andrew Ng on Coursera.

Description

In this lab, I explored the basic concepts of TensorFlow 1.x, focusing on creating and manipulating tensors, using placeholders and sessions, and building simple computation graphs.
This assignment lays the foundation for using TensorFlow in more complex deep learning tasks later.

Key Concepts Covered:

• Tensors and TensorFlow operations
• Creating computation graphs
• Placeholders and feeding data dynamically
• Running sessions to evaluate operations
• Building a simple logistic regression model using TensorFlow
• Understanding variables, constants, and optimizers

Files Included

• tensorflow_introduction_lab.ipynb: Jupyter notebook introducing basic TensorFlow operations and model training
• tensorflow_utils.py: Helper functions for initializing variables and plotting
• data/: Contains datasets used for logistic regression examples

⚠️ This repository contains only my own implementation and strictly follows Coursera’s Honor Code.

Tools Used

• Python 3
• TensorFlow 1.x
• NumPy
• Jupyter Notebook

Course Info

This assignment is part of:

Deep Learning Specialization
Instructor: Andrew Ng
Course 2: Improving Deep Neural Networks
Week 3: Introduction to TensorFlow Programming Framework

License

This repository is intended for educational and portfolio purposes only. Please do not use it for direct assignment submission on Coursera.

---

Star this repository if you're excited about building deep learning models using TensorFlow!