DeepLearning.AI - Deep Learning Specialization

This repository contains my personal solutions and learning progress for the Deep Learning Specialization on Coursera, taught by Andrew Ng and offered by DeepLearning.AI and Stanford University.

---

📚 Course Breakdown

---

📘 1. Neural Networks and Deep Learning

In the first course of the Deep Learning Specialization, you will study the foundational concept of neural networks and deep learning.

You will:

• Understand the significant technological trends driving the rise of deep learning
• Build, train, and apply fully connected deep neural networks
• Implement efficient (vectorized) neural networks
• Identify key parameters in a neural network’s architecture
• Apply deep learning to your own applications

---

📘 2. Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

In the second course, you will open the deep learning black box to understand the processes that drive performance and generate good results systematically.

You will:

• Learn best practices for building deep learning applications
• Use techniques like L2 and dropout regularization, hyperparameter tuning, batch normalization, and gradient checking
• Apply optimization algorithms like mini-batch gradient descent, Momentum, RMSprop, and Adam
• Implement neural networks using TensorFlow

---

📘 3. Structuring Machine Learning Projects

This course teaches you how to build and lead successful ML projects, making strategic decisions based on real-world experience.

You will:

• Diagnose and prioritize errors in ML systems
• Understand complex ML settings like mismatched training/test sets and surpassing human-level performance
• Apply end-to-end learning, transfer learning, and multi-task learning

---

📘 4. Convolutional Neural Networks

You will understand the evolution and application of computer vision techniques using convolutional neural networks (CNNs).

You will:

• Build CNNs, including architectures like ResNets
• Apply CNNs to visual recognition and detection tasks
• Use neural style transfer for artistic image generation

---

📘 5. Sequence Models

This course explores sequence models and their applications in NLP, speech, and more.

You will:

• Build RNNs, GRUs, and LSTMs
• Perform character-level language modeling
• Use word embeddings and HuggingFace transformers
• Apply sequence models to NLP tasks like NER and Question Answering

⚠️ Note: I completed this course before the major content update in Course 5 Week 4, so I did not study Transformers in-depth at that time. However, the overall course content remains excellent and highly recommended.

---

📝 Disclaimer

This repository is intended for educational purposes and personal reference only. Please do not copy and submit these solutions as your own.

---

📜 License

This project is licensed under the MIT License.

---

🔗 Enroll in the Course