Coursera — Deep Learning Specialization

My coursework and programming assignments from Andrew Ng's Deep Learning Specialization on Coursera, offered by DeepLearning.AI. Notebooks are in Python using NumPy and TensorFlow/Keras.

Courses

Folder	Course	Topics covered
C1	Neural Networks and Deep Learning	Logistic regression from scratch, shallow and deep neural networks, forward/backward propagation, vectorization
C2	Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization	L2 regularization, dropout, gradient checking, mini-batch gradient descent, momentum, RMSprop, Adam, learning rate decay, batch normalization, hyperparameter search
C3	Structuring Machine Learning Projects	Train/dev/test splits, bias-variance tradeoff, error analysis, data augmentation, transfer learning, multi-task learning, end-to-end deep learning (quiz-based, no code assignments)
C4	Convolutional Neural Networks	CNN fundamentals, ResNets, Inception, object detection (YOLO), face recognition, neural style transfer
C5	Sequence Models	RNNs, GRUs, LSTMs, word embeddings, attention mechanism, transformers, speech recognition, trigger word detection

C4 and C5 are not yet uploaded.

Language

All assignments are Python in Jupyter Notebooks.

Structure

Each course folder contains one subfolder per week, with the programming assignments for that week.

Coursera-Deep-Learning-Specialization/
├── C1 Neural Networks and Deep Learning/
│   ├── Week 2/
│   ├── Week 3/
│   └── Week 4/
├── C2 Improving Deep Neural Networks.../
│   ├── Week 1/
│   ├── Week 2/
│   └── Week 3/
└── C3 Structuring Machine Learning Projects/
    └── (quiz-based, no notebooks)

Notes

This repo is for personal reference and learning. Assignment solutions are my own work completed during the course.