# Neural Networks and Deep Learning (Course 1 of the Deep Learning Specialization)

Neural Networks and Deep Learning (Course 1 of the Deep Learning Specialization)

- Welcome (Deep Learning Specialization C1W1L01)
- What is a Neural Network? (C1W1L02)
- Supervised Learning with a Neural Network (C1W1L03)
- Why is deep learning taking off? (C1W1L04)
- About This Course (C1W1L05)
- Course Resources (C1W1L06)
- Binary Classification (C1W2L01)
- Logistic Regression (C1W2L02)
- Logistic Regression Cost Function (C1W2L03)
- Gradient Descent (C1W2L04)
- Derivatives (C1W2L05)
- More Derivative Examples (C1W2L06)
- Computation Graph (C1W2L07)
- Derivatives With Computation Graphs (C1W2L08)
- Logistic Regression Gradient Descent (C1W2L09)
- Gradient Descent on m Examples (C1W2L10)
- Vectorization (C1W2L11)
- More Vectorization Examples (C1W2L12)
- Vectorizing Logistic Regression (C1W2L13)
- Vectorizing Logistic Regression’s Gradient Computation (C1W2L14)
- Broadcasting in Python (C1W2L15)
- A Note on Python/Numpy Vectors (C1W2L16)
- Quick Tour of Jupyter/iPython Notebooks (C1W2L17)
- Explanation of Logistic Regression’s Cost Function (C1W2L18)
- Neural Network Overview (C1W3L01)
- Neural Network Representations (C1W3L02)
- Computing Neural Network Output (C1W3L03)
- Vectorizing Across Multiple Examples (C1W3L04)
- Explanation For Vectorized Implementation (C1W3L05)
- Activation Functions (C1W3L06)
- Why Non-linear Activation Functions (C1W3L07)
- Derivatives Of Activation Functions (C1W3L08)
- Gradient Descent For Neural Networks (C1W3L09)
- Backpropagation Intuition (C1W3L10)
- Random Initialization (C1W3L11)
- Deep L-Layer Neural Network (C1W4L01)
- Forward Propagation in a Deep Network (C1W4L02)
- Getting Matrix Dimensions Right (C1W4L03)
- Why Deep Representations? (C1W4L04)
- Building Blocks of a Deep Neural Network (C1W4L05)
- Forward and Backward Propagation (C1W4L06)
- Parameters vs Hyperparameters (C1W4L07)
- What does this have to do with the brain? (C1W4L08)

# Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization (Course 2 of the Deep Learning Specialization)

- Train/Dev/Test Sets (C2W1L01)
- Bias/Variance (C2W1L02)
- Basic Recipe for Machine Learning (C2W1L03)
- Regularization (C2W1L04)
- Why Regularization Reduces Overfitting (C2W1L05)
- Dropout Regularization (C2W1L06)
- Understanding Dropout (C2W1L07)
- Other Regularization Methods (C2W1L08)
- Normalizing Inputs (C2W1L09)
- Vanishing/Exploding Gradients (C2W1L10)
- Weight Initialization in a Deep Network (C2W1L11)
- Numerical Approximations of Gradients (C2W1L12)
- Gradient Checking (C2W1L13)
- Gradient Checking Implementation Notes (C2W1L14)
- Mini Batch Gradient Descent (C2W2L01)
- Understanding Mini-Batch Gradient Dexcent (C2W2L02)
- Exponentially Weighted Averages (C2W2L03)
- Understanding Exponentially Weighted Averages (C2W2L04)
- Bias Correction of Exponentially Weighted Averages (C2W2L05)
- Gradient Descent With Momentum (C2W2L06)
- RMSProp (C2W2L07)
- Adam Optimization Algorithm (C2W2L08)
- Learning Rate Decay (C2W2L09)
- Tuning Process (C2W3L01)
- Using an Appropriate Scale (C2W3L02)
- Hyperparameter Tuning in Practice (C2W3L03)
- Normalizing Activations in a Network (C2W3L04)
- Fitting Batch Norm Into Neural Networks (C2W3L05)
- Why Does Batch Norm Work? (C2W3L06)
- Batch Norm At Test Time (C2W3L07)
- Softmax Regression (C2W3L08)
- Training Softmax Classifier (C2W3L09)
- The Problem of Local Optima (C2W3L10)
- TensorFlow (C2W3L11)

# Structuring Machine Learning Projects (Course 3 of the Deep Learning Specialization)

Structuring Machine Learning Projects (Course 3 of the Deep Learning Specialization)

- Improving Model Performance (C3W1L01)
- Orthogonalization (C3W1L02 )
- Single Number Evaluation Metric (C3W1L03)
- Satisficing and Optimizing Metrics (C3W1L04)
- Train/Dev/Test Set Distributions (C3W1L05)
- Sizeof Dev and Test Sets (C3W1L06)
- When to Change Dev/Test Sets (C3W1L07)
- C3W1L08 WhyHumanLevelPerformance
- Avoidable Bias (C3W1L09)
- Understanding Human-Level Performance? (C3W1L10)
- Surpassing Human-Level Performance (C3W1L11)
- Improving Model Performance (C3W1L12)
- Carrying Out Error Analysis (C3W2L01)
- Cleaning Up Incorrectly Labelled Data (C3W2L02)
- Build First System Quickly, Then Iterate (C3W2L03)
- Training and Testing on Different Distributions (C3W2L04)
- Bias and Variance With Mismatched Data (C3W2L05)
- Addressing Data Mismatch (C3W2L06)
- Transfer Learning (C3W2L07)
- Multitask Learning (C3W2L08)
- What is end-to-end deep learning? (C3W2L09)
- Whether to Use End-To-End Deep Learning (C3W2L10)

# Convolutional Neural Networks (Course 4 of the Deep Learning Specialization)

Convolutional Neural Networks (Course 4 of the Deep Learning Specialization)

- C4W1L01 Computer Vision
- C4W1L02 Edge Detection Examples
- C4W1L03 More Edge Detection
- C4W1L04 Padding
- C4W1L05 Strided Convolutions
- C4W1L06 Convolutions Over Volumes
- C4W1L07 One Layer of a Convolutional Net
- C4W1L08 Simple Convolutional Network Example
- C4W1L09 Pooling Layers
- C4W1L10 CNN Example
- C4W1L11 Why Convolutions
- C4W2L01 Why look at case studies?
- C4W2L02 Classic Network
- C4W2L03 Resnets
- C4W2L04 Why ResNets Work
- C4W2L05 Network In Network
- C4W2L06 Inception Network Motivation
- C4W2L07 Inception Network
- C4W2L08 Using Open Source Implementation
- C4W2L09 Transfer Learning
- C4W2L10 Data Augmentation
- C4W2L11 State of Computer Vision
- C4W3L01 Object Localization
- C4W3L02 Landmark Detection
- C4W3L03 Object Detection
- C4W3L04 Convolutional Implementation Sliding Windows
- C4W3L06 Intersection Over Union
- C4W3L07 Nonmax Suppression
- C4W3L08 Anchor Boxes
- C4W3L09 YOLO Algorithm
- C4W3L10 Region Proposals
- C4W4L01 What is face recognition
- C4W4L02 One Shot Learning
- C4W4L03 Siamese Network
- C4W4L04 Triplet loss
- C4W4L05 Face Verification
- C4W4L06 What is neural style transfer?
- C4W4L07 What are deep CNs learning?
- C4W4L08 Cost Function
- C4W4L09 Content Cost Function
- C4W4L10 Style Cost Function
- C4W4L11 1D and 3D Generalizations

# Sequence Models (Course 5 of the Deep Learning Specialization)

Sequence Models (Course 5 of the Deep Learning Specialization)

- C5W3L01 Basic Models
- C5W3L02 Picking the most likely sentence
- C5W3L06 Bleu Score (Optional)
- C5W3L07 Attention Model Intuition
- C5W3L08 Attention Model
- C5W3L09 SpeechRecog