Coursera - Neural Networks and Deep Learning - Week 3 - Section 1 - Shallow Neural Networks
2025年01月15日
What is a Neural Network?

Neural Network Representation

Neural Network Representation


Neural Network Representation learning

Vectorizing across multiple examples


Justification for vectorized implementation

Recap of vectorizing across multiple examples

Activation functions

Pros and cons of activation functions

Activation function

Sigmoid activation function

Tanh activation function

ReLU and Leaky ReLU

Gradient descent for neural networks

Formulas for computing derivatives

Computing gradients

Neural network gradients

Summary of gradient descent



What happens if you initialize weights to zero?

Random initialization

Week 3: Shallow Neural Networks
Section 1: Shallow Neural Network
1. Video: Neural Networks Overview
What is a Neural Network?

2. Video: Neural Network Representation
Neural Network Representation

3. Video: Computing a Neural Network's Output
Neural Network Representation


Neural Network Representation learning

4. Video: Vectorizing Across Multiple Examples
Vectorizing across multiple examples


5. Video: Explanation for Vectorized Implementation
Justification for vectorized implementation

Recap of vectorizing across multiple examples

6. Video: Activation Functions
Activation functions

Pros and cons of activation functions

7. Video: Why do you need Non-Linear Activation Functions?
Activation function

8. Video: Derivatives of Activation Functions
Sigmoid activation function

Tanh activation function

ReLU and Leaky ReLU

9. Video: Gradient Descent for Neural Networks
Gradient descent for neural networks

Formulas for computing derivatives

10. Video: Backpropagation Intuition (Optional)
Computing gradients

Neural network gradients

Summary of gradient descent



11. Video: Random Initialization
What happens if you initialize weights to zero?

Random initialization
