Foundations of Deep Learning in Python
Go to main | Course Page
Section 1: Preliminaries
- Scaling the Data
- Getting Matrix Dimensions Right
- Loss Functions for Regression
- Loss Functions for Classification
- Overall Flow of Model Training
Section 2: Setup Environment and Import Data (Code Demo)
- Import Data
- Conduct Train-Test Split
- Reshape Data for Neural Network
Section 3: Logistic Regression as a 1-Layer Neural Network (Code Demo)
- Introduction
- Step 1: Initializing Parameters
- Steps 2.1 & 2.2: Forward and Backward Propagation
- Step 2.3: Update Parameters
- Step 3: Combine into optimize() function
- Step 4: Computing Predictions
- Apply to Dataset
- Analyze Effects of Learning Rates for a Neural Network
Section 4: 2-Layer Neural Network (Code Demo)
- Introduction
- Step 1: Initializing Parameters
- Step 2.1: Forward Propagation
- Step 2.2: Backward Propagation
- Step 2.3: Update Parameters
- Step 3: Combine into optimize() function
- Step 4: Computing Predictions
- Apply to Dataset
- Analyze Effects of Learning Rates for a Neural Network
Section 5: L-Layer Neural Network (Code Demo)
- Getting Matrix Dimensions Right
- Introduction
- Step 2.1: Forward Propagation
- Step 2.2: Backward Propagation and rest of the steps
- Step 2.3: Update Parameters
- Step 3: Combine into optimize() function
- Step 4: Computing Predictions
- Apply to Dataset
- Analyze Effects of Learning Rates for a Neural Network