Foundations of Deep Learning in Python

Go to main | Course Page

Section 1: Preliminaries

  1. Scaling the Data
  2. Getting Matrix Dimensions Right
  3. Loss Functions for Regression
  4. Loss Functions for Classification
  5. Overall Flow of Model Training

Section 2: Setup Environment and Import Data (Code Demo)

  1. Import Data
  2. Conduct Train-Test Split
  3. Reshape Data for Neural Network

Section 3: Logistic Regression as a 1-Layer Neural Network (Code Demo)

  1. Introduction
  2. Step 1: Initializing Parameters
  3. Steps 2.1 & 2.2: Forward and Backward Propagation
  4. Step 2.3: Update Parameters
  5. Step 3: Combine into optimize() function
  6. Step 4: Computing Predictions
  7. Apply to Dataset
  8. Analyze Effects of Learning Rates for a Neural Network

Section 4: 2-Layer Neural Network (Code Demo)

  1. Introduction
  2. Step 1: Initializing Parameters
  3. Step 2.1: Forward Propagation
  4. Step 2.2: Backward Propagation
  5. Step 2.3: Update Parameters
  6. Step 3: Combine into optimize() function
  7. Step 4: Computing Predictions
  8. Apply to Dataset
  9. Analyze Effects of Learning Rates for a Neural Network

Section 5: L-Layer Neural Network (Code Demo)

  1. Getting Matrix Dimensions Right
  2. Introduction
  3. Step 2.1: Forward Propagation
  4. Step 2.2: Backward Propagation and rest of the steps
  5. Step 2.3: Update Parameters
  6. Step 3: Combine into optimize() function
  7. Step 4: Computing Predictions
  8. Apply to Dataset
  9. Analyze Effects of Learning Rates for a Neural Network
Report abuse