Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

CodeSignal

The MLP Architecture: Activations & Initialization

via CodeSignal

Go to class Write review

Overview

This course builds upon single layers to construct a complete Multi-Layer Perceptron (MLP). You'll learn to stack layers, explore different activation functions like ReLU and Softmax, and understand the importance of weight initialization for effective training.

Syllabus

  • Unit 1: Stacking Layers: Building a Multi-Layer Perceptron (MLP)
    • Passing Data Through the MLP
    • Aligning Layers in Your Neural Network
    • Build Your Own MLP Class
    • Deepening Your Neural Network Design
    • Build a Complete Neural Network
  • Unit 2: The ReLU Activation Function: Powering Modern Neural Networks
    • Debugging the ReLU Activation Function
    • Adding ReLU Power to DenseLayer
    • Build the ReLU Activation Function
  • Unit 3: Output Layer Activations: Softmax and Linear
    • Making Softmax Work for Any Input
    • Verifying Softmax Output Validity
    • Build the Linear Activation Function
    • Matching Activations to Layers
    • Comparing Classification and Regression Outputs
  • Unit 4: Weight Initialization Strategies
    • Random Weight Initialization in Action
    • Fixing Uniform Initialization for Layers
    • Mastering Xavier Initialization
    • He Uniform Initialization in Practice

Reviews

Start your review of The MLP Architecture: Activations & Initialization

Go to class

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.