This course focuses on transforming your code into a reusable Python library and applying it to a real-world problem. You'll refactor your existing components into a structured package, build a `Model` class for easier network definition and training, and finally, train your neural network on the California Housing dataset for a regression task.
Overview
Syllabus
- Unit 1: Building a Neural Network Library
- Complete Namespace Declarations in Main Library Header
- Creating the Main Library Header Interface
- Unit 2: Modular Training Components
- Define the XOR Dataset for Neural Network Training
- Implementing the Complete Training Loop with Modular Components
- Implementing Post-Training Evaluation for XOR Neural Network
- Unit 3: Model Orchestration in C++
- Implementing Model Constructor and Compile Method for Neural Network Orchestration
- Implementing Abstract Methods for Model Interface
- Implementing the Complete Neural Network Training Loop
- Implementing the SequentialModel Class
- Orchestrating Your Neural Network with the SequentialModel API
- Unit 4: Preparing Real World Data
- Loading and Preparing Housing Dataset for Neural Network Training
- Implementing Data Splitting for Housing Dataset Preprocessing
- Implementing Feature Scaling for Housing Dataset Preprocessing
- Unit 5: California Housing Regression
- Fixing Neural Network Architecture for California Housing Price Prediction
- Building Your First Neural Network for Housing Price Prediction
- Training Your Neural Network on California Housing Data