Module 1: Architect
Module Overview
This module introduces the foundational concepts of neural networks and how to architect them using the Keras Sequential API. Neural networks are computational models inspired by the human brain, capable of learning complex patterns from data. You'll learn about the building blocks of neural networks, including neurons, layers, and activation functions, and how to combine these components to create effective architectures for various machine learning tasks.
Learning Objectives
- Describe foundational components of neural networks
- Introduce the Keras sequential model API
- Learn how to select a model architecture
Guided Project
Open DS_421_Architect_Lecture.ipynb in the GitHub repository to follow along with the guided project.
Module Assignment
Build a neural network to classify sketches from the Quickdraw dataset using TensorFlow and Keras. Compare performance between SGD and Adam optimizers and analyze training metrics.
Assignment Solution Video
Additional Resources
Neural Network Fundamentals
- 3Blue1Brown: But what is a Neural Network?
- TensorFlow Playground: Interactive Neural Network Visualization
- Neural Networks, Manifolds, and Topology
Keras and TensorFlow Implementation
- Keras: The Sequential Model Guide
- TensorFlow: Basic Classification Tutorial
- Keras Layers API Documentation