Artificial Intelligence Foundations: Neural Networks

Introduction

• Neural networks 101: Your path to AI brilliance
• What you should know

1. What Are Neural Networks?

• Neural networks: The building blocks of generative AI
• Machine learning and neural networks
• Neural network fundamentals
• The need for multilayer networks

2. Key Components in Neural Network Architecture

• Layers: Input, hidden, and output
• Transfer and activation functions
• How neural networks learn

3. Other Types of Neural Networks

• Convolutional neural networks (CNN)
• Transformer architecture: The model that redefined modern AI
• Why we need more than CNNs
• Self-attention in vision transformers

4. Build a Simple Neural Network Using Keras

• The Keras Sequential model
• Use case and determine evaluation metric
• Data checks and data preparation
• Data preprocessing
• Train the neural network using Keras
• How to use the challenge exercise files
• Challenge: Build a neural network
• Solution: Build a neural network

5. Best Practices for Optimizing a Neural Network

• Overfitting and underfitting: Two common ANN problems
• Hyperparameters and neural networks
• How do you improve model performance?
• Regularization techniques to improve overfitting models
• Challenge: Manually tune hyperparameters
• Solution: Manually tune hyperparameters

Conclusion

• Next steps