AI Workshop: Build a Neural Network with PyTorch Lightning

Course details

In this interactive workshop, Janani Ravi—a certified Google cloud architect and data engineer—explores the fundamentals of building neural networks using PyTorch and PyTorch Lightning. Learn the basics of neural networks and setting up your virtual environment. Find out how to load and preprocess data, creating simple yet powerful neural networks to tackle regression tasks. Step through the conversion of PyTorch code to PyTorch Lightning and encapsulate data and models with LightningDataModule and LightningModule. Discover how to use PyTorch Lightning Trainer to streamline the training process and evaluate models efficiently. Explore building classification models to further hone your skills in data preparation, model creation, and performance evaluation. When you complete this course, you will be well-equipped to construct and deploy efficient neural network models, adding significant value to your AI projects.

Concepts

0. Introduction

01 - AI workshop build a neural network with PyTorch Lightning
02 - Prerequisites
03 - Quick overview of neural networks

1. Building a Neural Network with PyTorch

04 - Setting up the virtual environment
05 - Loading and exploring regression data
06 - Preprocessing data for training
07 - Creating a simple neural network
08 - Setting up the Dataset and DataLoader
09 - Training a neural network using PyTorch
10 - Visualizing losses and evaluating models

2. Using PyTorch Lightning to Build a Regression Model

11 - Prompt engineering to convert PyTorch to PyTorch Lightning
12 - Encapsulating data using a LightningDataModule
13 - Encapsulating a model using a LightningModule
14 - Training the model using the PyTorch Lightning Trainer

3. Using PyTorch Lightning to Build a Classification Model

15 - Loading and exploring classification data
16 - Creating a LightningDataModule
17 - Creating a LightningModule
18 - Training a classification model and evaluating metrics

Conclusion

19 - Summary and next steps