In this codelab, you will learn how to build and train a neural network that recognises handwritten digits. Along the way, as you enhance your neural network to achieve 99% accuracy, you will also discover the tools of the trade that deep learning professionals use to train their models efficiently.
This codelab uses the MNIST dataset, a collection of 60,000 labeled digits that has kept generations of PhDs busy for almost two decades. You will solve the problem with less than 100 lines of Python / TensorFlow code.
What you'll learn
- What is a neural network and how to train it
- How to build a basic 1-layer neural network using tf.keras
- How to add more layers
- How to set up a learning rate schedule
- How to build convolutional neural networks
- How to use regularisation techniques: dropout, batch normalization
- What is overfitting
What you'll need
Just a browser. This workshop can be run entirely with Google Colaboratory.
CGG / GDG London
A Self-taught Machine Learning Engineer passionate about helping and teaching junior developers getting a great start in their careers. With over 4 years of experience designing, developing, and deploying state-of-the-art solutions to real world applications. With a highly diverse educational background and cultural experiences, excels at connecting with audiences of different knowledge sets
Jana is a recent MSc in Software Design and Development NUI Galway graduate, having previously studied law there. This has led her to a machine learning intern position at Genesys, where she is learning both about the trade and what Diversity, Equity and Inclusion mean. She likes languages, including NLP, and talking about cats and running.
Data enthusiast | #Techlover | Geek | Traveler | Foodie | Vegan | Fitness freak | GDG Dublin | WTM Dublin | WWC Dublin
PM / GDG Organizer
Senior Architect / GDG Organizer
Second Year Electronic Engineering student
Pursuing Bachelors in Electronic Engineering