Handwriting Recognition with Neural Networks

Create a Handwriting Recognition AI with TensorFlow


Product Description

This title is part of the Python Mini-Degree – 12 Courses to Learn and Master Python

In this course we’ll use the Machine Intelligence library TensorFlow to build an application that can detect handwritten numbers. The approach we’ll take is to train a neural network with thousands of photos of handwritten numbers, so that it can learn the right patterns and be able to recognize numbers on it’s own. As we train our neural network, we’ll reach a recognition accuracy of over 90%.

We’ll cover neural networks from scratch, starting with modeling a single neuron using the Perceptron model, which is similar to real neuron cells in the brain. We’ll move on from that to cover systems of multiple neurons and cover the Gradient Descent and Backpropagation techniques to train our networks.

To implement our handwritting recognition neural network we’ll be using the popular TensorFlow framework created by Google. We’ll visualize the training using TensorBoard.

About the Python Mini-Degree

The Python Mini-Degree is a bundle of 12 online video courses, that go all the way from teaching you how to code in Python while making a game, to building your own Artificial Intelligence (AI) and Internet of Things (IoT) applications using Computer Vision, Machine Learning and Deep Learning.

Learn more and enroll HERE.


Course Requirements

This course builds up on the concepts covered in our course Build Sarah - An Image Classification AI.

You need to have Python 2.7 installed.

It is recommended to take this course as part of the Python Mini-Degree, which includes 12 courses on Python, Computer Vision, Machine Learning, Deep Learning and much more.