Six lines of code is all it takes to write your first Machine Learning program. In the first few episodes of the series, we'll teach you how to get started with Machine Learning from scratch. To do that, we'll work with two open source libraries, scikit-learn and TensorFlow. We'll see scikit in action in a minute. But first, let's talk quickly about what Machine Learning is and why it's important.
Artificial intelligence (AI) is the science of programming computers to perceive their environment and make rational, cognitive decisions in order to achieve a goal. It is one of the most rapidly progressing and sought after technologies in the world. It is, however, a rather general term. When most people talk about artificial intelligence, they are usually talking about machine learning. At its most basic definition, machine learning is a method of teaching computers to make predictions based on data.
This program is a super simple one that classifies/predicts the type of fruit from two given features. This example uses apples and oranges. After being given some features, the program learns, and whenever we give it totally separate features, it will predict the type of the fruit. Since this is a basic program, it only needs one library, and that is sci-kit learn. You need to install sci-kit learn on your current computer using Pip install scikitlearn in the command prompt or in your Anaconda virtual env.
This article aims to provide the basic knowledge of how to recognize snacks by using Python and SimpleCV. Readers will gain practical programming knowledge via experimentation with the Python scripts included in the Snack Classifier open source project. To illustrate with a snacks recognition app, the Snack Watcher watches any snacks present on the snack table. For Snack Watcher to determine if there was an interesting event, it needs to process the image into a set of image "Blobs". For each "Blob", Snack Watcher compares the "Blob" with it's previous state to determine if the "Blob" was added, removed or stationary.