Have Fun with Machine Learning: A Guide for Beginners
A hands-on beginner's guide that walks programmers with no AI background through training a convolutional neural network to classify dolphin and seahorse images using Caffe and DIGITS.
Have Fun with Machine Learning is a hands-on guide to machine learning for programmers with no background in AI, written from the point of view of a practitioner rather than from first principles. Its running example trains a program to predict, from images alone, whether an image shows a dolphin or a seahorse it has never seen before, using a convolutional neural network.
It walks through setting up and using existing open-source machine learning tools, specifically Caffe and DIGITS, creating a dataset of images, training a neural network from scratch, testing it on unseen images, improving its accuracy by fine-tuning existing networks such as AlexNet and GoogLeNet, and deploying the finished network. It does not cover how neural networks are designed and does not use mathematical notation, and it is available in the original English as well as Traditional Chinese and Korean translations.