Programming Machine Learning: From Coding to Deep Learning
You've decided to tackle machine learning - because you're jobhunting, embarking on a new project, or just think self-drivingcars are cool. But where to start? It's easy to be intimidated,even as a software developer. The good news is that it doesn't haveto be that hard. Master machine learning by writing code one lineat a time, from simple learning programs all the way to a true deeplearning system. Tackle the hard topics by breaking them down sothey're easier to understand, and build your confidence by gettingyour hands dirty.Peel away the obscurities of machine learning, starting fromscratch and going all the way to deep learning. Machine learningcan be intimidating, with its reliance on math and algorithms thatmost programmers don't encounter in their regular work. Take ahands-on approach, writing the Python code yourself, without anylibraries to obscure what's really going on. Iterate on yourdesign, and add layers of complexity as you go.Build an image recognition application from scratch withsupervised learning. Predict the future with linear regression.Dive into gradient descent, a fundamental algorithm that drivesmost of machine learning. Create perceptrons to classify data.Build neural networks to tackle more complex and sophisticated datasets. Train and refine those networks with backpropagation andbatching. Layer the neural networks, eliminate overfitting, and addconvolution to transform your neural network into a true deeplearning system.Start from the beginning and code your way to machine learningmastery.What You Need:The examples in this book are written in Python, but don't worryif you don't know this language: you'll pick up all the Python youneed very quickly. Apart from that, you'll only need your computer,and your code-adept brain.