Even the most amazing programmers may not have the first clue about math. That makes learning neural networks particularly inaccessible, as an integral part of explaining it relies on mathematical formulas. Ah, the formulas…with all their lines and curves and ancient symbols; they’re just as unintelligible as they are beautiful.
What’s a better way for us to learn it instead? With a language we all speak: code.
Ellen Körbes dives into every component required to write a neural network from scratch, like network structure, activation functions, forward propagation, gradient descent, and backpropagation. But you’ll look at them as a programmer: defining what you’re trying to achieve, then writing an implementation for it. And you’ll do it using only Go code—no specialized libraries like TensorFlow and PyTorch required. So if you ever wanted to really understand how a neural network works but thought it to be out of your reach because of the math, this is for you. Code, not math. Algorithms, not logarithms.
Ellen Körbes works with developer relations at Garden. They code, write, speak, teach Go, make videos, and dabble with Kubernetes. A native of Brazil, they’re deeply involved with diversity and inclusiveness in tech.
©2019, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • firstname.lastname@example.org