Knowledge of calculus is not required to get results and solve problems in machine learning or deep learning. However, knowing some calculus will help you in a number of ways, such as in reading mathematical notation in books and papers, and in understanding the terms used to describe fitting models like "gradient," and in understanding the learning dynamics of models fit via optimization such as neural networks. Calculus is a challenging topic as taught at a university level, but you don't need to know all of calculus, just a handful of terms and methods related to numerical function optimization, central to fitting algorithms like neural networks. And the best way to get a handle on calculus is from books. In this tutorial, you will discover books on calculus for machine learning.

Isaac Newton (left) and Gottfried Wilhelm Leibniz each independently invented calculus.Credit: Left, DeAgostini/Getty; Right, Lombard/ullstein bild via Getty Midway through Infinite Powers, Steven Strogatz writes that Isaac Newton and Gottfried Wilhelm Leibniz both "died in excruciating pain while suffering from calculi -- a bladder stone for Newton, a kidney stone for Leibniz". It was a cruelly ironic end for the scientists who independently invented calculus: the word comes from the Latin for'small stone', in reference to pebbles once used for counting. Such fascinating anecdotes abound in Infinite Powers. Strogatz, a mathematician working in nonlinear dynamics and complex systems, has written a romp through the history of calculus -- the study of how things change. Starting with the ancient Greeks, the book ends with connections between the field and artificial intelligence and machine learning. Calculus was key to working with Newton's laws of motion, which stimulated the Industrial Revolution.