Reader small image

You're reading from  Hands-On Mathematics for Deep Learning

Product typeBook
Published inJun 2020
Reading LevelIntermediate
PublisherPackt
ISBN-139781838647292
Edition1st Edition
Languages
Right arrow
Author (1)
Jay Dawani
Jay Dawani
author image
Jay Dawani

Jay Dawani is a former professional swimmer turned mathematician and computer scientist. He is also a Forbes 30 Under 30 Fellow. At present, he is the Director of Artificial Intelligence at Geometric Energy Corporation (NATO CAGE) and the CEO of Lemurian Labs - a startup he founded that is developing the next generation of autonomy, intelligent process automation, and driver intelligence. Previously he has also been the technology and R&D advisor to Spacebit Capital. He has spent the last three years researching at the frontiers of AI with a focus on reinforcement learning, open-ended learning, deep learning, quantum machine learning, human-machine interaction, multi-agent and complex systems, and artificial general intelligence.
Read more about Jay Dawani

Right arrow

Understanding optimization and it's different types

In optimization, our goal is to either minimize or maximize a function. For example, a business wants to minimize its costs while maximizing its profits or a shopper might want to get as much as possible while spending as little as possible. Therefore, the goal of optimization is to find the best case of , which is denoted by x* (where x is a set of points), that satisfies certain criteria. These criteria are, for our purposes, mathematical functions known as objective functions.

For example, let's suppose we have the equation. If we plot it, we get the following graph:

You will recall from Chapter 1, Vector Calculus, that we can find the gradient of a function by taking its derivative, equating it to 0, and solving for x. We can find the point(s) at which the function has a minimum or maximum, as follows:

After...

lock icon
The rest of the page is locked
Previous PageNext Page
You have been reading a chapter from
Hands-On Mathematics for Deep Learning
Published in: Jun 2020Publisher: PacktISBN-13: 9781838647292

Author (1)

author image
Jay Dawani

Jay Dawani is a former professional swimmer turned mathematician and computer scientist. He is also a Forbes 30 Under 30 Fellow. At present, he is the Director of Artificial Intelligence at Geometric Energy Corporation (NATO CAGE) and the CEO of Lemurian Labs - a startup he founded that is developing the next generation of autonomy, intelligent process automation, and driver intelligence. Previously he has also been the technology and R&D advisor to Spacebit Capital. He has spent the last three years researching at the frontiers of AI with a focus on reinforcement learning, open-ended learning, deep learning, quantum machine learning, human-machine interaction, multi-agent and complex systems, and artificial general intelligence.
Read more about Jay Dawani