Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Machine Learning for Finance

You're reading from   Machine Learning for Finance Principles and practice for financial insiders

Arrow left icon
Product type Paperback
Published in May 2019
Publisher Packt
ISBN-13 9781789136364
Length 456 pages
Edition 1st Edition
Languages
Arrow right icon
Authors (2):
Arrow left icon
Jannes Klaas Jannes Klaas
Author Profile Icon Jannes Klaas
Jannes Klaas
James Le James Le
Author Profile Icon James Le
James Le
Arrow right icon
View More author details
Toc

Table of Contents (15) Chapters Close

Machine Learning for Finance
Contributors
Preface
Other Books You May Enjoy
1. Neural Networks and Gradient-Based Optimization 2. Applying Machine Learning to Structured Data FREE CHAPTER 3. Utilizing Computer Vision 4. Understanding Time Series 5. Parsing Textual Data with Natural Language Processing 6. Using Generative Models 7. Reinforcement Learning for Financial Markets 8. Privacy, Debugging, and Launching Your Products 9. Fighting Bias 10. Bayesian Inference and Probabilistic Programming Index

More bells and whistles for our neural network


Let's take a minute to look at some of the other elements of our neural network.

Momentum

In previous chapters we've explained gradient descent in terms of someone trying to find the way down a mountain by just following the slope of the floor. Momentum can be explained with an analogy to physics, where a ball is rolling down the same hill. A small bump in the hill would not make the ball roll in a completely different direction. The ball already has some momentum, meaning that its movement gets influenced by its previous movement.

Instead of directly updating the model parameters with their gradient, we update them with the exponentially weighted moving average. We update our parameter with an outlier gradient, then we take the moving average, which will smoothen out outliers and capture the general direction of the gradient, as we can see in the following diagram:

How momentum smoothens gradient updates

The exponentially weighted moving average...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $19.99/month. Cancel anytime
Banner background image