Skip to Content
Hands-On Machine Learning for Algorithmic Trading
book

Hands-On Machine Learning for Algorithmic Trading

by Stefan Jansen
December 2018
Beginner to intermediate
684 pages
21h 9m
English
Packt Publishing
Content preview from Hands-On Machine Learning for Algorithmic Trading

LeNet5 – the first modern CNN (1998)

Yann LeCun, now the Director of AI Research at Facebook, was a leading pioneer in CNN development. In 1998, after several iterations starting in the 1980s, LeNet5 became the first modern CNN used in real-world applications, which introduced several architectural elements still relevant today.

LeNet5 was published in a very instructive paper, Gradient-Based Learning Applied to Document Recognition (co-authored by Yoshua Bengio and others: http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf), that laid out many of the central concepts. Most importantly, it promoted the insight that convolutions with learnable filters are effective at extracting related features at multiple locations with few parameters. ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Start your free trial

You might also like

Machine Learning for Algorithmic Trading - Second Edition

Machine Learning for Algorithmic Trading - Second Edition

Stefan Jansen

Publisher Resources

ISBN: 9781789346411Supplemental Content