This page requires that JavaScript be enabled in your browser.
Learn how »
Machine Learning: Current and Future
Etienne Bernard
As part of the Wolfram Language, we developed efficient yet user-friendly machine learning tools aimed for use at both beginners and experts in the field. These tools include a neural network framework, a repository of pretrained networks and fully automated machine learning functions. In this talk, Etienne Bernard gives an overview of these tools, presents the novelties since Version 12 and discusses our current and future projects in this area.
Thanks for your feedback.
Channels: Technology Conference
1311 videos match your search.
|
Eric Mjolsness Collaborative projects have resulted in several Mathematica-implemented modeling languages aimed at general-purpose biological modeling, which is a useful and topical but an indefinitely expandable goal. We update previous work on ... |
|
Jae Bum Jung/Yan Zhuang |
|
Phillip Todd |
|
Василий Сороко |
|
Phil Ramsden |
|
Lou D'Andria Constructing interfaces with Dynamic, DynamicModule and Manipulate is nothing new, but those aren't the only Dynamic primitives available in Mathematica. In this talk, we'll identify and demonstrate some of the ... |
|
Галина Михалкина, Григорий Фридман |
|
Галина Михалкина |
|
Андрей Кротких |
|
Антон Екименко, Кирилл Белов |
|
Физический институт имени П.Н. Лебедева |
|
Григорий Фридман, Олег Иванов |
|
Галина Михалкина |
|
Олег Кофнов |
|
Николай Сосновский |
|
Микаэл Эгибян |
|
Микаэл Эгибян |
|
Леонид Шифрин |
|
Вахагн Геворгян |
|
Алексей Семенов |