Stanford CS224W: Machine Learning with Graphs - Stanford CS224W: Machine Learning with Graphs | 2021 | Lecture 6.2 - Basics of Deep Learning

4.0 (2)

29 learners

What you'll learn

This course includes

22.3 hours of video
Certificate of completion
Access on mobile and TV

Summary

Keywords

Jure Leskovec Machine Learning Machine Learning with Graphs Graphs CS224W Stanford Basics of Deep Learning Deep Learning graph neural networks objective function gradient descent non-linearity

Full Transcript

For more information about Stanford’s Artificial Intelligence professional and graduate programs, visit: https://stanford.io/3Cim9k7 Jure Leskovec Computer Science, PhD In this lecture, we give a review of deep learning concepts and techniques that are essential for understanding graph neural networks. Starting from formulating machine learning as optimization problems, we introduce the concepts of objective function, gradient descent, non-linearity and back propagation. To follow along with the course schedule and syllabus, visit: http://web.stanford.edu/class/cs224w/

Continue this lesson in the app

Install CourseHive on Android or iOS to keep learning while you move.

Welcome