This page is the entry point for machine learning in the Engineering Math section. It does not derive any algorithm. Instead, it collects lectures and talks that explain what machine learning is and how its main methods work. Machine learning is built on the math covered elsewhere in this section. Matrices hold the data and the model weights. Derivatives drive the training, because gradient descent moves each weight against the slope of the error. Probability describes how certain a prediction is. So it helps to keep those pages at hand while you watch the videos below.
Video Digest
The links in the table below are grouped by format. The two groups for short clips and for talks are still empty placeholders. The lecture group holds three talks, by Andrew Ng, Demis Hassabis and Geoffrey Hinton. The last group holds three MIT OpenCourseWare lectures on machine learning, clustering and classification. Every link opens YouTube in a new tab.
Basic Introduction/Short Clips : In these video, you would have the introductions to Machine Learning in many different ways from many different persons. |
|
|
|
|
Talks/Discussion on Machine Learning |
|
|
|
|
|
Forum/Presentation/Lecture on Machine Learning |
|
|
Algorithm/Machine Learning for Machine Learning |
|