The Fundamentals of Machine Learning

In this event I'll present the the basics of Machine Learning, what is a training dataset, what is a testing dataset, what is a cluster, a classifier, and a model. We'll also discuss feature recognition in images and videos, and image processing generally. Finally, we'll apply these concepts to real world datasets from the UCI and MNIST, providing real world examples of data, image, video, and time-series classification.

For many people this will be review, but I will also supplement the discussion with mathematical theorems that prove the algorithms we'll make use of have high accuracy for real world datasets. These results can be found in my paper, Analyzing Dataset Consistency.

I'll also discuss some of the limitations of machine learning and A.I. generally, again using mathematical theorems. We'll then discuss, in light of these results, whether generative A.I. is simply plagiarism, at least when using unlicensed underlying content.