Grok University

Grok University

Come learn about AI and machine learning from industry data scientists and practitioners. To sign up, please contact the Grok team.

Machine Learning Virtual Classes

Grok offers introductory, hands-on classes to better understand machine learning, data mining and statistical pattern recognition.

In these classes, we will discuss effective machine learning techniques, provide practical examples and most importantly, apply the content in a practice environment. Our classes are free and fully-guided by a live instructor.

Please contact us for the latest class schedules

Intro to Hierarchical Clustering for Event Data

Intro to Hierarchical
Clustering for Event Data

Clustering is an unsupervised machine learning technique used to identify similar entries for grouping purposes. It is broadly used in many applications for pattern recognition and information retrieval. Data stream clustering is attracting more attention as the number of relevant applications is rapidly increasing. Examples include, but are not limited to phone records, financial transactions, social streams, and equipment maintenance. In this course, we will present the most common clustering types, then demonstrate how Grok uses hierarchical clustering to group event data in Python.

Watch Video

Send video link to:

Semantic Clustering Log Data in Python

Clustering is an unsupervised machine learning technique used to identify similar entries for grouping purposes. It is broadly used in many applications such as pattern recognition and information retrieval. Semantic clustering involves extracting numerical data from semantic data, such as that produced by system log files. In this course, we will provide an overview of semantic embedding, then demonstrate how Grok uses classical clustering techniques. The sample dataset will be provided and analyzed using the developed clustering method in the lecture

Semantic Clustering Log data in Python

Training a Classification Model

Classification is a supervised, machine learning technique that involves training a predictive model on examples with labels. In this course, we explore how anomaly data (from operational metrics) can be labeled such that a classifier recognizes evolving incidents as they unfold. The sample dataset will be provided and analyzed using the developed classification method in the lecture.