Overview
This course explores the limitations and challenges of using Machine Learning (ML) in production engineering. It addresses common proposed uses of ML in this field and explains why they are often not feasible. The course also discusses approaches to evaluating the feasibility of ML applications and emphasizes that while ML can solve some problems, it is not a universal solution. The intended audience for this course includes professionals in the field of production engineering, particularly those interested in applying ML technologies. The course covers topics such as the differences between Machine Learning and Artificial Intelligence, the shortcomings of using ML for ticket categorization and root cause analysis, and the impact of confirmation bias in ML applications.
Syllabus
Intro
Agenda
Who am I
Machine Learning vs AI
Machine Learning Primer
Deep Learning vs ML
What is ML for
Why ML is bad
Ticket categorizing
Single ticket queue
Single ticket algorithm
Whats wrong with this
Automatic Root Cause Analysis
Outages
Statistical Correlation
Low Uncertainty
Deep Learning
Confirmation Bias
Plausible Use
Prework
ontology epistemology metaphysics
QA
Taught by
USENIX