Curriculum on Ryan Orban

OSSU Data Science Curriculum

me@ryanorban.com (Ryan Orban) — Fri, 08 Jan 2021 00:00:00 +0000

Summary

Open Source Society University (OSSU) Data Science is a structured, free curriculum for self-taught data science, organized to approximate the depth of a university degree without the cost. It sequences coursework from mathematical prerequisites (linear algebra, calculus, statistics, probability) through programming foundations (Python, SQL) to core machine learning and domain specializations. Each section links to specific courses — primarily from Coursera, edX, and free university course sites.

A Practical Intro to Data Science — Zipfian Academy

me@ryanorban.com (Ryan Orban) — Fri, 14 Mar 2014 00:00:00 +0000

Summary

This Zipfian Academy post became a reference document in the early data science community — widely cited as one of the most honest, practical articulations of what the job actually requires. Where most data science writing in 2014 was either too high-level (data science is about insight!) or too tool-specific, this post tried to map the actual SKILL set: what you need to know, what tools you need to use, and why.

Metacademy — Bayesian Machine Learning Roadmap

me@ryanorban.com (Ryan Orban) — Mon, 16 Dec 2013 00:00:00 +0000

Summary

Roger Grosse’s Bayesian machine learning roadmap on Metacademy is a curated learning path through the full stack of Bayesian inference techniques used in modern ML. Unlike a textbook or course, it structures the curriculum as a dependency graph — each topic lists what you need to know first and links to the best resources for learning it.

Self-Study Guide to Machine Learning

me@ryanorban.com (Ryan Orban) — Mon, 16 Dec 2013 00:00:00 +0000

Summary

Jason Brownlee’s Machine Learning Mastery site published this structured self-study guide for practitioners wanting to learn machine learning without a formal academic path. Brownlee’s approach was deliberately top-down: don’t start with theory and work toward applications, start with working code and a running model, then fill in theory as needed.

Metacademy

me@ryanorban.com (Ryan Orban) — Fri, 13 Dec 2013 00:00:00 +0000

Summary

Metacademy is a knowledge graph for machine learning and probabilistic artificial intelligence. Each concept is a node with explicitly listed prerequisites — you can navigate to any topic (say, Variational Inference) and see the minimum prerequisite knowledge tree you need to understand it first. The site then surfaces specific resources (papers, textbook chapters, lectures) for learning each node.

What Every Computer Science Major Should Know

me@ryanorban.com (Ryan Orban) — Fri, 19 Jul 2013 00:00:00 +0000

Summary

Matt Might (then a professor at the University of Utah) wrote this canonical essay as a guide to the breadth and depth a CS graduate should have. It covers a remarkable range: from Unix proficiency and the command line to formal languages and automata theory, from data structures and algorithms to systems programming, operating systems, networks, security, and software engineering practice. The essay’s tone is prescriptive but pragmatic — these aren’t theoretical ideals, they’re the things that separate a practitioner who can reason about hard problems from one who can only apply known patterns.