Georgia Tech OMSCS

I’m still getting back into the hang of writing for fun after the last few semesters at Georgia Tech wrung me dry with paper after paper painstakingly filled with Matplotlib charts and LaTeX. The first two semesters were more of a programmer’s dream of building FTP servers, implementing MapReduce with gRPC, diving deeply into architecture, and dipping my toe into artificial intelligence.

Once the rubber met the road and my brain turned toward the machine learning curriculum, all bets were off. ISYE 6420 (Bayesian Stats) served as a brutal reminder that my algebra and calculus were not up to snuff, requiring more than one weekend doing nothing but going through a Coursera course or two while making precious little progress against any homework. CS 6601 (Artificial Intelligence) provided some heady moments of implementing Tri A*-search and the Viterbi algorithm, but brought reality crashing down with a 50 page midterm and an equally long final. Meanwhile, CS 7641 (Machine Learning), pushed me further than I thought possible with 4 projects, each requiring a rather large program to support a paper of 10-15 pages. And I’m still not recovered from CS 6476 (Computer Vision).

Robotics: AI Techniques marked the beginning of my foray into Georgia Tech’s OMSCS machine learning and artificial intelligence offerings. As I mentioned in my review of High Performance Computer Architecture (HPCA), my other Georgia Tech courses have focused on computing systems. This was mostly a function of the popularity of the ML/AI courses making them difficult to register for, and the computing system courses being among the most well-regarded classes in the program. However, my chosen specialization for this degree is machine learning, and so this semester it was time to get going.

I chose this as my first AI-centric course as it’s relatively “easy” (I put this in quotes because easy is in the eye of the beholder) and was entirely project-based allowing me to level up on my Python while also giving me time to explore mathematical concepts that were completely new territory. As I’m taking CS6601 – Aritifical Intelligence in the fall, I wanted a course to provide exposure to the field of study without being overwhelming. I can say pretty definitively that this course did all of those things while being pretty fun at the same time.

For me, Georgia Tech’s OMSCS program’s biggest draw was it’s extensive machine learning and artificial intelligence curriculum. There are other online Master’s programs from well-regarded schools (University of Texas and University of Illinois immediately come to mind), but none as established as Georgia Tech and none with classes that felt worth the time and investment. However, through a quirk of scheduling (most of the ML/AI courses are in high demand and fill up quite quickly), three of my first four classes at GT have focused on computing systems.

Now, it would be unfair to blame this purely on scheduling. It would have been quite easy to take different courses from different specializations, but I got into this program to learn and to challenge myself, and the computing systems offerings come highly recommended from the community of OMSCS students and are known for their difficulty. High Performance Computer Architecture (HPCA) certainly belongs in that conversation, and like the other computing systems courses that I’ve taken so far (Graduate Introduction to Operating Systems and Advanced Operating Systems being the other two), I left the class with a far better grasp on and appreciation for the internals of computers.

If your vocation is one that manages computers, you’re in the business of bits. That is to say, you’re somehow responsible for the writing and/or reading of binary digits. Ones and zeros. Bits.

A bit is a fundamental unit for computers. One bit represents a binary logical state as it can be one of two values (again, 0 or 1). Alone, a bit doesn’t tell us much (the value of its information has been measured) but if you string them together magic happens. If you work with computers at a higher level, like writing a web-app in JavaScript or PHP, it’s easy to forget this although you’ll certainly encounter them from time to time. If you work with computers at an even higher level, like say just opening Excel from time to time, then you’re apt to think most of this is gibberish. However, at the lowest levels of software, it’s impossible to escape bits.

One of my favorite (personal) sayings about computers is that they are highly advanced guessing machines. You can see this play out practically with things like branch prediction, where a processor must guess the path of a logical branch based on the history of that branch. This heuristic is analogous to how many humans guess; we use history as a predictor for future events. While HPCA has many similar techniques, this scenario is even more common in the other Georgia Tech course that I’m taking this semester, Robotics: AI Techniques.

Artificial intelligence is the pinnacle of guessing as it employs practical techniques (like search algorithms) and combines them with statistical tricks based primarily on probability density (usually Gaussian) distributions. The mathematics behind these distributions, in my opinion, can often seek to confuse and distract from what is actually a delightfully simple concept.

In a course about high performance computer architecture, it’s no surprise that most of the time is spent discussing how to speed up computers using their architecture. It’s almost as though the name of the course tells you exactly what to expect.

This week in CS6290 at Georgia Tech, we’ve moved on to caches, which play a key role in speeding up the retrieval of information. The processor’s goal is crunching data which is held either in main memory (RAM) or on the disk (an SSD or HDD). To get that data, the processor issues requests for memory addresses and retrieves the data from the memory storage unit that holds that information.

This will probably be my last semester at Georgia Tech that includes a computing systems course (unless high performance computing becomes available again online). The rest of my coursework will be focused on my specialization – machine learning – and while I’m excited to focus more on the questions that brought me to this program, I will undoubtedly miss computing systems.

The beautiful part of this area of computer science is that it is where the rubber meets the road. Theory meets application and provides lessons to feed back into theory which then feeds into other applications.

My wife and I have a running joke in the house when either one of us moves something to its “correct” resting place, usually punctuated by breaking out into song.

Computer science is the practical application of many other sciences (solid state physics, calculus, linear algebra, information science, etc., etc., etc.), but it is at its most exacting and least forgiving the closer to the hardware you get. Here, everything truly does have its right place.

Every so often, a few posts come across my desk at the same time, and it reminds me of how at some basic level, all work is the same work, just manifested in different ways. Checklists and agendas, which are near and dear to my heart, are crucial for communicating and getting things done correctly across a team. They represent an agreement, a contract, reflections of expectations.

When you enter a meeting that has gone off the rails, it’s likely that either someone has torpedoed the agenda or one was never established. Likewise, any time I’ve needed to get a project back in a manageable state, a forced prioritized to-do list is my weapon of choice.

Similarly, sequential logical steps are the bread and butter of processors. Most of my high performance computing architecture course is focused on how processors squeeze every possible optimization out of a program’s instructions. There are dozens of ways that it does this (branch prediction, loop unfurling, data caches, etc), but perhaps most approachable is how a processor issues and executes instructions.

For my first semester at Georgia Tech, I wanted to take two courses that were well-reviewed, challenging, and introduced me to new concepts but that also played to my strengths. The first two months of the semester were bound to be hectic as I balanced gracefully leaving my full-time job of the past 6+ years with starting OMSCS. With that in mind, I ended up taking both of the operating systems courses GT offers online students.

Fortunately, there was only some overlap between the two courses and once I was a full time student my schedule made it easy to cram on the sort of “presumed knowledge” that Advanced Operating Systems (AOS) assumed was rattling around in my brain. There is also a “refresher” course that I would strongly recommend going through if you’re taking this course without GIOS. It’s possible to complete in a weekend and the first week of the course is a perfect time to cram this in. Going through this refresher and honing in on areas of weakness had the added bonus of forcing me to learn topics that pushed me ahead of the curve in a few areas in GIOS, but not so many to make that course redundant.

Similar to GIOS, the course professor (Umakishore Ramachandran) provided excellent lectures with a well-structured course, but was largely absent from managing the day-to-day of the class. While the TA’s in this course were less active than in GIOS, they still capably managed all forum questions and were readily available in Slack. There are four projects (one of which is essentially a warmup for the last project) and two tests. The projects are manageable if you have C/C++ skills, and I found the tests to be easier than those in GIOS (more memorization on these tests and less applied concepts).