The Open Source Society University offers a complete education in computer science using online materials.
According to their GitHub page, the curriculum is suited for people with the discipline, will, and good habits to obtain this education largely on their own, but who’d still like support from a worldwide community of fellow learners.
Intro CS: for students to try out CS and see if it’s right for them
Core CS: corresponds roughly to the first three years of a computer science curriculum, taking classes that all majors would be required to take
Advanced CS: corresponds roughly to the final year of a computer science curriculum, taking electives according to the student’s interests
Final Project: a project for students to validate, consolidate, and display their knowledge, to be evaluated by their peers worldwide
Pro CS: graduate-level specializations students can elect to take after completing the above curriculum if they want to maximize their chances of getting a good job
It is possible to finish Core CS within about 2 years if you plan carefully and devote roughly 18-22 hours/week to your studies. Courses in Core CS should be taken linearly if possible, but since a perfectly linear progression is rarely possible, each class’s prerequisites are specified so that you can design a logical but non-linear progression based on the class schedules and your own life plans.
Over the last months I’ve been working my way through Project Euler in my spare time. I wanted to learn Python programming, and what better way than solving mini-problems and -projects?!
Well, Project Euler got a ton of these, listed in increasing order of difficulty. It starts out simple: to solve the first problem you need to write a program to identify multiples of 3 and 5. Next, in problem two, you are asked to sum the first thousand even Fibonacci numbers. Each problem, the task at hand gets slighly more difficult…
For me, Project Euler combines math, programming, and stats in a way that really keeps me motivated to continue and learn new concepts and programming / problem-solving approaches.
However, at problem 31, I really got stuck. For several hours, I struggled to solve it in a satisfactory fashion, even though most other problems only take 5-90 minutes.
After hours of struggling, I pretty much gave up, and googled some potential solutions. Aparently, the way to solve problem 31, is to take a so-called dynamic programming approach.
Dynamic programming is both a mathematical optimization method and a computer programming method. The method was developed by Richard Bellman in the 1950s and has found applications in numerous fields, from aerospace engineering to economics. In both contexts it refers to simplifying a complicated problem by breaking it down into simpler sub-problems in a recursive manner. While some decision problems cannot be taken apart this way, decisions that span several points in time do often break apart recursively. Likewise, in computer science, if a problem can be solved optimally by breaking it into sub-problems and then recursively finding the optimal solutions to the sub-problems, then it is said to have optimal substructure.
Katie Jolly wanted to surprise a friend with a nice geeky gift: a custom-made map cutout. Using R and some visual finetuning in Inkscape, she was able to made the below.
A detailed write-up of how Katie got to this product is posted here.
Basically, the R’s tigris package included all data on roads, and the ArcGIS Open Data Hub provided the neighborhood boundaries. Fortunately, the sf package is great for transforming and manipulating geospatial data, and includes some functions to retrieve a subset of roads based on their distance to a centroid. With this subset, Katie could then build these wonderful plots in no time with ggplot2.
The website PapersWithCode.com lists all scientific publications of which the codes are open-sourced on GitHub. Moreover, you can sort these papers by the stars they accumulated on Github over the past days.
Papers with Code allows you to quickly browse state-of-the-art research on GANs and the code behind them, for instance. Alternatively, you can browse for research and code on sentiment analysis or LSTMs.
In optimizing their transportation services, Uber uses evolutionary strategies and genetic algorithms to train deep neural networks through reinforcement learning. A lot of difficult words in one sentence; you can imagine the complexity of the process.
Because it is particularly difficult to observe the underlying dynamics of this learning process in neural network optimization, Uber built VINE – a Visual Inspector for NeuroEvolution. VINE helps to discover how evolutionary strategies and genetic optimizing are performing under the hood. In a recent article, they demonstrate how VINE works on the MujocoHumanoid Locomotion task.
[…] In the Humanoid Locomotion Task, each pseudo-offspring neural network controls the movement of a robot, and earns a score, called its fitness, based on how well it walks. [Evolutionary principles] construct the next parent by aggregating the parameters of pseudo-offspring based on these fitness scores […]. The cycle then repeats.