[GAME REVIEW] while True: learn() - it talks all about machine learning, big data and AI.
Hey guys, this is Vivy here, thank you so much for stopping by my channel. Today I'm gonna introduce an educational puzzle game called while true: learn. The name already looks very geek, through this game, you will learn about the history of machine learning, big data, AI, and… some very fundamental programming knowledge and logic.
The features in the game are cats, modules, programming, machine learning, AI..They combine together in a very smart and interesting way. Today, let’s see how professional we can be after playing this game. So the game starts from, the player wants to understand what his cat is speaking.
Then he went on the website to ask, and some guru told him some information and passed on some work. And the game starts from here. To understand the cats, you will need to be able to recognize the cat's shape, learn their facial expressions, get more cats involved so you will have more samples… just like what we do nowadays to do machine learning things.
And basically it is talking about the fundamentals of machine learning, then neural networks, big data and lastly AI, it talks about the history of the whole thing as early as 1935, when everything started, to the AI as the current date. Yeah, this game is serious, not joking around.
Some information it provides are very basic but I never heard of them before. Very interesting to know that. Each level is a job that is referred from someone. You can tell those jobs are fake, since the names, logic are made up, and there are some puns, some silly stories, mocking like rescue from the mars, helping the FBI, delivery company, tarari.
Different things… but in some way, they also look realistic, you can see some ideas through them, and you can tell it could totally happen in the real world. Except for the jobs, you can use your knowledge to invest in a startup, build the algorithm and let it run automatically, then just get money day by day..
Well there is a chance that you will get bankrupt if you don’t manage it well. So here is how to play. In each level, you will need to assemble the modules, to sort and filter the data on the left, which has three colors and three shapes, according to the output requirements on the right side.
The modules are different algorithms, the game will introduce the modules as the story moves on. It coversthe very early and basic one, the decision tree, then the regression tree, then to MARK II, then to neutral networks, deep learning, then to the AI.
Basically I guess every essential one for machine learning. And they offer related articles and videos for you to explore on your own. When I was playing, I partly feel it’s very gamey, like those puzzle, logic games. But when I got stuck sometimes, and I went to search for some related knowledge about the algorithms, and tried them in the game, it’s a little difficult to relate the game with real algorithms, but somehow it worked.
Here is an example using some “geek” language. What I learn from searching is that the algorithm module decision tree, which is the most basic one we use most in the game, in the real world it will do a yes or no decision. But in the game it doesn’t work like that.
The color decision tree, if you choose to separate red and blue, the red output will get red and green, the blue output will get blue and green, it’s not a yes or no answer. So it’s a little tricky to relate the real with the game. And the final output always requires different colors and shapes, it’s not a simple yes or no situation.
But in someway, it made me feel very realistic, because in the real world, we don’t always need a yes or no, either this or that result, the programmers just need to find a way to apply the simple yes or no decision tree to achieve the needs, to get the more complicated various results.
Another realistic thing in the game is, you need to beat the time and use modules within a limit to get the gold medal. I feel that I did need to observe the original data set, and calculate the processing time, and after some searchings I will consider the GINI to calculate the efficiency, and try to optimize the process.
I was arranging the modules, and did testing all the time, just like what a programmer will do in the real life. It’s tricky to apply the knowledge from the real world in the game, since it looks so different, but surprisingly I got it worked.
I hope it’s not just because I’m lucky. I hope it’s because I understood how the developers set the mechanism. And…. another another realistic thing is, the money in the game, you can use it to upgrade hardwares, to improve the data processing speed, increase the capacity, and so.
Which is just like what we do in the real world. They have puns everywhere. For some early levels, sometimes you just can’t beat the time, after upgrading the equipment, you just run the program again, and you could get the gold medal easily.
And the balancer in the game could separate the data, which is like the server in real world, that you need to rent. Ennn, you could also buy some decos that do nothing but entertainment and increase your happiness. Another thing that impressed me a lot in the game is, it made me think about reality.
Sometimes you don’t need to get a high accuracy, or you need to get everything correct. I will consider the samples needed, and processing time, and server rental fee, that eventually i might decide to abandon some data. Such as the candy factory, if it’s in the real world, abandon the data, means throw away the candys, that means waste.
But by abandoning some candies it will increase the speed and get a higher accuracy. So, I’m thinking, maybe this is where the waste and processing fee come from. A better algorithm or equipment might be able to help with it. Technology changes life.
If you only play the game, it is a short game. It took me about a week or so to finish, since I played and learned from other sources at the same time. I felt I’m part of this field after playing this game. For sure I can’t become a machine learning guru after playing the game, but this high tech thing doesn’t look that far away to approach. It’s a very nice tool to help you step into this field, and it not only just bring you there, it also leads you to some deeper learnings, by offering many resources.
And this is super helpful and thoughtful. So if you would like, you could directly step forward after this game. this game is on most main platforms, I bought the iPad version, which i don’t recommend. I have some troubles dragging and selecting.
I assume the switch version might have similar issues. So get a steam version to play on PC on Mac if you could. The prices are different, ipad version is 5 dollars, and switch and steam version is 13 dollars. Maybe there will be some more functions and content? I really love the concept of the game, it’s for adults, but still using a format as a game, to turn the boring learning to some interesting knowledge.
The mechanism is rather addictive and the dialogs and puns always made me laugh. It is not as hard as a hardcore game. it’s helpful for those who want to start learning about machine learning, since it has so many related links. to those who just want to generally know about machine learning, the game does contain enough information.
I hope there will be more games like these, that will make you learn while playing, that will make people think. I will keep trying to find these kinds of games and introduce them to you. If you have some recommendations, please comment below, share with me and other audiences.