It would be cool for you to learn Machine Learning.

I got into machine learning because I am also obsessed with how humans learn. I didn’t get very good grades when I was in middle school, so, since then, I’ve been reading books on learning psychology in order to learn techniques as well as honing those techniques while I’m working on problems or reading. But more practically machine learning is a way for software to adopt intuition that was only previously available to humans and that practicality is what drives me to learn more about it every day. Before, we would have to hard code all the details about a problem for a program to be able to employ a task. For example, if you wanted to program a computer to be able to detect someone’s mood based on facial expressions, you wouldn’t be able to. There are too many details about our face and so it would take too long to code up the algorithms to analyze all the intricacies that make up a facial expression.

a

Yet, why approach it that way when that is not how we learn? Aside from school, we learn by experiences, which we store as intuitive knowledge. If I were to ask you to describe to me in words what a curious facial expression looks like you would have a very difficult time talking about each and every ridge and crevice of the face. But, it’s very easy for you to show me how it looks like or show me a person who is curious. This way is much easier and relies on forming an intuition based on multiple examples. We don’t have to read countless textbooks on facial expressions and facial muscles in order to learn how people feel based on their facial expressions. We simply see the expression enough times to know what it means. This is the kind of learning power that software now has through machine learning. The future is about to be crazy.

a

There is already so much that machine learning can do for us but in the future this will become even more prevalent in our lives. Based on data about our behaviors, software becomes intuitive and is able to guess what we like and don’t like so it can give recommendations. As each one of us produces more data, the number of types of recommendations and the quality of recommendations is going to skyrocket. Imagine a world in which your refrigerator suggests a food based on your mood as determined by your facial expressions detected through a camera in you house, or even recommends food based on information on your current workout routine. Imagine your fridge being programmed to restrict certain foods based on learned health data and what it knows about your current health state. More controversially, imagine a world in which there is no financial crash because all the world’s financial institutions can predict them with ease.

a

How do you get into this exciting field? Well, Machine learning sort of works like a black box in which you put a piece of data into the black box like an image of a face, and the black box outputs a label for that piece of data such as “happy”. For this reason, in machine learning jargon that black box is called a classifier because it classifies a piece of unknown data sort of like a person sorting a bunch of unlabeled face into male or female. As you learn more you can determine the best type of “black box” to use based on the problem or go even deeper and develop your own new algorithm. So, as someone passionate about machine learning, you can either work on creating new machine learning algorithms or you can use algorithms that already exist in order to solve real world problems. Unlike in other fields though, the line between these two is blurred but still generally separated by a graduate degree. In my next post I describe the specific skills to learn it and how you can get involved today.

Advertisements

Questions are the Most Undervalued Note Taking Technique

I think that the advice I give here can also be used for other subjects but I want to focus on my experience with technical subjects because I study Computer Science. Here I’m going to explain to you why I find it efficient to go through multiple versions of notes and why my first version of notes is literally only questions.
a
To cite two eminent writers/researchers on learning and skill acquisition, Anders Ericsson argues that deliberate practice is what leads to expert performance and Cal Newport says that our most significant work is produced in a state of Deep Work.
a
To tie these two together, I believe deliberate practice is both what puts you into a state of deep work and is also what you are doing when you are in deep work. Sounds confusing, but let me explain what I mean by that. The only way to focus deeply is to be fully engaged with what you are doing but into order to be engaged you have to do something that gets you engaged. Once you are doing that you maintain the same level of engagement throughout that session. Methods of becoming engaged are referred to as orienting tasks and questions are my favorite type of orienting task.
a
This leads to my note taking method. I believe that note taking itself is Deep Work and thus should be approached in a deliberate practice manner. I see it as more of a way to organize and absorb information than as a way to keep track of what the professor or book said about a topic. The best way to activate this state while note taking is to write down any question that pops into your mind. As you go through, anytime you feel stuck or confused, that’s a question. Even if the question doesn’t immediately pop into your head it is still a question. If it’s not obvious what the question is, put in deliberate effort to figure out what it is.  Formulate what you don’t know into a question and move on.   If you remember anything from today, it should be that questions are the biggest source of focus while taking notes.
a
The Cornell style of taking notes is awesome but I prefer something more dynamic. Through a lot of trial and error I’ve learned that the more complicated the subject is the more questions are going help your first version of notes. Thus for the first version of a complex subject, don’t worry if you just write a ton of questions. My first version of notes is mostly questions which is a little hard to believe, but it helps me target what I don’t know and think deeply about it.
a
Now, comes your second version of notes. This time there will most likely be much fewer questions because you’ve already written most of them down. The goal of these notes is to use the space on the paper to tackle the questions in the previous set of notes. For this you have a toolset of learning techniques including breaking the equation into smaller parts, looking up other resources and even asking questions. In future posts I’m going to explain in greater detail some specific learning techniques for figuring out answers to the questions you’ve posed.
a
Writing down questions keeps you engaged throughout your initial session of absorbing the knowledge as well as helping you keep track of what you don’t know so that you can specifically tackle those concepts after your initial scan of the material. I also see questions as a sort of guide for what you don’t know so that you are never sitting still wondering what you don’t know or what you should study next. Just look at what questions you have and you’ll know what you need to figure out.