Machine Learning - MRI Analysis Project (Part II)

*This is a second part of an introductory post on machine learning. It is based on a practical project I worked on at ETH. Here I give you an explanation of two crucial steps in machine learning pipeline – Model selection and Validation. I then wrap up with some useful takeaways from the project, that you can eventually use in your own work and concise summary. If you missed the first part of the post, or just feel you could use a refresher, you can find it here.* Model Selection Although we have discussed quite few steps so far, they were only preparatory (albeit necessary and crucial) and it is only now, in model selection phase, that we actually get our hands on machine learning algorithms. We can further divide this phase into two steps – training and validation. Let’s look at training first. In the scope of our project we needed to deal with both regression and classification, here I will describe the latter one as it is perhaps more intuitive and again, I will illustrate it on an example from our project. Recalling the task at hand – to disambiguate between mentally healthy and sick patients from an MRI scan, we can imagine a simplified scenario where each brain scan is described by single two-dimensional vector of features. Further, assume that they form two point-clouds that are perfectly linearly separable as show in the figure: Fig. 5: Idealized example of classification task Fig. 6: More realistic example of a classification task, notice that data don't form any recognizable sub-groups We may than write down an equation of line that divides the two-dimensional space into two half-planes. Whenever we make a new observation (take an MRI of a new patient), his brain, described by two feature vector, will fall to one of those two regions and we will label it accordingly as ‘healthy’ or ‘sick’. ...

2017-06-05 · (34.95%) · Martin Holub

Projects, Cows and Apéros. What Was the Semester at ETH Like?

Hello everybody, after more than a two-months break I am getting back to you with already fourth blog post. Do you know what this means? Don’t worry it doesn’t mean that I decided to bore you with a post of several times the normal length (although, truth be told, this one is bit meatier than the usual fare), rather it means that my exam period is over. It is exactly at this time that I want to share with you a concise summary of what a semester at ETH is like. A summary enriched by my personal impressions and experiences. And if you are not a student anymore, don’t worry, on top of offering you a view on Swiss education and ETH, I will give you a sneak-peak into what the Swiss are like and how does this play out in one’s day-to-day life. ...

2017-02-25 · (34.55%) · Martin Holub

One Tip on How to Become More Satisfied With Your Studies

We are nearing the end of November. For most of us this means that the Christmas mood is slowly finding way into our minds. And if you are so lucky to orient yourself still mainly by academic calendar, this also means that you are well into the second half of your autumn semester. The initial enthusiasm may be well extinguished by the sheer amount of workload. Things that were supposed to be fun are becoming an annoying routine and you are starting to wonder if you are interested in what you are supposed to learn in the first place. ...

2016-11-24 · (34.17%) · Martin Holub

ETHWeek - Challenging Water

How did you start your day this morning? First, I hope that well. Second, I guess that you did at least one of these: made yourself a coffee, brushed your teeth or took a shower. And to assume this, I don’t have to be particularly good in guessing. This is how millions of people start their day. But these activities have more in common. All of them would be either significantly different or even impossible without water running out of our taps. Luckily, clean drinking water is an infinite resource. Or isn’t it? ...

2016-10-22 · (34.04%) · Martin Holub

To accept or not to accept, that is the question

Imagine that one day someone knocks on your door. A stranger. And at his feet, there lies a package. A package so big that he had to put it down to free his hands to knock. It is wrapped to impress - in bright colors with a shiny ribbon. You immediately wonder about the contents. And the stranger says to you: “I offer you this present but I don’t know what is inside. It is possible that it will be entirely good for you, it may also be entirely bad. But most likely there is both of those, mixed at unknown ratio.” Would you be tempted to open this package? Almost certainly you would. And would you open it? ...

2016-10-01 · (33.95%) · Martin Holub