One of the main challenges in feature learning using Deep Convolutional Neural Networks (DCNNs) for large-scale face recognition is the design of appropriate loss functions that enhance discriminative power.

This quote was taken from ArcFace paper. The paper investigates face recognition problem, and introduces a loss function to train more discriminative embeddings. An embedding is a relatively low-dimensional space into which you can translate high-dimensional vectors. Ideally, an embedding captures some of the semantics of the input by placing semantically similar inputs close together in the embedding space. For example, let’s say you have embeddings representing “Person A” and “Person…


By the end of this post you should,

  1. understand the idea behind generative modeling,
  2. understand the differences between generative and discriminative modeling,
  3. understand what is an Autoencoder and how to built one,

This is the first post of a series about “Generative Deep Learning”. In later posts, we are going to investigate other generative models such as Variational Autoencoder, Generative Adversarial Networks (and variations of it) and more. However, the reason why we start with vanilla Autoencoder is because they are easy to understand, they encapsulate some of the core ideas behind generative modeling, and they provide a smoother transition…

My journey with recording and editing videos has started a year ago, after I had decided to open my own YouTube channel (the main content is in Turkish language, however there will also be some English content in the future. If you are interested in, check it out!). I was thinking: “Okay, I work as a Data Scientist and I know some stuff about it. There are many resources where you can learn more about it in English, however there aren’t that many in my own language. So, wouldn’t it be nice if someone who doesn’t speak English from my…


By the end of this post you should:

  1. understand what is mean, and why is it so useful,
  2. understand the importance of variance and what it is tell us,
  3. understand what is normal distribution, and why we use it.

We all are a bit different, aren’t we? It is mostly not a bad thing. If we were all the same color, we wouldn’t have any rainbow right? Some people are taller than others; some have blue eyes, some brown; some people can eat anything they want and still don’t gain any weight, and for some people, water is enough. My…


By the end of this post you should:

  1. understand why accuracy is not always the best metric of choice in classification tasks,
  2. understand the difference between accuracy, precision, recall and F1 score and be able to choose the right metric for your needs.

One of the most important decisions that have to be made before starting a Machine Learning project is to decide which metric to use. It is so crucial, in a sense that the wrong metric can potentially trick you to believe that your model is good, or getting better when in reality it is not.

I have…

Kıvanç Yüksel

Machine Learning Engineer/Researcher

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store