On a lot of machine learning tasks, the progress of the model (in terms of accuracy) is relatively rapid in the beginning. However, as it reaches the human-level performance it begins to slow down and later on plateau almost completely.

Figure 1: Model performance increase over time. Comparing Human Error vs Bayes Error. Src: Nezar Assawiel

Over time, as the models keep getting bigger and bigger and they are trained on more and more data, the performance approaches but never surpasses a theoretical limit known as Bayesian Optimal Error (B.O.E.). In other words, you can think of Bayesian Optimal Error as the best optimal error than can be achieved. However, there’s no function that can go…


Photo by israel palacio on Unsplash

Before we dive into explaining the core concepts of neural networks, I want to take some time and appreciate the remarkable and complex thing we, humans, hold between our ears —the brain.


I want to start this article with a question —How many jelly beans exactly do you think there are in this jar? Give a wild guess…

A finance professor named Jack Treynor performed this same experiment on 56 student of his students and asked them to write down the number of jelly beans in a jar. Individually, students came nowhere close to the correct answer; many assumptions were either too high, or too low.

However, when the average of those assumption was calculated, 871, it came really close to the actual number of jelly beans in the jar, 850, with…


In the previous articles, I have explained the underlying distinction between supervised and unsupervised learning, which was the presence or absence of labeled data (teacher). In reinforcement learning (RF) there is no supervisor that tells the algorithm that the decision was good or bad; instead, there is reward that signals the algorithm toward the general desired direction.

Courtesy of David Silver

Reinforcement learning, as a field of study, can be expressed as the overlap of many others. As shown in the graph, it includes everything from computer science to economics to neuroscience — and it tries to study the approach to solving reward-based problems.


Photo by Marius Masalar on Unsplash

I mentioned the unsupervised learning in the last blog, Classical Machine Learning — Supervised Edition, here’s the link in case you missed it.

We said that unsupervised learning is when we provide the machine with unlabeled data, and ask it to find meaningful structures on its own. In this type of learning, the machine does not have a teacher (labeled data).

Not always we have the luxury of labeled data. Say we want to create rabbit classifier — should I take a million pictures of rabbits and label them one by one? Well, thank you very much, but no.

Thanks…


Photo by Pereanu Sebastian on Unsplash

Machine Learning (ML) initially started in the ’50s and ’60s as pattern recognition. They got better by seeing more data. Most of these algorithms were based on statistics and probabilistic reasoning, by measuring the distance between data points, directions of vectors, intensities of values, etc.

These [old] algorithms are widespread. You can see them everywhere — read this article next, Google reporting your random sign-in — they’re simple to use, easy to understand, and don’t require a large amount of computational power.

Big tech companies do not hesitate to use more complex algorithms (neural-network-based). An additional 2% accuracy means earning…


With the rapid expansion of Machine Learning as a field of research, it’s not easy to keep up with everything that is being invented and discovered.

I have created a graph that will make the distinction of the types of machine learning systems easier to understand.

It is useful to keep in mind there’s more than one way (ML algorithm) to solve a specific problem. Usually, there are several that fit and it’s your duty to identify which is the best algorithm with the given circumstances of its implementation.

Nowadays, everything is being solved with neural networks; why use a…


In the following weeks I will share with you some articles with the intent to explain some machine learning concepts. A straightforward approach with real-world problems that uses simple language and is easy to understand. This series will be aimed at anyone and everyone, regardless of background. You’ll be able to follow regardless if you’re an engineer or manager.

The main idea behind writing this series is to spike some curiosity in Kosovo’s ICT community and other new-comers for machine learning and its great potential. …


Photo by Gertrūda Valasevičiūtė on Unsplash

If you’re reading this, it shows that you are curious and interested in learning! Awesome — you’ve come across the right article. Here, I will share with you my journey of learning Machine Learning (no pun intended) and will share the main resources I have utilized to get a good foundation for machine learning

Machine learning is the science and art of programming computers so they can learn from data. A more general definition goes:

“[Machine Learning] is the field of study that gives computers the ability to learn without being explicitly programmed” — Arthur Samuel, 1959

This field has…

Bardh Rushiti

Machine Learning Engineer | Innately curious about the world.

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