Thoughts and Theory

Uncertainty as the prerequisite to act in uncertainty. Implications for artificial intelligence.

Figure 1. The Bayesian and the frequentist start from different metaphysical biases and move towards one another in their pursuit of knowledge of things. Image by author.

In Part 1 of this series I discussed how two distinct metaphysical perceptions of uncertainty lead to different theories and approaches. The frequentist moves towards his knowledge of events with the intent of finding the best description. The Bayesian, on the other hand, moves towards his knowledge with the intent of finding the best logical narrative explaining the events. In this article, I argue their journeys for knowledge merge at the concept of compression. This merging becomes more evident in neural networks: the success story of frequentist AI.

Acquiring one’s knowledge in uncertainty one way or another is not the…


On how opposing preconceptions of Bayesians and Frequentists about uncertainty lead to different answers to the same questions.

Image by Arek Socha from Pixabay

Unlike other branches of mathematics that deal with exactitude, statistics deals with uncertainty. Despite being a branch of mathematics, there has been quite a bit of conflict about applying statistics and interpreting its results. The word statistics is derived from the Latin term statisticum collegium (“council of state”) and the Italian word statista (“ statesman” or “ politician”). In statistics, we have two “parties”: frequentists and Bayesians. As is the case with all opposing parties, frequentists and Bayesians have different presuppositions about uncertainty. The former perceive it as an inherent property of external events; the latter perceive it as something…


The Mutilation of Uranus (god of the sky) by Kronos (god of time) by Giorgio Vasari and Gherardi Christofano 16th century Palazzo Vecchio, Florence. {{PD-Art}}

Spiking Neural Networks (SNN) has recently been a topic of interest in the field of Artificial Intelligence. The premise behind SNN is that neurons in the brain, unlike our current modelling of it, communicate with one another via spike trains that occur at different frequencies and timings. Another way of visualizing the workings of natural neural netwoks is to image a pond with waves interacting with one another forming variety of patterns. The crucial advantage of SNN is the ability to encode time in a more meaningful way by making use of relative timings of the spikes.

New hardware and…


Why are Artificial Neural Networks so good at generating fake faces, classifying whether an image depicts a dog or a cat, translating texts across languages, converting speech to text, and more? These breakthroughs came about through creative errors and trials of new practical ideas. Our theoretical understanding of neural networks, however, did not catch up with these success stories. We frequently hear about the black-box nature of these networks, that they are unable to be explained.

For instance, the classic computer vision approach to image recognition problems would be to write an explicitly formulated piece of software that extracts well-defined…


Photo by Jeremy Bishop on Unsplash

Previously, I gave an introduction to applications of Artificial Intelligence (AI) and Machine Learning (ML) algorithms to cybersecurity problems, and argued that it will change the game of cyber defense. Here, I discuss a promising application of AI/ML to privileged access management. A privileged user is someone who has administrative access to critical systems, applications and accounts. Privileged access management can be defined as managing and auditing account and data access by privileged users. Conventionally, such privileged users, credentials, or accounts are identified beforehand. I propose a novel solution to learn which users, credentials, and accounts are privileged from the…


The high frequency of successful large-scale cyber attacks points to gaps existing in conventional cybersecurity. Though attacks are often blamed on mistakes stemming from human factors, the problems of the current cyber situation go deeper. In this article, I argue that the limitations of the conventional defense lie in its simplistic and generic approach, which enables attackers to bypass them with ease and re-use the same attack strategy on multiple victims. I show how the adoption of Artificial Intelligence can change this scene, by personalizing the defence to the defender, forcing attackers to a different and harder situation.

The increasing…

Nariman Mammadli

Exploring the boundaries of artificial intelligence with a special interest in its applications on cybersecurity. linkedin.com/in/mammadlinariman

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