@sepdek's

Clustering is an important category of machine learning methods and a main form of unsupervised learning. Clustering is essentially distinctive and substantially different from the other dominant form of machine learning, classification, in that it does not rely on training (supervised learning). In principle, clustering represents any method that tries to identify and distinguish groups […]

Of the most basic forms of a machine learning system based on neural networks is the one in which training is accomplished using back error propagation, or simply back-propagation. Back-propagation is a technique, like many others, that targets the minimisation of a cost function during a learning process by following the descending gradient of the […]

Machine learning is a research domain that is becoming the holy grail of data science towards the modelling and solution of science and engineering problems. I have already witnessed researchers proposing solutions to problems out of their area of expertise using machine learning methods, basing their approach on the success of modern machine learning algorithm […]

This post serves as a practical approach towards a vectorized implementation of the Expectation Maximization (EM) algorithm mainly for MATLAB or OCTAVE applications. EM is a really powerful and elegant method for finding maximum likelihood solutions in cases where the hypothesis involves a gaussian mixture model and latent variables. Introduction EM is connected with the […]

This post serves as a cheat sheet for differentiation. It just includes the most basic of the rules to be remembered when computing derivatives. First a little reminder on the notation being used in differentiation. Leibniz’s notation for the first derivative of a function f(x) is Newton’s notation for the first derivative of a function […]

There is a really large number of applications in engineering, in which the identification of critical points of a function is crucial for the analysis and modeling of a process or a system. Generally, one may identify three kinds of critical points, that is (a) maxima, (b) minima and (c) saddle or stationary inflection points. […]

A function is a rule that maps each of the elements in a domain to one and only one element in a range. The set of all possible elements in the input is the domain D of a function; the set of all possible elements in the output is the range R of a function. […]

Formally stated, the derivative of a function of the form with k a constant and with respect to an independent variable x, is simply, I find this to be extremely handy in all cases. Consider the simple case in which, In the same way, In a more complex example, In an even more complex example, […]

The thing starts with invariance, conservation and symmetry… Invariant is something that is unchanged by a coordinate transformation. Conserved is something that is unchanged by a process within a given coordinate system. Symmetry could be considered a broader property of some ‘universe’ in which some entity of interest remains the same under a specific operation. […]

In order to be a measure (distance) d must:   In order to be a metric (distance) d has to be a measure and:   …and here is the cheat sheet: