GID
_
_
Georgios' personal web page (last updated on Apr. 25th, 2025)
Featured

An introduction to self-organizing maps

An introduction to self-organizing maps
This post introduces the classical self-organizing map (SOM) algorithm proposed by Grossberg and later by Kohonen. We explain the algorithm's fundamental aspects and implement it on Pytorch.
Featured

Genetic Algorithms & Island Models

Genetic Algorithms & Island Models
Genetic algorithms (GAs) are a family of optimization algorithms that can solve constrained and unconstrained optimization problems by mimicking biological evolution. In this post, we introduce the fundamental concepts of GAs and the Island Model, an extension of GAs.
Featured

Autocorrelation Functions for Time Series

Autocorrelation Functions for Time Series
This post provides some theoretical background on autocorrelation functions and how to use them to analyze time series. Furthermore, we show how to use the autocorrelation (ACF) function and the Partial Autocorrelation (PACF) functions to determine the parameters for an ARMA model.
Featured

Time series forecasting error metrics

Time series forecasting error metrics
Error measures provide a way to quantify the quality of a forecasting algorithm (*e.g.*, performance). We briefly introduce time series and the fundamental terms of forecasting. We will then introduce the most commonly used error measures and give some examples. We provide an example of how to use error metrics in a real-life forecasting scenario.
Featured

Useful data transformations

Useful data transformations
Fundamental data transformations such as mean subtraction (centering data), normalization, and standardization are standard preprocessing steps for many algorithms. Therefore, in this post, we provide some information regarding different basic data transformations as well as simple examples of Python code for applying those transforms to real data.
Featured

Organs-on-Chip-as-a-Service: A proposal bridging cloud services and scientific experiments

Organs-on-Chip-as-a-Service: A proposal bridging cloud services and scientific experiments
Technological advancements enable delicate and complex experiments on small-scale devices, such as organs-on-chips, improving and accelerating research. At the same time, an ever-increasing diversity of hardware platforms is accessible via cloud services. This perspective article describes our vision for the future of organs-on-chips. We present the main idea behind organs-on-chips as a cloud service, a brief description of the proposed infrastructure, and some applications.

How do we compute a Gramian Angular Field (GAF) for time series?

How do we compute a Gramian Angular Field (GAF) for time series?
This post introduces the Gramian Angular Field and its implementation in Python.