This paper introduces Computational Intelligence (CI), discussing its concepts, technologies, and algorithms. The main technologies of CI include neural networks, fuzzy sets, and Granular Computing, as well as evolutionary optimization. These technologies are characterized by their synergistic nature, creating a highly symbiotic processing environment. The paper discusses the advantages and limitations of these technologies and emphasizes their key linkages with Software Engineering, particularly its quantitative aspects. The paper begins with an introduction to CI, focusing on its conceptual, methodological, and algorithmic foundations. It identifies the main features of CI and elaborates on their role in biomedical signal processing. The content is largely self-contained, with essential ideas explained from scratch. The reader is encouraged to have some introductory knowledge of neural networks, fuzzy sets, and evolutionary computing. The paper is structured in a top-down manner. It starts with an introduction to CI as a highly synergistic environment that integrates Granular Computing, neural networks, and evolutionary optimization. Subsequent sections discuss neurocomputing, evolutionary optimization, and Granular Computing, highlighting their synergistic relationships. The paper then explores formal platforms of information granularity, information granulation-degranulation, and the design of semantically sound information granules. It also discusses the role of CI in software engineering. The paper uses standard notation, treating patterns (data) as vectors in n-dimensional space. Distance measures such as Euclidean, Mahalanobis, Hamming, and Tchebyshev are used. Fuzzy sets are described using capital letters, with the same notation applied to their membership functions. The paper emphasizes the importance of integrating numeric data with domain knowledge in the formation of information granules.This paper introduces Computational Intelligence (CI), discussing its concepts, technologies, and algorithms. The main technologies of CI include neural networks, fuzzy sets, and Granular Computing, as well as evolutionary optimization. These technologies are characterized by their synergistic nature, creating a highly symbiotic processing environment. The paper discusses the advantages and limitations of these technologies and emphasizes their key linkages with Software Engineering, particularly its quantitative aspects. The paper begins with an introduction to CI, focusing on its conceptual, methodological, and algorithmic foundations. It identifies the main features of CI and elaborates on their role in biomedical signal processing. The content is largely self-contained, with essential ideas explained from scratch. The reader is encouraged to have some introductory knowledge of neural networks, fuzzy sets, and evolutionary computing. The paper is structured in a top-down manner. It starts with an introduction to CI as a highly synergistic environment that integrates Granular Computing, neural networks, and evolutionary optimization. Subsequent sections discuss neurocomputing, evolutionary optimization, and Granular Computing, highlighting their synergistic relationships. The paper then explores formal platforms of information granularity, information granulation-degranulation, and the design of semantically sound information granules. It also discusses the role of CI in software engineering. The paper uses standard notation, treating patterns (data) as vectors in n-dimensional space. Distance measures such as Euclidean, Mahalanobis, Hamming, and Tchebyshev are used. Fuzzy sets are described using capital letters, with the same notation applied to their membership functions. The paper emphasizes the importance of integrating numeric data with domain knowledge in the formation of information granules.