Having analyzed and reviewed a certain amount of articles and questions, apparently, the expression computational intelligence (CI) is not used consistently and it is still unclear the relationship between CI and artificial intelligence (AI).

According to IEEE computational intelligence society

The Field of Interest of the Computational Intelligence Society (CIS) shall be the theory, design, application, and development of biologically and linguistically motivated computational paradigms emphasizing neural networks, connectionist systems, genetic algorithms, evolutionary programming, fuzzy systems, and hybrid intelligent systems in which these paradigms are contained.

which suggests that CI could be a sub-field of AI or an umbrella term used to group certain AI sub-fields or topics, such as genetic algorithms or fuzzy systems.

What is the difference between artificial intelligence and computational intelligence? Is CI just a synonym for AI?


What is the difference between Artificial Intelligence and Computational Intelligence?

The short answer is that they are two parallel research efforts working on similar problems, but with different methodologies and histories. Essentially, they study similar things, but with different tools. In the modern context, computational intelligence tends to use bio-inspired computing, like evolutionary and genetic algorithms. AI tends to prefer techniques with stronger theoretical guarantees, and still has a significant community focused on purely deductive reasoning. The main area of overlap is in machine learning, especially neural networks.

The longer answer is that your source from 1948 says they are synonyms in part because it predates the split in the research community, which took place later.

The two communities have always some overlap in topics, but in my experience, mostly are skeptical of each other's methodologies, and mostly publish in separate journals. Some authors consider CI to be a subset of AI however, particularly those writing in the 1990s.

Example topics that are solidly in AI but definitely not in CI are logical and expert systems, and statistical approaches to machine learning like regression.

Example topics that are solidly in CI but perhaps not in AI (depending on whether one views CI as a subset of AI or not) are genetic programming, fuzzy logic, and ant colony optimization.

As a rule, AI-rooted techniques have better theoretical guarantees, and better developed theory in general (there are exceptions though). For example, Fuzzy Logic has been strongly criticized for the lack of a solid theoretical foundation (good modern summary here), as have genetic and evolutionary approaches (most famously, both lack a proof of convergence within finite time to a global optima on a smooth surface, even though they do quite well in practice).

CI-rooted techniques nonetheless often see major performance advantages in specific problems (see, for instance, deep learning results), and tend to have a strong experimental and engineering tradition. The No Free Lunch theorems are often used to justify their use when theoretical certainty is missing. Basically the theorems say that, in learning and optimization problems, a technique can only perform well on a problem by performing poorly on some other problem. CI authors argue that there are some problem domains in which their techniques work well (which must be true, because simpler algorithms like hill-climbing outperform them on simple problems).

Check out this paper for lots more references on CI, or this book for a list of core topics in the field.

| improve this answer | |
  • $\begingroup$ Comments are not for extended discussion; this conversation has been moved to chat. $\endgroup$ – nbro Mar 7 at 4:13

In the abstract of chapter 14 (Artificial Intelligence and Computational Intelligence: A Challenge for Power System Engineers) of the book Advanced Solutions in Power Systems: HVDC, FACTS, and Artificial Intelligence: HVDC, FACTS, and Artificial Intelligence the authors say

AI is concerned with decision‐making capabilities such as knowledge representation, search methods, inference techniques, heuristic reasoning, and machine learning. CI techniques include expert systems, fuzzy logic, genetic algorithms (GAs), and artificial neural networks (ANNs). CI can further involve adaptive mechanisms for intelligent behaviors in complex environments, such as the ability to adapt, generalize, abstract, discover, and associate.

AI is thus concerned with machine learning and CI is concerned with neural networks. However, neural networks, genetic algorithms and expert systems are, nowadays, widely considered or viewed as AI topics.

The paper What is Computational Intelligence and what could it become? (2003), by Duch Wlodzislaw, directly addresses the relationship between these two apparently distinct but highly related sub-fields. In the abstract, the author says

What is Computational Intelligence (CI) and what are its relations with Artificial Intelligence (AI)? A brief survey of the scope of CI journals and books with "computational intelligence" in their title shows that at present it is an umbrella for three core technologies (neural, fuzzy and evolutionary), their applications, and selected fashionable methods. At present, CI has no comprehensive foundations and is more a bag of tricks than a solid branch of science. The change of focus from methods to challenging problems is advocated, with CI defined as a part of computer science devoted to the solution of non-algoritmizable problems. In this view AI is a part of CI focused on problems related to higher cognitive functions, while the rest of the CI community works on problems related to perception and control, or lower cognitive functions. Grand challenges on both sides of this spectrum are addressed.

Therefore, AI is a sub-field of CI that focus on certain topics or approaches.

However, in the introduction of the same paper, the author states

Computational intelligence became a new buzzword that means different things to different people.

He further states

IEEE Computational Intelligence Society defines its subjects of interest as neural networks, fuzzy systems and evolutionary computation, including swarm intelligence. The approach taken by the journals and by the book authors is to treat computational intelligence as an umbrella under which more and more methods will be added. A good definition of the field is therefore impossible, because different people include or exclude different methods under the same CI heading.

And, in section 4

For many CI experts biological inspirations are very important, but even if biology is extended to include all neural, psychological, and evolutionary inspirations this will only cover the main themes (neural, fuzzy and evolutionary) that the CI community works on

In the same section

CI studies problems for which there are no effective algorithms, either because it is not possible to formulate them or because they are NP-hard and thus not effective in real life applications. This is quite broad definition: computational intelligence is a branch of computer science studying problems for which there are no effective computational algorithms. Biological organisms solve such problems every day


A good part of CI research is concerned with low-level cognitive functions: perception, object recognition, signal analysis, discovery of structures in data, simple associations and control

There are thus many journals and books that fall into the computational intelligence category, but apparently there is no consensus on the meaning of the expression, which can also change over time. However, there are certain concepts that are often associated with CI, such as evolutionary algorithms, neural networks and fuzzy systems, which are partially inspired by biological systems. There are people that systematically differentiate the two (and often state that AI is more about higher-order cognitive functions), but not all people do it.

To conclude, CI and AI may (or not) be used interchangeably, or CI may refer to a subfield of AI (or vice-versa). Therefore, you should interpret the two expressions depending on the context.

| improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.