Deep learning of artificial neural networks (ANNs) is creating highly functional processes that are, unfortunately, nearly as hard to interpret as their biological counterparts. Identification of functional modules in natural brains plays an important role in cognitive and neuroscience alike, and can be carried out using a wide range of technologies such as fMRI, EEG/ERP, MEG, or calcium imaging. However, we do not have such robust methods at our disposal when it comes to understanding functional modules in artificial neural networks. Ideally, understanding which parts of an artificial neural network perform what function might help us to address a number of vexing problems in ANN research, such as catastrophic forgetting and overfitting. Furthermore, revealing a network's modularity could improve our trust in them by making these black boxes more transparent. Here, we introduce a new information-theoretic concept that proves useful in understanding and analyzing a network's functional modularity: the relay information $I_R$. The relay information measures how much information groups of neurons that participate in a particular function (modules) relay from inputs to outputs. Combined with a greedy search algorithm, relay information can be used to identify computational modules in neural networks. We also show that the functionality of modules correlates with the amount of relay information they carry.

Artificial Intelligence (AI) is revolutionizing the way we live and work, so today I invite you to learn more about this topic by approaching it from three different and increasingly complex segments. Broadly speaking, we can refer to AI as the simulation of human intelligence by machines. In other words, a discipline that tries to create systems capable of learning and reasoning like people . Importantly, Artificial Intelligence is the most debated technology of the 21st century. Today, it is widely used to solve complex problems and facilitate human tasks.

A paper in the recent Artificial Life journal special issue on open-ended evolution (OEE) presents a simple evolving computational system that, it is claimed, satisfies all proposed requirements for OEE (Hintze, 2019). Analysis and discussion of the system are used to support the further claims that complexity and diversity are the crucial features of open-endedness, and that we should concentrate on providing proper definitions for those terms rather than engaging in "the quest for open-endedness for the sake of open-endedness" (Hintze, 2019, p. 205). While I wholeheartedly support the pursuit of precise definitions of complexity and diversity in relation to OEE research, I emphatically reject the suggestion that OEE is not a worthy research topic in its own right. In the same issue of the journal, I presented a "high-level conceptual framework to help orient the discussion and implementation of open-endedness in evolutionary systems" (Taylor, 2019). In the current brief contribution I apply my framework to Hinzte's model to understand its limitations. In so doing, I demonstrate the importance of studying open-endedness for the sake of open-endedness.

It's a process as old as time, but there's a twist: This worm is a bit of open-source software that encodes biological data gleaned from decades of scientific study into the nematode C. elegans. The parameters are programmed, but the worm acted on its own. Well, the widely studied nematode was the first multicellular organism to have its entire genome mapped. With just 1,031 cells and 302 neurons, the 1 millimeter-long transparent worm is a manageable animal to recreate as a software-based artificial life form. The simple life form nevertheless moves, mates, eats and even socializes, and replicating it using computer code may yield some biological insights into the biological bases for those behaviors.