Understanding the mechanisms behind mysterious evolutionary This simulation revolves around two processes: transitions in individuality (ETIs) is a central narrative self-organization, which is governed by evolving neural networks in contemporary biology Okasha (2005); Szathmáry that dictate boid behaviour, and natural selection, (2015). These transitions, which encompass the evolutionary which forces these agents to adapt and survive. This subtle milestones enabling discrete biological entities to coalesce interplay between individual behaviour modulation and into complex, higher-order wholes, pose profound group dynamics results in the formation of cohesive groups questions about the origins of collective reproduction and capable of collective reproduction--a phenomenon that mirrors complex life forms. At the heart of understanding ETIs lies key aspects of ETIs. VitaNova demonstrates how the the exploration of how new levels of biological organisation combined forces of self-organization and natural selection emerge and the dynamics by which these levels attain and can drive the spontaneous formation of reproductive groups, sustain the capability for collective reproduction Smith and providing new insights into the evolution of complex biological Szathmary (1997).

Deep Learning (DL) components are routinely integrated into software systems that need to perform complex tasks such as image or natural language processing. The adequacy of the test data used to test such systems can be assessed by their ability to expose artificially injected faults (mutations) that simulate real DL faults. In this paper, we describe an approach to automatically generate new test inputs that can be used to augment the existing test set so that its capability to detect DL mutations increases. Our tool DeepMetis implements a search based input generation strategy. To account for the non-determinism of the training and the mutation processes, our fitness function involves multiple instances of the DL model under test. Experimental results show that \tool is effective at augmenting the given test set, increasing its capability to detect mutants by 63% on average. A leave-one-out experiment shows that the augmented test set is capable of exposing unseen mutants, which simulate the occurrence of yet undetected faults.

ETIS is pleased to have Futurist Rudy de Waele as the keynote speaker of the Common Session of the 2017 ETIS Community Gathering. Rudy is a futurist and innovation strategist, a content curator, a keynote speaker and also an author of books and articles related to IoT, robotics and Artificial Intelligence. He has helped numerous companies to transform their business models by capturing the innovation trends that at first might have posed a risk to their industries. To mention a few names of the global brands Rudy worked with: Telefonica, Ericsson, Vodafone, IBM, PayPal, Samsung and the World Bank. Rudy has also developed more than 100 events in more than 50 cities, for instance Mobile Mondays in Barcelona and Madrid, AppCircus and Wearable Wednesdays.