Every machine learning system has hyperparameters, and the most basic task inautomated machine learning (AutoML) is to automatically set these hyperparam-eters to optimize performance. Especially recent deep neural networks cruciallydepend on a wide range of hyperparameter choices about the neural network’s archi-tecture, regularization, and optimization. Automated hyperpa…
Artificial intelligence (AI), generally thought of as using c omputers t o a ccomplish tasks r equiring human intelligence, is not a new c oncept. Ho wever, gen erative AI, a type of AI system that can generate t ext, ima ges, or other m edia in response to pr ompts, has suddenly become an omnipresent part of the a cademic scene. In the f orm of ChatGPT an d oth ers, generative…
The book provides an overview of the different AI technologies, demystifying terms such as search, reasoning, learning, adapting, understanding, and interacting. It covers the two dominant paradigms in AI, both the “data-driven” and “symbolic” AI systems, showing how they can complement each other. The theory is illustrated with 22 real-world examples from industry, giving a solid under…
Rapid advances in AI technologies have generated intense interest and debate about their potential to reshape industries and societies. This book compiles academic papers from "The Economic Perspective of Artificial Intelligence (EPEAI)" conference held at the Ruhr West University of Applied Sciences in Germany, in March 2023. The authors explore the economic dimensions of AI, shedding light on…
In the last few years, a growing and thriving AI ecosystem has emerged in Africa. Within this ecosystem, there are local tech spaces as well as a number of internationally driven technology hubs and centres estab-lished by big tech companies such as Twitter, Google, Facebook, Alibaba Group, Huawei, Amazon and Microsoft have significantly increas…
All AI applications rely on large datasets, to create algorithmic models, to trainthem, to run them over huge amounts of collected information and extract infer-ences, correlations, and new information for decision-making processes or otheroperations that, to some extent, replicate human cognitive abilities.These results can be achieved using a variety of different mathematical andcomputer-base…
The rise of civilization is synonymous with the creation of tools that extend the intel-lectual and physical reach of human beings [133]. The pinnacle of such endeavours isto replicate the flexible reasoning capacity of human intelligence within a machine,making it capable of performing useful work on command, despite the complexityand adversity of the real world. In order to achieve such Artif…
The intersection of AI, the Internet of Things (IoT) and edge computing has kindled the edge AI revolution that promises to redefine how we perceive and interact with the physical world through intelligent devices. Edge AI moves intelligence from the network centre to the devices at its edge, entrusting these endpoints to analyse data locally, make decisions, and provide real-time responses. Re…
This book comprises three parts. In Part I (Chaps. 2–7) we sketch the basic concepts andarchitecture of metalearning systems, especially focusing on which types of “metaknowl-edge” can be collected by observing the performance of different models on prior tasksand how this can be used within metalearning approaches to learn new tasks more effi-ciently. Since this type of metalearning is c…
It should be more widely appreciated that literature is a kind of scientific tool that can be used to shed light on consciousness. The argument is that the richest description of the phenomenon of human experience come from our finest writers, who are capable of capturing moments in time in exquisite detail from multiple perspectives. In this view, there is no …