Computational Intelligence (CI) community has developed hundreds of algorithms for intelligent data analysis, but still many hard problems in computer vision, signal processing or text and multimedia understanding, problems that require deep learning techniques, are open. Modern data mining packages contain numerous modules for data acquisition, pre-processing, feature selection and construction, instance selection, classification, association and approximation methods, optimization techniques, pattern discovery, clusterization, visualization and post-processing. A large data mining package allows for billions of ways in which these modules can be combined. No human expert can claim to explore and understand all possibilities in the knowledge discovery process. This is where algorithms that learn how to learnl come to rescue. Operating in the space of all available data transformations and optimization techniques these algorithms use meta-knowledge about learning processes automatically extracted from experience of solving diverse problems. Inferences about transformations useful in different contexts help to construct learning algorithms that can uncover various aspects of knowledge hidden in the data. Meta-learning shifts the focus of the whole CI field from individual learning algorithms to the higher level of learning how to learn. This book defines and reveals new theoretical and practical trends in meta-learning, inspiring the readers to further research in this exciting field.

The book focuses on different variants of decision tree induction but also describes the meta-learning approach in general which is applicable to other types of machine learning algorithms. The book discusses different variants of decision tree induction and represents a useful source of information to readers wishing to review some of the techniques used in decision tree learning, as well as different ensemble methods that involve decision trees. It is shown that the knowledge of different components used within decision tree learning needs to be systematized to enable the system to generate and evaluate different variants of machine learning algorithms with the aim of identifying the top-most performers or potentially the best one. A unified view of decision tree learning enables to emulate different decision tree algorithms simply by setting certain parameters. As meta-learning requires running many different processes with the aim of obtaining performance results, a detailed description of the experimental methodology and evaluation framework is provided. Meta-learning is discussed in great detail in the second half of the book. The exposition starts by presenting a comprehensive review of many meta-learning approaches explored in the past described in literature, including for instance approaches that provide a ranking of algorithms. The approach described can be related to other work that exploits planning whose aim is to construct data mining workflows. The book stimulates interchange of ideas between different, albeit related, approaches.

The two volume set LNAI 3801 and LNAI 3802 constitute the refereed proceedings of the annual International Conference on Computational Intelligence and Security, CIS 2005, held in Xi'an, China, in December 2005. The 338 revised papers presented - 254 regular and 84 extended papers - were carefully reviewed and selected from over 1800 submissions. The first volume is organized in topical sections on learning and fuzzy systems, evolutionary computation, intelligent agents and systems, intelligent information retrieval, support vector machines, swarm intelligence, data mining, pattern recognition, and applications. The second volume is subdivided in topical sections on cryptography and coding, cryptographic protocols, intrusion detection, security models and architecture, security management, watermarking and information hiding, web and network applications, image and signal processing, and applications.

This book constitutes the refereed proceedings of the 29th Australasian Joint Conference on Artificial Intelligence, AI 2016, held in Hobart, TAS, Australia, in December 2016. The 40 full papers and 18 short papers presented together with 8 invited short papers were carefully reviewed and selected from 121 submissions. The papers are organized in topical sections on agents and multiagent systems; AI applications and innovations; big data; constraint satisfaction, search and optimisation; knowledge representation and reasoning; machine learning and data mining; social intelligence; and text mining and NLP. The proceedings also contains 2 contributions of the AI 2016 doctoral consortium and 6 contributions of the SMA 2016.

“Life on earth is filled with many mysteries, but perhaps the most challenging of these is the nature of Intelligence.” – Prof. Terrence J. Sejnowski, Computational Neurobiologist The main objective of this book is to create awareness about both the promises and the formidable challenges that the era of Data-Driven Decision-Making and Machine Learning are confronted with, and especially about how these new developments may influence the future of the financial industry. The subject of Financial Machine Learning has attracted a lot of interest recently, specifically because it represents one of the most challenging problem spaces for the applicability of Machine Learning. The author has used a novel approach to introduce the reader to this topic: The first half of the book is a readable and coherent introduction to two modern topics that are not generally considered together: the data-driven paradigm and Computational Intelligence. The second half of the book illustrates a set of Case Studies that are contemporarily relevant to quantitative trading practitioners who are dealing with problems such as trade execution optimization, price dynamics forecast, portfolio management, market making, derivatives valuation, risk, and compliance. The main purpose of this book is pedagogical in nature, and it is specifically aimed at defining an adequate level of engineering and scientific clarity when it comes to the usage of the term “Artificial Intelligence,” especially as it relates to the financial industry. The message conveyed by this book is one of confidence in the possibilities offered by this new era of Data-Intensive Computation. This message is not grounded on the current hype surrounding the latest technologies, but on a deep analysis of their effectiveness and also on the author’s two decades of professional experience as a technologist, quant and academic.

Recent years have seen numerous applications across a variety of fields using various techniques of Computational Intelligence. This book, one of a series on the foundations of Computational Intelligence, is focused on learning and approximation.

Deep neural networks (DNNs) with their dense and complex algorithms provide real possibilities for Artificial General Intelligence (AGI). Meta-learning with DNNs brings AGI much closer: artificial agents solving intelligent tasks that human beings can achieve, even transcending what they can achieve. Meta-Learning: Theory, Algorithms and Applications shows how meta-learning in combination with DNNs advances towards AGI. Meta-Learning: Theory, Algorithms and Applications explains the fundamentals of meta-learning by providing answers to these questions: What is meta-learning?; why do we need meta-learning?; how are self-improved meta-learning mechanisms heading for AGI ?; how can we use meta-learning in our approach to specific scenarios? The book presents the background of seven mainstream paradigms: meta-learning, few-shot learning, deep learning, transfer learning, machine learning, probabilistic modeling, and Bayesian inference. It then explains important state-of-the-art mechanisms and their variants for meta-learning, including memory-augmented neural networks, meta-networks, convolutional Siamese neural networks, matching networks, prototypical networks, relation networks, LSTM meta-learning, model-agnostic meta-learning, and the Reptile algorithm. The book takes a deep dive into nearly 200 state-of-the-art meta-learning algorithms from top tier conferences (e.g. NeurIPS, ICML, CVPR, ACL, ICLR, KDD). It systematically investigates 39 categories of tasks from 11 real-world application fields: Computer Vision, Natural Language Processing, Meta-Reinforcement Learning, Healthcare, Finance and Economy, Construction Materials, Graphic Neural Networks, Program Synthesis, Smart City, Recommended Systems, and Climate Science. Each application field concludes by looking at future trends or by giving a summary of available resources. Meta-Learning: Theory, Algorithms and Applications is a great resource to understand the principles of meta-learning and to learn state-of-the-art meta-learning algorithms, giving the student, researcher and industry professional the ability to apply meta-learning for various novel applications. A comprehensive overview of state-of-the-art meta-learning techniques and methods associated with deep neural networks together with a broad range of application areas Coverage of nearly 200 state-of-the-art meta-learning algorithms, which are promoted by premier global AI conferences and journals, and 300 to 450 pieces of key research Systematic and detailed exploration of the most crucial state-of-the-art meta-learning algorithm mechanisms: model-based, metric-based, and optimization-based Provides solutions to the limitations of using deep learning and/or machine learning methods, particularly with small sample sizes and unlabeled data Gives an understanding of how meta-learning acts as a stepping stone to Artificial General Intelligence in 39 categories of tasks from 11 real-world application fields

This open access book as one of the fastest-growing areas of research in machine learning, metalearning studies principled methods to obtain efficient models and solutions by adapting machine learning and data mining processes. This adaptation usually exploits information from past experience on other tasks and the adaptive processes can involve machine learning approaches. As a related area to metalearning and a hot topic currently, automated machine learning (AutoML) is concerned with automating the machine learning processes. Metalearning and AutoML can help AI learn to control the application of different learning methods and acquire new solutions faster without unnecessary interventions from the user. This book offers a comprehensive and thorough introduction to almost all aspects of metalearning and AutoML, covering the basic concepts and architecture, evaluation, datasets, hyperparameter optimization, ensembles and workflows, and also how this knowledge can be used to select, combine, compose, adapt and configure both algorithms and models to yield faster and better solutions to data mining and data science problems. It can thus help developers to develop systems that can improve themselves through experience. This book is a substantial update of the first edition published in 2009. It includes 18 chapters, more than twice as much as the previous version. This enabled the authors to cover the most relevant topics in more depth and incorporate the overview of recent research in the respective area. The book will be of interest to researchers and graduate students in the areas of machine learning, data mining, data science and artificial intelligence.

Computational Knowledge Vision: The First Footprints presents a novel, advanced framework which combines structuralized knowledge and visual models. In advanced image and visual perception studies, a visual model's understanding and reasoning ability often determines whether it works well in complex scenarios. This book presents state-of-the-art mainstream vision models for visual perception. As computer vision is one of the key gateways to artificial intelligence and a significant component of modern intelligent systems, this book delves into computer vision systems that are highly specialized and very limited in their ability to do visual reasoning and causal inference. Questions naturally arise in this arena, including (1) How can human knowledge be incorporated with visual models? (2) How does human knowledge promote the performance of visual models? To address these problems, this book proposes a new framework for computer vision–computational knowledge vision. - Presents a concept and basic framework of Computational Knowledge Vision that extends the knowledge engineering methodology to the computer vision field - Discusses neural networks, meta-learning, graphs, and Transformer models - Illustrates a basic framework for Computational Knowledge Vision whose essential techniques include structuralized knowledge, knowledge projection, and conditional feedback

This book constitutes the thoroughly refereed post-conference proceedings of the Joint Meeting of the 2nd Luxembourg-Polish Symposium on Security and Trust and the 19th International Conference Intelligent Information Systems, held as International Joint Confererence on Security and Intelligent Information Systems, SIIS 2011, in Warsaw, Poland, in June 2011. The 29 revised full papers presented together with 2 invited lectures were carefully reviewed and selected from 60 initial submissions during two rounds of selection and improvement. The papers are organized in the following three thematic tracks: security and trust, data mining and machine learning, and natural language processing.