https://www2.econ.iastate.edu/tesfatsi/DeepLearningInNeuralNetworksOverview.JSchmidhuber2015.pdf

Deep learning in neural networks

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Data Mining - Concepts and Techniques.

Data Mining Practical Machine Learning Tools and Techniques

Agent-based modelling and simulation (ABMS) is a relatively new approach to modelling systems composed of autonomous, interacting agents. Agent-based modelling is a way to model the dynamics of complex systems and complex adaptive systems. Such systems often self-organize themselves and create emergent order. Agent-based models also include models of behaviour (human or otherwise) and are used to observe the collective effects of agent behaviours and interactions. The development of agent modelling tools, the availability of micro-data, and advances in computation have made possible a growing number of agent-based applications across a variety of domains and disciplines. This article provides a brief introduction to ABMS, illustrates the main concepts and foundations, discusses some recent applications across a variety of disciplines, and identifies methods and toolkits for developing agent models.

/pdf/tutorial-on-agent-based-modelling-and-simulation-4xgz9pwney.pdf

Tutorial on agent-based modelling and simulation

The XCS classifier system represents a major advance in learning classifier systems research because (1) it has a sound and accurate generalization mechanism, and (2) its learning mechanism is based on Q-learning, a recognized learning technique. In taking XCS beyond its very first environments and parameter settings, we show that, in certain difficult sequential (“animat”) environments, performance is poor. We suggest that this occurs because in the chosen environments, some conditions for proper functioning of the generalization mechanism do not hold, resulting in overly general classifiers that cause reduced performance. We hypothesize that one such condition is a lack of sufficiently wide exploration of the environment during learning. We show that if XCS is forced to explore its environment more completely, performance improves dramatically. We propose a technique, based on Sutton's Dyna concept, through which wider exploration would occur naturally. Separately, we demonstrate that the compactness of the representation evolved by XCS is limited by the number of instances of each generalization actually present in the environment. The paper shows that XCS's generalization mechanism is effective, but that the conditions under which it works must be clearly understood.

An analysis of generalization in the xcs classifier system

Web Usage Mining is that area of Web Mining which deals with the extraction of interesting knowledge from logging information produced by Web servers. In this paper we present a survey of the recent developments in this area that is receiving increasing attention from the Data Mining community.

Mining interesting knowledge from weblogs: a survey

Basics.- What Is a Learning Classifier System?.- A Roadmap to the Last Decade of Learning Classifier System Research (From 1989 to 1999).- State of XCS Classifier System Research.- An Introduction to Learning Fuzzy Classifier Systems.- Advanced Topics.- Fuzzy and Crisp Representations of Real-Valued Input for Learning Classifier Systems.- Do We Really Need to Estimate Rule Utilities in Classifier Systems?.- Strength or Accuracy? Fitness Calculation in Learning Classifier Systems.- Non-homogeneous Classifier Systems in a Macro-evolution Process.- An Introduction to Anticipatory Classifier Systems.- A Corporate XCS.- Get Real! XCS with Continuous-Valued Inputs.- Applications.- XCS and the Monk's Problems.- Learning Classifier Systems Applied to Knowledge Discovery in Clinical Research Databases.- An Adaptive Agent Based Economic Model.- The Fighter Aircraft LCS: A Case of Different LCS Goals and Techniques.- Latent Learning and Action Planning in Robots with Anticipatory Classifier Systems.- The Bibliography.- A Learning Classifier Systems Bibliography.

Learning Classifier Systems, From Foundations to Applications

Takes initial steps toward a theory of generalization and learning in the learning classifier system XCS. We start from Wilson's generalization hypothesis, which states that XCS has an intrinsic tendency to evolve accurate, maximally general classifiers. We analyze the different evolutionary pressures in XCS and derive a simple equation that supports the hypothesis theoretically. The equation is tested with a number of experiments that confirm the model of generalization pressure that we provide. Then, we focus on the conditions, termed "challenges," that must be satisfied for the existence of effective fitness or accuracy pressure in XCS. We derive two equations that suggest how to set the population size and the covering probability so as to ensure the development of fitness pressure. We argue that when the challenges are met, XCS is able to evolve problem solutions reliably. When the challenges are not met, a problem may provide intrinsic fitness guidance or the reward may be biased in such a way that the problem will still be solved. The equations and the influence of intrinsic fitness guidance and biased reward are tested on large Boolean multiplexer problems. The paper is a contribution to understanding how XCS functions and lays the foundation for research on XCS's learning complexity.

/pdf/toward-a-theory-of-generalization-and-learning-in-xcs-3fowsn4tnv.pdf

Toward a theory of generalization and learning in XCS

user-deﬁned types : in this case, the event service would pro-vide the features of a typed programming language that allows thedeﬁnition of data types (e.g., an object-oriented language).Extending ﬁlters to user-deﬁned types can be done with easy exten-sions to the ﬁltering language similarly to query languages for object-oriented databases like O2 SQL or OQL. A ﬁlter might look like this: person.birthday.greaterThan ( Date “Dec 16” )) ;From the viewpoint of the application programmer, the latter solutionwould be best for its enhanced modeling features. However, because ﬁlterscould contain an arbitrary user-deﬁned code, it would be very difﬁcult to per-form optimizations based on the static analysis of ﬁlters. This would severelyimpact on scalability. Also, on a largescale, it might not be legitimate to assumethat every component of the system is able to understand an object orientedlanguage.From the viewpoint of the designer of the event service, the ﬁrst solutionis deﬁnitely the easiest one to implement. It poses less problems of encoding

/pdf/architectures-for-an-event-notification-service-scalable-to-5a6dkithds.pdf

Pier Luca Lanzi

Papers

An analysis of generalization in the xcs classifier system

Mining interesting knowledge from weblogs: a survey

Learning Classifier Systems, From Foundations to Applications

Toward a theory of generalization and learning in XCS

Architectures for an Event Notification Service Scalable to Wide-area Networks