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

Introduction to linear and nonlinear programming

There is increasing interest in employing shotgun sequencing, rather than amplicon sequencing, to analyze microbiome samples. Typical projects may involve hundreds of samples and billions of sequencing reads. The comparison of such samples against a protein reference database generates billions of alignments and the analysis of such data is computationally challenging. To address this, we have substantially rewritten and extended our widely-used microbiome analysis tool MEGAN so as to facilitate the interactive analysis of the taxonomic and functional content of very large microbiome datasets. Other new features include a functional classifier called InterPro2GO, gene-centric read assembly, principal coordinate analysis of taxonomy and function, and support for metadata. The new program is called MEGAN Community Edition (CE) and is open source. By integrating MEGAN CE with our high-throughput DNA-to-protein alignment tool DIAMOND and by providing a new program MeganServer that allows access to metagenome analysis files hosted on a server, we provide a straightforward, yet powerful and complete pipeline for the analysis of metagenome shotgun sequences. We illustrate how to perform a full-scale computational analysis of a metagenomic sequencing project, involving 12 samples and 800 million reads, in less than three days on a single server. All source code is available here: https://github.com/danielhuson/megan-ce

/pdf/megan-community-edition-interactive-exploration-and-analysis-4sr8x52dk7.pdf

MEGAN Community Edition - Interactive Exploration and Analysis of Large-Scale Microbiome Sequencing Data

C4.5: Programs for Machine Learning (書評)

Model Predictive Control (MPC), the dominant advanced control approach in industry over the past twenty-five years, is presented comprehensively in this unique book. With a simple, unified approach, and with attention to real-time implementation, it covers predictive control theory including the stability, feasibility, and robustness of MPC controllers. The theory of explicit MPC, where the nonlinear optimal feedback controller can be calculated efficiently, is presented in the context of linear systems with linear constraints, switched linear systems, and, more generally, linear hybrid systems. Drawing upon years of practical experience and using numerous examples and illustrative applications, the authors discuss the techniques required to design predictive control laws, including algorithms for polyhedral manipulations, mathematical and multiparametric programming and how to validate the theoretical properties and to implement predictive control policies. The most important algorithms feature in an accompanying free online MATLAB toolbox, which allows easy access to sample solutions. Predictive Control for Linear and Hybrid Systems is an ideal reference for graduate, postgraduate and advanced control practitioners interested in theory and/or implementation aspects of predictive control.

Predictive Control for Linear and Hybrid Systems

http://sisdin.unipv.it/lab/personale/pers_hp/ferrari/files/idpwa-auto_2.pdf

A clustering technique for the identification of piecewise affine systems

https://homes.di.unimi.it/~valentini/papers/bag-svm-cancer-letter-revised.pdf

Cancer recognition with bagged ensembles of support vector machines

Jordan recurrent neural network versus IHACRES in modelling daily streamflows

The generation of a set of rules underlying a classification problem is performed by applying a new algorithm called Hamming Clustering (HC). It reconstructs the AND-OR expression associated with any Boolean function from a training set of samples. The basic kernel of the method is the generation of clusters of input patterns that belong to the same class and are close to each other according to the Hamming distance. Inputs which do not influence the final output are identified, thus automatically reducing the complexity of the final set of rules. The performance of HC has been evaluated through a variety of artificial and real-world benchmarks. In particular, its application in the diagnosis of breast cancer has led to the derivation of a reduced set of rules solving the associated classification problem.

http://ftp.it.murdoch.edu.au/units/ICT219/Papers%20for%20transfer/papers%20on%20Clustering/Binary%20Rule%20Generation.pdf

Binary rule generation via Hamming Clustering

We focus on the identification of discrete time hybrid systems in the piecewise affine (PWA) form. This problem can be formulated as the reconstruction of a possibly discontinuous PWA map with a multidimensional domain. In order to achieve our goal, we propose an algorithm that exploits the combined use of clustering, linear identification, and classification techniques. This allows one to identify both the affine sub-models and the polyhedral partition of the domain on which each submodel is valid.

/pdf/identification-of-piecewise-affine-and-hybrid-systems-1mghs38lx0.pdf

Marco Muselli

Papers

A clustering technique for the identification of piecewise affine systems

Cancer recognition with bagged ensembles of support vector machines

Jordan recurrent neural network versus IHACRES in modelling daily streamflows

Binary rule generation via Hamming Clustering

Identification of piecewise affine and hybrid systems