There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

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

Deposits of clastic carbonate-dominated (calciclastic) sedimentary slope systems in the rock record have been identified mostly as linearly-consistent carbonate apron deposits, even though most ancient clastic carbonate slope deposits fit the submarine fan systems better. Calciclastic submarine fans are consequently rarely described and are poorly understood. Subsequently, very little is known especially in mud-dominated calciclastic submarine fan systems. Presented in this study are a sedimentological core and petrographic characterisation of samples from eleven boreholes from the Lower Carboniferous of Bowland Basin (Northwest England) that reveals a >250 m thick calciturbidite complex deposited in a calciclastic submarine fan setting. Seven facies are recognised from core and thin section characterisation and are grouped into three carbonate turbidite sequences. They include: 1) Calciturbidites, comprising mostly of highto low-density, wavy-laminated bioclast-rich facies; 2) low-density densite mudstones which are characterised by planar laminated and unlaminated muddominated facies; and 3) Calcidebrites which are muddy or hyper-concentrated debrisflow deposits occurring as poorly-sorted, chaotic, mud-supported floatstones. These

Phd by thesis

Today's Web-enabled deluge of electronic data calls for automated methods of data analysis. Machine learning provides these, developing methods that can automatically detect patterns in data and then use the uncovered patterns to predict future data. This textbook offers a comprehensive and self-contained introduction to the field of machine learning, based on a unified, probabilistic approach. The coverage combines breadth and depth, offering necessary background material on such topics as probability, optimization, and linear algebra as well as discussion of recent developments in the field, including conditional random fields, L1 regularization, and deep learning. The book is written in an informal, accessible style, complete with pseudo-code for the most important algorithms. All topics are copiously illustrated with color images and worked examples drawn from such application domains as biology, text processing, computer vision, and robotics. Rather than providing a cookbook of different heuristic methods, the book stresses a principled model-based approach, often using the language of graphical models to specify models in a concise and intuitive way. Almost all the models described have been implemented in a MATLAB software package--PMTK (probabilistic modeling toolkit)--that is freely available online. The book is suitable for upper-level undergraduates with an introductory-level college math background and beginning graduate students.

Machine Learning : A Probabilistic Perspective

Data analysis plays an indispensable role for understanding various phenomena. Cluster analysis, primitive exploration with little or no prior knowledge, consists of research developed across a wide variety of communities. The diversity, on one hand, equips us with many tools. On the other hand, the profusion of options causes confusion. We survey clustering algorithms for data sets appearing in statistics, computer science, and machine learning, and illustrate their applications in some benchmark data sets, the traveling salesman problem, and bioinformatics, a new field attracting intensive efforts. Several tightly related topics, proximity measure, and cluster validation, are also discussed.

/pdf/survey-of-clustering-algorithms-6zezqhbjyo.pdf

Survey of clustering algorithms

A compressed full-text self-index for a text T is a data structure requiring reduced space and able of searching for patterns P in T. Furthermore, the structure can reproduce any substring of T, thus it actually replaces T. Despite the explosion of interest on self-indexes in recent years, there has not been much progress on search functionalities beyond the basic exact search. In this paper we focus on indexed approximate string matching (ASM), which is of great interest, say, in computational biology applications. We present an ASM algorithm that works on top of a Lempel-Ziv self-index. We consider the so-called hybrid indexes, which are the best in practice for this problem. We show that a Lemplel-Ziv index can be seen as an extension of the classical q-samples index. We give new insights on this type of index, which can be of independent interest, and then apply them to the Lempel-Ziv index. We show experimentally that our algorithm has a competitive performance and provides a useful space-time tradeoff compared to classical indexes.

/pdf/approximate-string-matching-with-lempel-ziv-compressed-1c6ztp20y3.pdf

Approximate string matching with Lempel-Ziv compressed indexes

Due to the rapid growth in digital storage technologies, Information Retrieval (IR) has gained a significant importance, both for academia and for the industry. However, very few proposals have been made for the creation of an environment capable of both providing useful IR services and acting as a workbench for the design, implementation, and research of new IR solutions. In this work, we propose IR-BASE, a basic object oriented framework for the integration of components, documentation and services, focused on the rapid development of prototypes for research and teaching. At its core, IR-BASE consists of a set of base classes that provide a skeleton to create new IR components, a set of guidelines to ensure that the developed components are fully interoperable, and a component pool, where IR-BASE users can find implementations of all kinds of functionalities needed to build a full IR system, and to which IR-BASE users can contribute with their own implementations. IR-BASE is of interest not only to IR researchers and professionals, who want to rapidly develop prototypes to test new ideas, but also to teachers and students, who will have an easily configurable, modifiable and extendible set of components to act has a basis for learning, building and experimenting with current IR algorithms.

http://web.ist.utl.pt/acardoso/docs/2007-TLIR-IR-BASE-handout.pdf

IR-BASE: An integrated framework for the research and teaching of information retrieval technologies

We address the problem of selecting the minimum sized finite state machine consistent with given input/output samples. The problem can be solved by computing the minimum finite state machine equivalent to a finite state machine without loops obtained from the training set. We compare the performance of four algorithms for this task: two algorithms for incompletely specified finite state machine reduction, an algorithm based on a well known explicit search procedure and an algorithm based on a new implicit search procedure that is introduced in this paper.

Limits of Exact Algorithms For Inference of Minimum Size Finite State Machines

We present a new search procedure for approximate string matching over suffix trees. We show that hierarchical verification, which is a well-established technique for on-line searching, can also be used with an indexed approach. For this, we need that the index supports bidirectionality, meaning that the search for a pattern can be updated by adding a letter at the right or at the left. This turns out to be easily supported by most compressed text self-indexes, which represent the index and the text essentially in the same space of the compressed text alone. To complete the symbiotic exchange, our hierarchical verification largely reduces the need to access the text, which is expensive in compressed text self-indexes. The resulting algorithm can, in particular, run over an existing fully compressed suffix tree, which makes it very appealing for applications in computational biology. We compare our algorithm with related approaches, showing that our method offers an interesting space/time tradeoff, and in particular does not need of any parameterization, which is necessary in the most successful competing approaches.

/pdf/indexed-hierarchical-approximate-string-matching-5g97n8s0mp.pdf

Indexed Hierarchical Approximate String Matching

The human interaction through the web generates both implicit and explicit knowledge. An example of an implicit contribution is searching, as people contribute with their knowledge by clicking on retrieved documents. When this information is available, an important and interesting challenge is to extract relations from query logs, and, in particular, semantic relations between queries and their terms. In this paper, we present and discuss results on query contextualization through the association of tags to queries, that is, query folksonomies. Note that tags may not even occur within the query. Our results rely on the analysis of large query log induced graphs, namely click induced graphs. Results obtained with real data show that the inferred query folksonomy provide interesting insights both on semantic relations among queries and on web users intent.Copyright © 2011 John Wiley & Sons, Ltd.

(Work done while visiting Yahoo! Research Barcelona.)

/pdf/mining-query-log-graphs-towards-a-query-folksonomy-kwsw8l4388.pdf

Arlindo L. Oliveira

Papers

Approximate string matching with Lempel-Ziv compressed indexes

IR-BASE: An integrated framework for the research and teaching of information retrieval technologies

Limits of Exact Algorithms For Inference of Minimum Size Finite State Machines

Indexed Hierarchical Approximate String Matching

Mining query log graphs towards a query folksonomy