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

From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

General Topology-I

A recent paper posed the question: "Graph Matching: What are we really talking about?". Far from providing a definite answer to that question, in this paper we will try to characterize the role that graphs play within the Pattern Recognition field. To this aim two taxonomies are presented and discussed. The first includes almost all the graph matching algorithms proposed from the late seventies, and describes the different classes of algorithms. The second taxonomy considers the types of common applications of graph-based techniques in the Pattern Recognition and Machine Vision field.

/pdf/thirty-years-of-graph-matching-in-pattern-recognition-58lvpdkcaj.pdf

Thirty years of graph matching in pattern recognition

Titanium dioxide is a key material in many fields, including technological, industrial and biomedical applications. Many of these applications are related to the surface reactivity of TiO2 and involve its reducibility properties. Recently titania has been banned as a food additive due to its (nano)toxicity, and the release of reactive oxygen species plays a crucial role in many toxicological mechanisms. Determining chemical descriptors that account for the extension of reduction is necessary to understand such processes and necessary for predicting the reactivity of an unknown system. In the present work, we compute a set of chemical descriptors for selected surfaces of anatase and rutile TiO2. The aim is twofold: we want to provide chemically meaningful information on the surface reactivity, and benchmark the descriptors for two ab initio schemes. To do so, we compute the oxygen vacancy formation energy, and the corresponding electronic structure, in four slab models with two different computational schemes (DFT+U and DFTB). In this way, we characterize the robustness of the dataset, with the purpose of scaling up to more realistic model systems such as nanoparticles or explicit solvent, which are too computationally demanding for state-of-the-art density functional theory approaches.

Analyzing the TiO2 surface reactivity based on oxygen vacancies computed by DFT and DFTB methods

Alignment of point sets is frequently used in pattern recognition when objects are represented by sets of coordinate points. The idea behind this problem is to be able to compare two objects regardless of the effect of a given transformation on their coordinate data. This paper presents a method to align point sets based on the graph edit distance. The main idea is to learn the edit costs (in a learning step) and then apply graph edit distance (in a pattern recognition step) with the learned edit costs. Thus, the edit cost would have to incorporate the transformation parameters. In the experimental section, we show that the method is competitive if the graph edit distance parameters are automatically learned considering the learning set. These parameters are the insertion and deletion costs and also the weights on the substitution costs.

Learning the Graph Edit Distance Parameters for Point-Set Image Registration

This article presents the current trends on wheeled mobile robotics being pursued at IRI-UPC-CSIC. It includes an overview of recent results produced in our group in a wide range of areas, including robot localization, color invariance, segmentation, tracking, visual servoing, and object and face recognition.

/pdf/learning-and-vision-mobile-robotics-group-research-report-1vw9imalzc.pdf

Francesc Serratosa

Papers

Analyzing the TiO2 surface reactivity based on oxygen vacancies computed by DFT and DFTB methods

Learning the Graph Edit Distance Parameters for Point-Set Image Registration

Learning and vision mobile robotics group research report 2002-2003

Graph Regression Based on Graph Autoencoders

A commentary on “Learning error-correcting graph matching with a multiclass neural network”, Pattern Recognition Letters, 2018