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

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

A new aspect of cell membrane structure is presented, based on the dynamic clustering of sphingolipids and cholesterol to form rafts that move within the fluid bilayer. It is proposed that these rafts function as platforms for the attachment of proteins when membranes are moved around inside the cell and during signal transduction.

Functional rafts in cell membranes

We will review some of the major results in random graphs and some of the more challenging open problems. We will cover algorithmic and structural questions. We will touch on newer models, including those related to the WWW.

Random graphs

We propose a distributed VNT control method in IP over WDM networks. Our method is based on a dynamical system that models behavior where living organisms adapt to unknown changes in their surrounding environments and recover their conditions, and reduces computational overhead from previously proposed method. Evaluation results show that the method is as adaptive to traffic changes as previously proposed method.

A Distributed Control of Virtual Network Topologies by Using Attractor Selection Model

Performance Evaluation of Distributed Computing Environment Considering Power Consumption

SUMMARY Overlay networks, such as P2P, Grid, and CDN, have been widely deployed over physical IP networks. Since simultaneous overlay networks compete for network resources, their selfish behaviors to improve their application-oriented QoS disrupt each other. To enhance the collective performance and improve the QoS at the application level, we consider so-called the overlay network symbiosis where overlay networks cooperate with each other. In this paper, we proposed a cooperative mechanism for hybrid P2P file-sharing networks, where peers can find more files and exchange files with more peers. Through simulation experiments, we verified the effectiveness of cooperation from view points of application and system.

A Cooperative Mechanism for Hybrid P2P File-Sharing Networks to Enhance Application-Level QoS

In wireless sensor networks used as a social infrastructure, urgent information, such as a fire alarm, is needed to be transmitted as fast and reliably as possible. In this paper, we propose design methodology for a sensor network which provides preferential control of urgent information over other non-urgent information. In our methodology, several simple mechanisms which function in different spatial and temporal levels are introduced on each node and they work autonomously and independently as a reaction to the surrounding situation. We also show an example of a network architecture designed following the methodology. Our simulation experiments showed that the architecture successfully improved the delivery ratio and delay of the urgent sensor information.

Designing a sensor network architecture for transmission of urgent sensor information

Spatial composition method for end-to-end network measurement avoids lengthy measurements of a path and the path is divided into some sub-paths when multiple measured paths share the underlay network route. The performance of the overall path is estimated by spatially composing measurement results of the sub-paths. This method is quite effective for measurement in overlay networks where many paths between overlay nodes share the underlay network. However, such estimation methods may include the additional errors caused by the measurement inaccuracy of sub-paths. Therefore, we need to assess the estimation accuracy of the spatial composition-based method and introduce statistical processing to suppress the estimation errors. In this paper, we propose statistical processing methods of measurement results to improve estimation accuracy of spatial composition-based measurement method for packet loss ratio. We introduce a statistical test for measurement results to exclude outliers from spatial composition. We also propose some statistical indexes for determining whether we should discard the measurement results and reconduct the measurement. We evaluate the performance of the proposed method by using measurement results obtained on Planet Lab environment. From the evaluation results we find that proposed two methods can decrease the estimation error of the spatial composition of packet loss ratio by 36% and 23%, respectively.

Masayuki Murata

Papers

A Distributed Control of Virtual Network Topologies by Using Attractor Selection Model

Performance Evaluation of Distributed Computing Environment Considering Power Consumption

A Cooperative Mechanism for Hybrid P2P File-Sharing Networks to Enhance Application-Level QoS

Designing a sensor network architecture for transmission of urgent sensor information

Accuracy Improvement for Spatial Composition-Based End-to-End Network Measurement