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

In this article, we introduce two new organizations for IT (information technology)-related research and development at Osaka University. One is the Cybermedia Center, started in April 2000, which plays the role of a strategic center of information-related technology for supporting research and educational activities carried out at Osaka University. The other is a new graduate school for information-related education and research, called the Graduate School of Information Science and Technology, which was planned to start in April 2002. We introduce the missions, roles and current status of these new organizations.

New organizations for IT-related R&D at Osaka University

Nowadays, Linked Open Data is spreading year by year, and its further utilization is expected. Since the size of the data is large, Linked Open Data is attempted to learn by using neural networks. Since the data is still scaling in various region, unlike the existing neural network specialized to learn only one region, a neural network which can continuously learn wide region of knowledge is needed. However, neural network is known in its problem, catastrophic forgetting, which is to lose previously acquired skills when learning a new skill. In this research, we approach catastrophic forgetting from modularity, which is said to exist in human's brain functional network. It is true that there are many previous researches in catastrophic forgetting of neural network, however, most of the research need to know the number of learning tasks in advance, so that it is not applicable for continuously learning wide region of knowledge. The basic idea of our design approach is to design a neural network with multiple learning subsets only considering modularity without considering the number of tasks. In the evaluation, we evaluated not only for tasks learned just before, but also for tasks learned a while before. Our results show that, although, as we can expected, a neural network with high modularity can mitigate forgetting for tasks learned just before because of the low interference, a neural network with low modularity is better for the worst case when evaluating for all the tasks it learned in the past.

Mitigate catastrophic forgetting for continuously learning linked open data using modularity

This method for producing a Cas9-gRNA complex is provided with a step for mixing Cas9 and gRNA at 20°C or higher to form a Cas9-gRNA complex, the gRNA including a polynucleotide that comprises a base sequence complementary to a base sequence from 1 base upstream to 20-24 bases upstream of the PAM sequence in the target gene. This method for introducing a Cas9-gRNA complex into a cell nucleus is provided with: a step for causing a streptococcal enzyme-sensitive toxin streptolysin O to act on the plasma membrane of a cell to form pores in at least part of the plasma membrane; a step for introducing a Cas9-gRNA complex obtained by the above method for producing a Cas9-gRNA complex into the cell in which pores have been formed in at least part of the plasma membrane; and a step for adding a solution that includes calcium ions to the cell in which pores have been formed in at least part of the plasma membrane and into which the Cas9-gRNA complex has been introduced, and resealing the pores formed in at least part of the plasma membrane.

Method for producing cas9-grna complex, method for introducing cas9-grna complex into cell nucleus, and method for modifying target gene in cell

OoS Guarantees for Multimedia Computer Networks

With the development of low-cost microsensor equipment having the capability of wireless communications, sensor network technology has attracted the attention of many researchers and developers. By deploying a large number of sensors in a monitored region and composing a sensor network of them, one can remotely obtain information on behavior, condition, and position of elements in the region. In [1], we have proposed a novel and efficient scheme for data gathering in sensor networks where a large number of sensor nodes were deployed. In such networks, nodes are randomly introduced, occasionally die or get removed, and sometimes change their locations. We considered an application that periodically collected sensor information from distributed sensor nodes to a base station. In our scheme, sensor information periodically propagates without any centralized control from the edge of a sensor network to a base station as the propagation forms a concentric circle. By observing the radio signals emitted by sensor nodes in its vicinity, a sensor node independently determines the cycle

Masayuki Murata

Papers

New organizations for IT-related R&D at Osaka University

Mitigate catastrophic forgetting for continuously learning linked open data using modularity

Method for producing cas9-grna complex, method for introducing cas9-grna complex into cell nucleus, and method for modifying target gene in cell

OoS Guarantees for Multimedia Computer Networks

Implementation and evaluation of scalable and robust scheme for data gathering in wireless sensor networks