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

Data Mining Practical Machine Learning Tools and Techniques

The modern science of networks has brought significant advances to our understanding of complex systems. One of the most relevant features of graphs representing real systems is community structure, or clustering, i. e. the organization of vertices in clusters, with many edges joining vertices of the same cluster and comparatively few edges joining vertices of different clusters. Such clusters, or communities, can be considered as fairly independent compartments of a graph, playing a similar role like, e. g., the tissues or the organs in the human body. Detecting communities is of great importance in sociology, biology and computer science, disciplines where systems are often represented as graphs. This problem is very hard and not yet satisfactorily solved, despite the huge effort of a large interdisciplinary community of scientists working on it over the past few years. We will attempt a thorough exposition of the topic, from the definition of the main elements of the problem, to the presentation of most methods developed, with a special focus on techniques designed by statistical physicists, from the discussion of crucial issues like the significance of clustering and how methods should be tested and compared against each other, to the description of applications to real networks.

/pdf/community-detection-in-graphs-34rogm3r6p.pdf

Community detection in graphs

Statistics for Spatial Data.

A method and apparatus that enables approximate packet classification by using both an exact packet classification method and an inexact packet classification method are disclosed. For example, the method filters a plurality of packets using an exact packet classification method when a processing load is below or equal to a threshold, and filters the plurality of packets by dynamically switching between the exact packet classification method and an inexact packet classification method when the processing load is above the threshold.

Method and apparatus for filtering packets using an approximate packet classification

A communication network is operated by identifying at least one potential hijack autonomous system (AS) that can be used to generate a corrupt routing path from a source AS to a destination AS. For each of the at least one potential hijack AS the following operations are performed: identifying at least one regional AS that is configured to adopt the corrupt routing path from the source AS to the destination AS and determining a reflector AS set such that, for each reflector AS in the set, a source AS to reflector AS routing path and a reflector AS to destination AS routing path do not comprise any of the at least one regional AS. A reflector AS is then identified that is common among the at least one reflector AS set responsive to performing the identifying and determining operations for each of the at least one potential hijack AS.

Methods, systems, and computer program products for protecting against ip prefix hijacking

Most important commercial Web sites maintain multiple replicas of their server infrastructure to increase both reliability and performance. In this paper, we study how many replicas should be used and where they should be placed in order to improve client network performance, including both the latency (e.g., round-trip time) between clients and the replicas, and the bandwidth performance between them. This study is based on a large scale measurement study from an 18-node infrastructure, which reveals for the first time the distribution of today's Internet end-user access bandwidth. For example, we find that 50% of end users have access bandwidth less than 4.2Mbps. Using a greedy algorithm, we show that the first five replicas dominate latency optimization in our measurement infrastructure, while the first two replicas dominate bandwidth optimization. We also found that geographic diversity does not help as much for bandwidth optimization as it does for latency. To determine the proper trade-off between latency and bandwidth, we use a simplified TCP model to show that, when content size is less than 10Kb, the deployment should focus on optimizing latency, while for content sizes larger than 1 Mb, the deployment should focus on optimizing bandwidth.

/pdf/optimizing-network-performance-in-replicated-hosting-toczvy08ht.pdf

Optimizing network performance in replicated hosting

Despite its importance in today's Internet, network measurement was not an integral part of the original Internet architecture, i.e., there was (and still is) little native support for many essential measurement tasks. Targeting the inadequacy of counting/accounting capabilities of existing routers, many data streaming and sketching techniques have been proposed to estimate the important statistics of traffic going through a network link. Most of these techniques are, however, developed to track one specific statistic and/or answer a specific type of query. Since there are a large number of such statistics and queries of interest, it is very difficult, if not impossible, for network vendors and operators to implement and deploy data streaming/sketching solutions for all of them, due to router resource (memory, CPU, bus bandwidth, etc.) constraints.

In this paper, we propose a general-purpose solution that can not only answer a wide range of queries, but also be able to answer types of queries that were not known a priori. In particular, we introduce the use of the Conditional Random Sampling (CRS) sketch data structure for succinctly capturing network traffic data between a set of nodes in the network. This sketch is the first step towards a "universal" sketch data structure in the sense that it is not tied to measurement of a single quantity. We show that the CRS sketch can compute unbiased estimates for any linear summary statistic in the intersection of a pair of traffic streams, e.g., traffic and flow matrix information, flow counts, and entropy. We present detailed experiments, using data collected at a tier-1 ISP, that show that our sketch is capable of estimating this wide range of statistics with fairly high accuracy.

/pdf/towards-a-universal-sketch-for-origin-destination-network-451tc0yper.pdf

Towards a universal sketch for origin-destination network measurements

A mechanism is provided for predicting video engagement from network measurements for a user device connected to a wireless network. Wireless network measurements are retrieved from a wireless network device in the wireless network. The wireless network measurements are related to the user device of a user. It is determined that the user device is engaged in a video streaming session. A computer classifies the video streaming session as one of a plurality of classes, in which the plurality of classes predict an outcome of the video streaming session for the user device.

Jia Wang

Papers

Method and apparatus for filtering packets using an approximate packet classification

Methods, systems, and computer program products for protecting against ip prefix hijacking

Optimizing network performance in replicated hosting

Towards a universal sketch for origin-destination network measurements

Predicting video engagement from wireless network measurements