A Connection Between GRBF and MLP

Both multilayer perceptrons (MLP) and Generalized Radial Basis Functions (GRBF) have good approximation properties, theoretically and experimentally. Are they related? The main point of this paper is to show that for normalized inputs, multilayer perceptron networks are radial function networks (albeit with a non-standard radial function). This provides an interpretation of the weights w as centers t of the radial function network, and therefore as equivalent to templates. This insight may be useful for practical applications, including better initialization procedures for MLP. In the remainder of the paper, we discuss the relation between the radial functions that correspond to the sigmoid for normalized inputs and well-behaved radial basis functions, such as the Gaussian. In particular, we observe that the radial function associated with the sigmoid is an activation function that is good approximation to Gaussian basis functions for a range of values of the bias parameter. The implication is that a MLP network can always simulate a Gaussian GRBF network (with the same number of units but less parameters); the converse is true only for certain values of the bias parameter. Numerical experiments indicate that this constraint is not always satisfied in practice by MLP networks trained with backpropagation. Multiscale GRBF networks, on the other hand, can approximate MLP networks with a similar number of parameters.

Dynamical Systems in the Sensorimotor Loop: On the Interrelation Between Internal and External Mechanisms of Evolved Robot Behavior

Huelse, M., Wischmann, S., Manoonpong, P., Twickel, A.v., Pasemann, F.: Dynamical Systems in the Sensorimotor Loop: On the Interrelation Between Internal and External Mechanisms of Evolved Robot Behavior. In: M. Lungarella, F. Iida, J. Bongard, R. Pfeifer (Eds.) 50 Years of Artificial Intelligence, LNCS 4850, Springer, 186 - 195, 2007.

Internal War, International Mediation and Non-Official Diplomacy: Lessons from Mozambique

Jackson, R. (2005). Internal War, International Mediation and Non-Official Diplomacy: Lessons from Mozambique. Journal of Conflict Studies. 25(1), pp.153-76 RAE2008

Internal structure of copper(II)-phthalocyanine thin films on SiO2/Si substrates investigated by grazing incidence x-ray reflectometry

Jenkins, Tudor; Brieva, A.C.; Jones, D.G.; Evans, D.A., (2006) 'Internal structure of copper(II)-phthalocyanine thin films on SiO2/Si substrates investigated by grazing incidence x-ray reflectometry', Journal of Applied Physics 99 pp.73504 RAE2008

Współpraca transgraniczna i regionalna w obszarze Morza Bałtyckiego w latach 1989 -2007

Wydział Nauk Politycznych i Dziennikarstwa

Geomorfologiczne uwarunkowania rozwoju sieci komunikacyjnej na obszarze młodoglacjalnym (zlewnia Perznicy, Pojezierze Drawskie

The aim of the studies in the Perznica River catchment were relief changes caused by the development of transportation infrastructure. This type of transformation is dependable on the state of economy and the settlements. The development of transportation network in the last two hundred years was examined through the analysis of archival cartographic materials – maps from the years 1789, 1855, 1877, 1935 – and the comparison with the situation from mid 1980s. The Perznica River catchment has an area of 249 km2 and it is located in north-western Poland in the central part of the Drawskie Lakeland macroregion, which belongs to the West Pomeranian Lakeland. The heterogeneous Perznica River catchment relief has a denivelation of 159 m and is within 60 and 219 m a.s.l. The study area is within the Parsęta River lobe. A number of subzones, whose morphological diversity and diversity of sediments lithofacies is mainly a reflection of areal deglaciation of the continental ice-sheet marginal zone, has been distinguished and these are: • subzone of the internal kame moraine – the undulated moraine upland, diversified by kame forms and kettle holes, • subzone of ice-free space forms – the uplands of kame plateaux, • subzone of melt-out lake basins – Lake Wielatowo basin with a characteristic collar ridge, • morphological levels of the northern Pomeranian sloping surface – mainly flat moraine uplands and small outwashes. The economic development of the Perznica River catchment advanced in close connection with the physical and geographical context, mainly with the relief, soils and hydrological conditions. As a result, the flat moraine uplands and marginal outflow plains, which were easiest to cultivate, have been developed and populated faster than any other. Since the early medieval period, large, compact villages, often centered around big estates, were emerging in those areas. In areas with a high relief energy–kame-melt moraines, ice-free space forms and ridges around melt-out lake basins–farming entered on a larger scale from the eighteenth century. Scattered settlements in those areas forced the creation of a dense access road network to farms and fields. In the case of anthropogenic forms of transportation with denivelation exceeding 1 m in the study area, road excavations are present for 37.3 km, road undercuttings for 43.8 km and road embankments for 38.7 km in total length. That gives a high ratio of density of such forms, equal to 2.1 km per km–2.

Inference and Labeling of Metric-Induced Network Topologies

The development and deployment of distributed network-aware applications and services over the Internet require the ability to compile and maintain a model of the underlying network resources with respect to (one or more) characteristic properties of interest. To be manageable, such models must be compact, and must enable a representation of properties along temporal, spatial, and measurement resolution dimensions. In this paper, we propose a general framework for the construction of such metric-induced models using end-to-end measurements. We instantiate our approach using one such property, packet loss rates, and present an analytical framework for the characterization of Internet loss topologies. From the perspective of a server the loss topology is a logical tree rooted at the server with clients at its leaves, in which edges represent lossy paths between a pair of internal network nodes. We show how end-to-end unicast packet probing techniques could b e used to (1) infer a loss topology and (2) identify the loss rates of links in an existing loss topology. Correct, efficient inference of loss topology information enables new techniques for aggregate congestion control, QoS admission control, connection scheduling and mirror site selection. We report on simulation, implementation, and Internet deployment results that show the effectiveness of our approach and its robustness in terms of its accuracy and convergence over a wide range of network conditions.

Connection Scheduling in Web Servers

Under high loads, a Web server may be servicing many hundreds of connections concurrently. In traditional Web servers, the question of the order in which concurrent connections are serviced has been left to the operating system. In this paper we ask whether servers might provide better service by using non-traditional service ordering. In particular, for the case when a Web server is serving static files, we examine the costs and benefits of a policy that gives preferential service to short connections. We start by assessing the scheduling behavior of a commonly used server (Apache running on Linux) with respect to connection size and show that it does not appear to provide preferential service to short connections. We then examine the potential performance improvements of a policy that does favor short connections (shortest-connection-first). We show that mean response time can be improved by factors of four or five under shortest-connection-first, as compared to an (Apache-like) size-independent policy. Finally we assess the costs of shortest-connection-first scheduling in terms of unfairness (i.e., the degree to which long connections suffer). We show that under shortest-connection-first scheduling, long connections pay very little penalty. This surprising result can be understood as a consequence of heavy-tailed Web server workloads, in which most connections are small, but most server load is due to the few large connections. We support this explanation using analysis.

Unicast-based Characterization of Network Loss Topologies

Current Internet transport protocols make end-to-end measurements and maintain per-connection state to regulate the use of shared network resources. When a number of such connections share a common endpoint, that endpoint has the opportunity to correlate these end-to-end measurements to better diagnose and control the use of shared resources. A valuable characterization of such shared resources is the "loss topology". From the perspective of a server with concurrent connections to multiple clients, the loss topology is a logical tree rooted at the server in which edges represent lossy paths between a pair of internal network nodes. We develop an end-to-end unicast packet probing technique and an associated analytical framework to: (1) infer loss topologies, (2) identify loss rates of links in an existing loss topology, and (3) augment a topology to incorporate the arrival of a new connection. Correct, efficient inference of loss topology information enables new techniques for aggregate congestion control, QoS admission control, connection scheduling and mirror site selection. Our extensive simulation results demonstrate that our approach is robust in terms of its accuracy and convergence over a wide range of network conditions.

An Independent-Connection Model for Traffic Matrices

A common assumption made in traffic matrix (TM) modeling and estimation is independence of a packet's network ingress and egress. We argue that in real IP networks, this assumption should not and does not hold. The fact that most traffic consists of two-way exchanges of packets means that traffic streams flowing in opposite directions at any point in the network are not independent. In this paper we propose a model for traffic matrices based on independence of connections rather than packets. We argue that the independent connection (IC) model is more intuitive, and has a more direct connection to underlying network phenomena than the gravity model. To validate the IC model, we show that it fits real data better than the gravity model and that it works well as a prior in the TM estimation problem. We study the model's parameters empirically and identify useful stability properties. This justifies the use of the simpler versions of the model for TM applications. To illustrate the utility of the model we focus on two such applications: synthetic TM generation and TM estimation. To the best of our knowledge this is the first traffic matrix model that incorporates properties of bidirectional traffic.