Publisher Summary This chapter provides an account of different neural network architectures for pattern recognition. A neural network consists of several simple processing elements called neurons. Each neuron is connected to some other neurons and possibly to the input nodes. Neural networks provide a simple computing paradigm to perform complex recognition tasks in real time. The chapter categorizes neural networks into three types: single-layer networks, multilayer feedforward networks, and feedback networks. It discusses the gradient descent and the relaxation method as the two underlying mathematical themes for deriving learning algorithms. A lot of research activity is centered on learning algorithms because of their fundamental importance in neural networks. The chapter discusses two important directions of research to improve learning algorithms: the dynamic node generation, which is used by the cascade correlation algorithm; and designing learning algorithms where the choice of parameters is not an issue. It closes with the discussion of performance and implementation issues.

Neural Networks for Pattern Recognition

http://www.maths.qmul.ac.uk/%7Elatora/report_06.pdf

Complex networks: Structure and dynamics

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

Cause, conseguenze e strategie di mitigazione Proponiamo il primo di una serie di articoli in cui affronteremo l’attuale problema dei mutamenti climatici. Presentiamo il documento redatto, votato e pubblicato dall’Ipcc - Comitato intergovernativo sui cambiamenti climatici - che illustra la sintesi delle ricerche svolte su questo tema rilevante.

/pdf/climate-change-2007-the-physical-science-basis-1x93ttz9jt.pdf

Climate Change 2007: The Physical Science Basis.

Statistical physics has proven to be a fruitful framework to describe phenomena outside the realm of traditional physics. Recent years have witnessed an attempt by physicists to study collective phenomena emerging from the interactions of individuals as elementary units in social structures. A wide list of topics are reviewed ranging from opinion and cultural and language dynamics to crowd behavior, hierarchy formation, human dynamics, and social spreading. The connections between these problems and other, more traditional, topics of statistical physics are highlighted. Comparison of model results with empirical data from social systems are also emphasized.

Statistical physics of social dynamics

A contribution to the JASSS forum, in reaction to the paper in FASZ about our model of extremism

Simple is beautiful ... and necessary.

We study damage propagation in networks, with an emphasis on production-chain models. The models are formulated as systems of Boolean delay equations. This formalism helps take into account the complexity of the interactions between firms; it turns out to be well adapted to investigating propagation of an initial damage due to a climatic or other natural disaster. We consider in detail the effects of distinct delays and forcing, which represent external intervention to prevent economic collapse. We also account for the possible presence of randomness in the links and the delays. The paper concentrates on two different network structures, periodic and random, respectively; their study allows one to understand the effects of multiple, concurrent production paths, and the role played by the network topology in damage propagation. Applications to the recent network modeling of climate variability are discussed.

/pdf/boolean-delay-equations-on-networks-in-economics-and-the-32ok04b62h.pdf

Boolean delay equations on networks in economics and the geosciences

We discuss the influence of information contagion on the dynamics of choices in social networks of heterogeneous buyers. Starting from an inhomogeneous cellular automata model of buyers dynamics, we show that when agents try to adjust their reservation price, the tatonement process does not converge to equilibrium at some intermediate market share and that large amplitude fluctuations are actually observed. When the tatonnement dynamics is slow with respect to the contagion dynamics, large periodic oscillations reminiscent of business cycles appear.

Adjustment and social choice

There are clear benefits associated with a particular consumer choice for many current markets. For example, as we consider here, some products might carry environmental or `green' benefits. Some consumers might value these benefits while others do not. However, as evidenced by myriad failed attempts of environmental products to maintain even a niche market, such benefits do not necessarily outweigh the extra purchasing cost. The question we pose is, how can such an initially economically-disadvantaged green product evolve to hold the greater share of the market? We present a simple mathematical model for the dynamics of product competition in a heterogeneous consumer population. Our model preassigns a hierarchy to the products, which designates the consumer choice when prices are comparable, while prices are dynamically rescaled to reflect increasing returns to scale. Our approach allows us to model many scenarios of technology substitution and provides a method for generalizing market forces. With this model, we begin to forecast irreversible trends associated with consumer dynamics as well as policies that could be made to influence transitions

Heterogeneity and Increasing Returns May Drive Socio-Economic Transitions

Jerne (1974) proposed that the immune system has important network characteristics
that are similar in many respects to neural networks. This paper outlines some recent
approaches taken by the authors and their colleagues toward the analysis of immune
networks. Other approaches have been omitted owing to space limitations, notably
that of Coutinho, Stewart, and Varela.

/pdf/recent-approaches-to-immune-networks-4fii7gd996.pdf

Gérard Weisbuch

Papers

Simple is beautiful ... and necessary.

Boolean delay equations on networks in economics and the geosciences

Adjustment and social choice

Heterogeneity and Increasing Returns May Drive Socio-Economic Transitions

Recent approaches to immune networks