The Internet makes it possible to share and manipulate a vast quantity of information efficiently and effectively, but the rapid and chaotic growth experienced by the Net has generated a poorly organized environment that hinders the sharing and mining of useful data. The need for meaningful web-page classification techniques is therefore becoming an urgent issue. This paper describes a novel ap...

Casting neural network weights in symbolic terms is crucial for interpreting and explaining the behavior of a network. Additionally, in some domains, a symbolic description may lead to more robust generalization. We present a principled approach to symbolic rule extraction based on the notion of weight templates, parameterized regions of weight space corresponding to specific symbolic expressio...

We introduce a weight update formula that is expressed only in terms of firing rates and their derivatives and that results in changes consistent with those associated with spike-timing dependent plasticity (STDP) rules and biological observations, even though the explicit timing of spikes is not needed. The new rule changes a synaptic weight in proportion to the product of the presynaptic firi...

This study aimed to examine the relative effect of feedback and operational experience on children's rule learning in a balance scale task, in which 88 children under the age of 7 years were asked to judge the state of equilibrium under four conditions. In the Control condition, children were required to observe the scale and predict which side would tilt down or keep balance, without feedback ...

The relationship between spatial density and size of plants is an important topic in plant ecology. The self-thinning rule suggests a -3/2 power between average biomass and density or a -1/2 power between stand yield and density. However, the self-thinning rule based on total leaf area per plant and density of plants has been neglected presumably because of the lack of a method that can accurat...

An approach is presented to multi-expert’s opinions combination based on the Dempster-Shafer evidence theory. In the method, we use multi-expert’s knowledge as evidence, the possible value of weight as frame of discernment, expert’s evaluation to a weight on frame of discernment as basic probability assignment, and use D-S rule combining to give fusion basic probability assignment m. Finally, t...

This dissertation consists of three essays organized as chapters. On the first chapter, I revisit the discussions which evaluate different fluctuations of major economic variables produced by different monetary policy rules for small open economies, given the existence of liability dollarization. In particular, monetary rules which either include or exclude exchange rate stability as a monetary...