This paper introduces a hierarchical learning architecture that grows online an adaptive problem representation from scratch. The representation extracts frequent perceptual patterns representing them in a layered hierarchy where neural activity in higher layers is initiated bottom-up by firing neurons in lower layers and, vice versa, firing neurons in higher layers predispose activity and prov...

Agnieszka Czaplicka, Krzysztof Suchecki, Borja Minano, Miquel Trias, and Janusz A. Ho lyst 3 Faculty of Physics, Center of Excellence for Complex Systems Research, Warsaw University of Technology, Koszykowa 75, PL-00-662 Warsaw, Poland Institute for Applied Computing with Community Code (IAC) Universitat de les Illes Balears. Cra. Valldemossa km 7.5, E-07122, Palma, Spain Netherlands Institute ...

Current Address: GE Corporate Research and Development Schenectady, New York 12301 The hierarchical lexicon, in contrast to the traditional flat lexicon, enables a linguistic model to perform even in situations of incomplete knowledge: when a specific entry is missing, a more general entry can cover the gap. The question still remains regarding the construction of the lexicon itself. Since the ...

Structural hierarchy and complex 3D architecture are characteristics of biological photonic designs that are challenging to reproduce in synthetic materials. Top-down lithography allows for designer patterning of arbitrary shapes, but is largely restricted to planar 2D structures. Self-assembly techniques facilitate easy fabrication of 3D photonic crystals, but controllable defect-integration i...

Visualising objects of wildly differing scales, such as the contents of the Solar System, is a trade-off between accuracy and overview. The various existing solutions used in top-down games may have unwanted side effects on the resulting gameplay. We present a new solution based on treemaps placed in a spatial hierarchy that is capable of visualising these objects while maintaining the immersio...

This paper shows that classical results about complexity classes involving “delayed diagonalization” and “gap languages,” such as Ladner’s Theorem and Schöning’s Theorem and independence results of a kind noted by Schöning and Hartmanis, apply at very low levels of complexity, indeed all the way down in Sipser’s log-time hierarchy. This paper also investigates refinements of Sipser’s classes an...

Top-down attention is an essential cognitive ability, allowing our finite brains to process complex natural environments by prioritizing information relevant to our goals. Previous evidence suggests that top-down attention operates by modulating stimulus-evoked neural activity within visual areas specialized for processing goal-relevant information. We show that top-down attention also has a se...

In this paper we explore the hierarchical nature of tourism demand time series and produce short-term forecasts for Australian domestic tourism. The data and forecasts are organized in a hierarchy based on disaggregating the data for different geographical regions and for different purposes of travel. We consider five approaches to hierarchical forecasting: two variations of the top-down approa...

This talk reviews some recent results on the NLL resummed smallx gluon splitting function, as determined including renormalisation-group improvements. It also discusses the observation that the LO, NLO, NNLO, etc. hierarchy for the gluon splitting function breaks down not when αs ln 1/x ∼ 1 but rather for αs ln 2 1/x ∼ 1. It is well-known that the resummation of leading-logarithms of x (LLx) [1...