Text classification is one of the most widely studied task in natural language processing. Recently, larger and larger multilayer neural network models are employed for the task motivated by the principle of compositionality. Almost all of the methods reported use discriminative approaches for the task. Discriminative approaches come with a caveat that if there is no proper capacity control, it...

media (including books, newspapers & journals/magazines) is one of the most important elements in construction & institutionalization of modern identity. this paper will survey the role and importance of newspapers/journals in the national identity construct. for explaining the relations between these two variables, the following issues will be considered: • the construction of modern national ...

A wide range of complex systems can be modeled as networks with corresponding constraints on the edges and nodes, which have been extensively studied in recent years. Nowadays, with the progress of information technology, systems that contain the information collected from multiple perspectives have been generated. The conventional models designed for single perspective networks fail to depict ...

In this paper we propose and analyze a multilayer perceptron-like model with matrix inputs. We applied the proposed model to the financial time series prediction problem, compared it with the standard multilayer perceptron model, and got fairly good results.

Starting from a field theoretical description of multicomponent anyons with mutual statistical interactions in the lowest Landau level, we construct a model of interacting chiral fields on the circle, with the energy spectrum characterized by a symmetric matrix gαβ with nonnegative entries. Being represented in a free form, the model provides a field theoretical realization of (ideal) fractiona...

The use of decision support systems in agriculture may help monitoring large fields of crops by automatically detecting the symptoms of foliage diseases. In our work, we designed and implemented a decision support system for small tomatoes producers. This work investigates ways to recognize the late blight disease from the analysis of digital images of tomatoes, using a pair of multilayer perce...

Recent studies have investigated the photomechanical properties of carbon nanotubes which can be utilized to construct optical actuators. In this paper we compare the photomechanical response from single-wall and multi-wall carbon nanotube/polymer systems in multilayer and nanocomposite actuator constructions. Incorporating polymers in the actuators, single-wall and multi-wall nanotubes show si...

Synchronous neural activity can improve neural processing and is believed to mediate neuronal interaction by providing temporal windows during which information is more easily transferred. We demonstrate a pulse gating mechanism in a feedforward network that can exactly propagate graded information through a multilayer circuit. Based on this mechanism, we present a unified framework wherein neu...

Imaging systems that construct an image from phase information in received signals include synthetic aperture radar (SAR) and optical Doppler tomography (ODT) systems. A fundamental problem in the image formation is phase ambiguity; i.e. it is impossible to distinguish between phases that differ by 2π. Phase unwrapping in two dimensions essentially consists of detecting the pixel locations of t...

A rapid and simple fabrication method to construct tiny shadow-masks and their use in multi-layer surface patterning with in-situ micromechanical alignment is presented. Free-standing shadow-mask membranes are made of a 5-μm-thick SU-8 based resist layer by photolithography. They are supported by a 1-mm-large and 150-μm-thick SU-8 rim. The membrane has apertures with feature sizes ranging from ...