Improved SOM learning using simulated annealing

Self-Organizing Map (SOM) algorithm has been extensively used for analysis and classification problems. For this kind of problems, datasets become more and more large and it is necessary to speed up the SOM learning. In this paper we present an application of the Simulated Annealing (SA) procedure to the SOM learning algorithm. The goal of the algorithm is to obtain fast learning and better performance in terms of matching of input data and regularity of the obtained map. An advantage of the proposed technique is that it preserves the simplicity of the basic algorithm. Several tests, carried out on different large datasets, demonstrate the effectiveness of the proposed algorithm in comparison with the original SOM and with some of its modification introduced to speed-up the learning.

Ballet-Granite

Live Performance, Szuper Gallery + Curtain Razors Dur: 50 mins NTSC HD 2011 Direction/Conception - Susanne Clausen, Pavlo Kerestey, Michele Sereda Performance Installation - Susanne Clausen, Pavlo Kerestey Performers - Jason Cawood, Susanne Clausen, Blair Fornwald, Morgan Garneau, John Hampton, Pavlo Kerestey, Michele Sereda Cave Video - Susanne Clausen and Pavlo Kerestey Sound scape - Szuper Gallery Voice - Michele Sereda Ballet Band - Billy Hughes, Trent Mailander and Otis Young Music - Dance of the Spirits - Danilo Villalta Technical Direction - Kenneth Young Stage Management - Paul Crepeau Sound Support - Jeff Morton Structural Design Consultant - James Phillips and Caragana Production Design Inc Set Assistants - Rebbeca Donison and Shelby Lowe Headress - Alla Sidorenko Costume consultation - Dean Renwick Documentation, Still - Carey Shaw, Szuper Gallery Documentation, Moving - Gabriel Yahyahkeekoot Administration + PR - Carey Shaw and the Mackenzie Art Gallery Poster Design - Rio Saxon Design Produced by Curtain Razors and Szuper Gallery in collaboration with the Mackenzie Art Gallery with the support of the Canada Council for the Arts, the Saskatchewan Arts Board and the City of Regina Arts Advisory Committee.

The link between temporal attention and emotion: a playground for psychology, neuroscience, and plausible artificial neural networks

In this paper, we will address the endeavors of three disciplines, Psychology, Neuroscience, and Artificial Neural Network (ANN) modeling, in explaining how the mind perceives and attends information. More precisely, we will shed some light on the efforts to understand the allocation of attentional resources to the processing of emotional stimuli. This review aims at informing the three disciplines about converging points of their research and to provide a starting point for discussion.

Evidence of increased net ecosystem productivity associated with a longer vegetated season in a deciduous forest in south-central Indiana, USA

Observations of net ecosystem exchange (NEE) of carbon and its biophysical drivers have been collected at the AmeriFlux site in the Morgan-Monroe State Forest (MMSF) in Indiana, USA since 1998. Thus, this is one of the few deciduous forest sites in the world, where a decadal analysis on net ecosystem productivity (NEP) trends is possible. Despite the large interannual variability in NEP, the observations show a significant increase in forest productivity over the past 10 years (by an annual increment of about 10 g C m−2 yr−1). There is evidence that this trend can be explained by longer vegetative seasons, caused by extension of the vegetative activity in the fall. Both phenological and flux observations indicate that the vegetative season extended later in the fall with an increase in length of about 3 days yr−1 for the past 10 years. However, these changes are responsible for only 50% of the total annual gain in forest productivity in the past decade. A negative trend in air and soil temperature during the winter months may explain an equivalent increase in NEP through a decrease in ecosystem respiration.