Zoekresultaten

The Eternal Network

‘The network is everlasting’ wrote Robert Filliou and George Brecht in 1967, a statement that, at first glance, still seems to be true of today’s world. Yet there are also signs that the omnipresence of networks is evolving into another reality. In recent times, the limits of networks rather than their endless possibilities have been brought into focus. Ongoing media debates about hate speech, fake news, and algorithmic bias swirl into a growing backlash against networks. Perhaps it is time to reconsider the contemporary reach and relevance of the network imaginary.Accompanying transmediale 2020 End to End’s exhibition ‘The Eternal Network’, this collection gathers contributions from artists, activists, and theorists who engage with the question of the network anew. In referencing Filliou’s eternal notion, the exhibition and publication project closes the loop between pre- and post-internet imaginaries, opening up possible futures with and beyond networks. This calls many of the collection’s authors to turn to instances of independent and critical net cultures as historical points of inspiration for rethinking, reforming, or refuting networks in the present.---The Eternal Network: Vom Enden und Werden der NetzkulturDEUTSCHE FASSUNG:„Das Netzwerk wird es ewig geben“, schrieben Robert Filliou und George Brecht 1967 – eine Aussage, die auf den ersten Blick auch heute noch zuzutreffen scheint. Doch gibt es auch Anzeichen, dass die Allgegenwärtigkeit von Netzwerken eine andere W irklichkeit hervorbringt. Mittlerweile rückt die Endlichkeit von Netzwerken – anstatt deren endlose Möglichkeiten – in den Fokus; davon zeugen die anhaltenden Mediendebatten über Hassrede, Fake News und algorithmischer Diskriminierung. Vielleicht ist es an der Zeit, die aktuelle Reichweite und Relevanz des Netzwerks neu zu betrachten.Begleitend zur Ausstellung „Das ewige Netzwerk“ der transmediale 2020 End to End versammelt dieser Band Beiträge von Künstler*innen, Aktivist*innen und Theoretiker* innen, die sich neu mit der Frage des Netzwerks beschäftigen. Ausstellung und Publikation beziehen sich auf Fillious Konzept von der Ewigkeit des Netzwerks. Sie verbinden dabei die Vorstellungswelten, die zeitlich vor der Entwicklung des Internets entstanden sind, mit jenen, die darauf folgten. So eröffnen sie mögliche Zukünfte mit und jenseits von Netzwerken. Viele Autor*innen in diesem Band lassen sich dabei von historischen Momenten der unabhängigen und kritischen Netzkulturen inspirieren, um Netzwerke der Gegenwart neu zu denken, sie zu reformieren oder anzufechten.

Integrating meta-Information into recurrent neural network language models

Airport passenger flow prediction using LTSM Recurrent Neural Networks

Passenger flow management is an important issue at many airports around the world. There are high concentrations of passengers arriving and leaving the airport in waves of large volumes in short periods, particularly in big hubs. This might cause congestion in some locations depending on the layout of the terminal building. With a combination of real airport data, as well as synthetic data obtained through an airport simulator, a Long Short-Term Memory Recurrent Neural Network has been implemented to predict the possible trajectories that passengers may travel within the airport depending on user-defined passenger profiles. The aim of this research is to improve passenger flow predictability and situational awareness to make a more efficient use of the airport, that could also positively impact communication with public and private land transport operators.

An invariants based architecture for combining small and large data sets in neural networks

We present a novel architecture for an AI system that allows a priori knowledge to combine with deep learning. In traditional neural networks, all available data is pooled at the input layer. Our alternative neural network is constructed so that partial representations (invariants) are learned in the intermediate layers, which can then be combined with a priori knowledge or with other predictive analyses of the same data. This leads to smaller training datasets due to more efficient learning. In addition, because this architecture allows inclusion of a priori knowledge and interpretable predictive models, the interpretability of the entire system increases while the data can still be used in a black box neural network. Our system makes use of networks of neurons rather than single neurons to enable the representation of approximations (invariants) of the output.

Sentiment polarity classification of corporate review data with a bidirectional Long-Short Term Memory (biLSTM) neural network architecture

A considerable amount of literature has been published on Corporate Reputation, Branding and Brand Image. These studies are extensive and focus particularly on questionnaires and statistical analysis. Although extensive research has been carried out, no single study was found which attempted to predict corporate reputation performance based on data collected from media sources. To perform this task, a biLSTM Neural Network extended with attention mechanism was utilized. The advantages of this architecture are that it obtains excellent performance for NLP tasks. The state-of-the-art designed model achieves highly competitive results, F1 scores around 72%, accuracy of 92% and loss around 20%.

The Neural Network Zoo

From the article: Abstract: An overview of neural network architectures is presented. Some of these architectures have been created in recent years, whereas others originate from many decades ago. Apart from providing a practical tool for comparing deep learning models, the Neural Network Zoo also uncovers a taxonomy of network architectures, their chronology, and traces back lineages and inspirations for these neural information processing systems.