1,721,723 research outputs found
Evolutionary and Iterative Training of Recurrent Neural Networks via the Singular Value Decomposition
Full text linkLa tesi esamina l'uso della decomposizione ai valori singolari (SVD) dall'algebra lineare come strumento per l'analisi delle reti neurali, nonché il suo utilizzo per accelerare o addirittura limitare l'apprendimento (ad esempio, per prevenire l'over-fitting o mantenere la stabilità) e come base per gli algoritmi di apprendimento iterativo ed evolutivo.
Ciò che si presenta sono metodi per tenere conto della struttura intrinseca della trasformazione, anche durante l'utilizzo di metodi evolutivi, impiegando la decomposizione ai valori singolari. Naturalmente, il tentativo di preservare una certa struttura delle trasformazioni non è inedito, sia che questo significhi preservare la scarsità sia che si riferisca a qualche tipo di invarianza, come nell'invarianza di spostamento di uno strato convoluzionale.
I metodi presentati nel lavoro consentono di addestrare reti neurali ricorrenti per una varietà di problemi con cambiamenti nel tempo, tra cui la previsione dei prezzi, la manutenzione predittiva, l'identificazione del modello e il controllo automatico. Il nostro metodo non si basa sulla propagazione all'indietro e può essere utilizzato in ambienti supervisionati o non supervisionati. Inoltre, i nostri modelli possono essere facilmente inizializzati utilizzando la conoscenza del dominio o il metodo dei minimi quadrati (lineari) per "pre-programmare" il modello e iniziare l'ottimizzazione in un'area dello spazio della soluzione suscettibile di produrre risultati. Infine, data una rete neurale precedentemente addestrata in un dominio, i nostri modelli e metodi consentono il riutilizzo e la rapida riqualificazione per un dominio simile, preservando la struttura intrinseca della trasformazione nel cuore della rete neurale.This work examines the use of the singular value decomposition (SVD) from linear algebra as a tool for the analysis of neural networks, as well as its use to speed up or even limit learning (to prevent over-fitting or maintain stability, for example) and as the basis for iterative and evolutionary learning algorithms.
What we present here are methods of taking the inherent structure of the transformation into account — even while using evolutionary methods — using the singular value decomposition. Of course, preserving some structure of the transformations is not completely new — whether this means preserving sparseness or some type of invariance, as in the shift invariance of a convolutional layer.
The methods we present allow us to train recurrent neural networks for a variety of problems with changes through time, including price prediction, predictive maintenance and model identification, and automatic control. Our method does not rely on back propagation and can be used in either supervised or unsupervised settings. Further, our models can be easily initialized by using either domain knowledge or (linear) least squares to “pre-program” the model and begin optimization in an area of the solution space likely to yield results. Finally, given a neural network previously trained in one domain, our models and methods allow the reuse and quick retraining for a similar domain, by preserving the inherent structure of the transformation at the heart of the neural network
BODY SIZE AND ITS VARIABILITY IN THE COPEPOD ACARTIA MARGALEFI (CALANOIDA) FROM LAKE ACQUATINA (SE ITALY)
No full textEconomic growth: The role of digitalization and entrepreneurship
No full textResearch widely acknowledge that entrepreneurial activity is a driving force for economies. Recently, leading political institutions and scholars argue that digitalization is a central factor for economic growth and a fundamental right for citizens and societies. Moreover, studies have introduced the emergence “digital entrepreneurship” as a new research stream, to indicate an entrepreneurial process triggered by the infusion of new digital technologies in various aspects of entrepreneurship. However, research has often treated entrepreneurship and digitalization in isolation, partially neglecting a combined role as explanatory factors and driving forces for economic growth. To cope with this research gap, with this study, we aim at exploring how entrepreneurship and digitalization may impact economic growth. By employing a quantitative approach, we observe that entrepreneurship is positively related to economic growth and that digitalization mediates this relationship. Building on previous studies, we propose an original process model for measuring entrepreneurial activity made up of three phases, entrepreneurial quantity, quality and outcome. Findings show that only the last two phases of entrepreneurial quality and outcome have a positive impact on economic development. We believe that scholars can find interesting this research to further explore the role of digital entrepreneurship for economies and societies. Finally, policymakers can find useful our original method to measure the entrepreneurial activity and the impact that digitalization and entrepreneurship have on their economies
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
- …
