Thursday 10 Nov, 1:15PM, room: G45
Hamouda Khalifa H Chantar: Arabic Document Categorization using a combination of Binary Particle Swarm Optimization and K nearest neighbour.
Abstract—Document categorization is an important topic that is central to many applications that demand reasoning about and organisation of text documents, web pages, and so forth. Document classification is commonly achieved by choosing appropriate features (terms) and building a TFIDF document vector feature. In this process, feature selection is a key factor in determining the accuracy and effectiveness of resulting classifications. For a given classification task, the right choice of features means accurate classification with suitable levels of computational efficiency. Meanwhile, most document classification work is based on English language documents. In this work, we make three main contributions: (i) we demonstrate successful document classification in the context of Arabic documents (although previous work has demonstrated text classification in Arabic, the datasets used, and the experimental setup, have not been revealed); (ii) we offer our datasets to enable other researchers to compare directly with our results; (iii) we demonstrate a combination of Binary Particle Swarm Optimization and K nearest neighbour that performs well in selecting good sets of features for this task.
Gordon M Govan: Dynamics of neural networks with different motif distributions
In a network a 3-node motif is a group of three nodes linked together. The 3-node motif distribution indicates the percentages of 3-node motifs present in a network. We study the dynamics of Random Recurrent Neural Networks having two specific 3-node motif distributions. We find out that one of these motif distributions is more likely to have regular dynamics before any stimulus is applied and that few nodes need to be influenced in order to consistently have regular dynamics.
Majed Al-Saeed:TBA
No comments:
Post a Comment