Classification of Large Biomedical Data Using ANNs Based on BFGS Method

Abstract

Abstract-Artificial neural networks have been widely used for knowledge extraction from biomedical datasets and constitute an important role in bio-data exploration and analysis. In this work, we proposed a new curvilinear algorithm for training large neural networks which is based on the analysis of the eigenstructure of the memoryless BFGS matrices. The proposed method preserves the strong convergence properties provided by the quasi-Newton direction while simultaneously it exploits the nonconvexity of the error surface through the computation of the negative curvature direction without using any storage and matrix factorization. Moreover, for improving the generalization capability of trained ANNs, we explore the incorporation of several dimensionality reduction techniques as a pre-processing step.

CRFs based parallel biomedical named entity recognition algorithm employing MapReduce framework

“…As a result, the parameter selection process needs to use some numerical iteration techniques, such as Generalized Iterative Scaling Algorithm (GIS), Improved Iterative Scaling Algorithm (IIS), Limited-memory BroydenFletcher-Goldfarb-Shanno Algorithm (L-BFGS) [29], and so on.…”

An Ensemble SSL Algorithm for Efficient Chest X-Ray Image Classification

“…During the second half of the last century, the area of diagnostic medicine has massively changed; from a rather qualitative science that was based on observations of whole organisms to a more quantitative science, which is also based on knowledge extraction from databases. The widespread adoption of electronic medical records contributes to the exponential generation of biomedical data in size, dimension and complexity [1]. Furthermore, these biomedical datasets have non-linear relationships between inputs and outcomes, hindering their analysis and modeling.…”

Μη Γραμμικές Μέθοδοι Συζυγών Κλίσεων Για Βελτιστοποίηση Και Εκπαίδευση Νευρωνικών Δικτύων

“…Συγκεκριµένα, διερευνήσαµε πειραµατικά την επίπτωση της εφαρµογής µίας τεχνικής µείωσης διάστασης, ως προστάδιο της εκπαίδευσης των νευρωνικών δικτύων. Τα σύνολα δεδοµένων µεγάλης διάστασης, τα οποία επιλέξαµε είναι τα ακόλουθα : BFGS τέθηκαν οι εξ΄ ορισµού τιµές c 1 = c 2 = 10 −4[76]. Τα αρχικά ϐάρη αρχικοποιήθηκαν σύµφωνα µε τη µέθοδο των Nguyen-Widrow[99].…”