SELECTING NEURAL NETWORK ARCHITECTURE FOR INVESTMENT PROFITABILITY PREDICTIONS Cover Image

SELECTING NEURAL NETWORK ARCHITECTURE FOR INVESTMENT PROFITABILITY PREDICTIONS
SELECTING NEURAL NETWORK ARCHITECTURE FOR INVESTMENT PROFITABILITY PREDICTIONS

Author(s): Tonimir Kišasondi, Alen Lovrenčić
Subject(s): Computational linguistics, ICT Information and Communications Technologies
Published by: Fakultet organizacije i informatike, Sveučilište u Zagrebu
Keywords: neural networks; MLP training algorithms; neural network ADT; neural network graph modelling;

Summary/Abstract: In this paper we present a modified neural network architecture and an algorithm that enables neural networks to learn vectors in accordance to user designed sequences or graph structures. This enables us to use the modified network algorithm to identify, generate or complete specified patterns that are learned in the training phase. The algorithm is based on the idea that neural networks in the human neurocortex represent a distributed memory of sequences that are stored in invariant hierarchical form with associative access. The algorithm was tested on our custom built simulator that supports the usage of our ADT neural network with standard backpropagation and our custom built training algorithms, and it proved to be useful and successful in modelling graphs.

  • Issue Year: 30/2006
  • Issue No: 1
  • Page Range: 93-103
  • Page Count: 11
  • Language: English
Toggle Accessibility Mode