Search International and National Patent Collections

1. (WO2014203042) METHOD FOR PSEUDO-RECURRENT PROCESSING OF DATA USING A FEEDFORWARD NEURAL NETWORK ARCHITECTURE

Pub. No.:    WO/2014/203042    International Application No.:    PCT/IB2013/055112
Publication Date: Thu Dec 25 00:59:59 CET 2014 International Filing Date: Sat Jun 22 01:59:59 CEST 2013
IPC: G06N 3/04
Applicants: ASELSAN ELEKTRONIK SANAYI VE TICARET ANONIM SIRKETI
Inventors: YILMAZ, Ozgur
OZKAN, Huseyin
Title: METHOD FOR PSEUDO-RECURRENT PROCESSING OF DATA USING A FEEDFORWARD NEURAL NETWORK ARCHITECTURE
Abstract:
Recurrent neural networks are powerful tools for handling incomplete data problems in machine learning thanks to their significant generative capabilities. However, the computational demand for algorithms to work in real time applications requires specialized hardware and software solutions. We disclose a method for adding recurrent processing capabilities into a feedforward network without sacrificing much from computational efficiency. We assume a mixture model and generate samples of the last hidden layer according to the class decisions of the output layer, modify the hidden layer activity using the samples, and propagate to lower layers. For an incomplete data problem, the iterative procedure emulates feedforward-feedback loop, filling-in the missing hidden layer activity with meaningful representations.