Neural networks letter: Capturing significant events with neural networks

Authors:
Harold Szu;Charles Hsu;Jeffrey Jenkins;Jefferson Willey;Joseph Landa
Affiliations:
US Army NVESD, Fort Belvoir, VA, United States;Trident Systems Inc., Fairfax, VA, United States;US Army NVESD, Fort Belvoir, VA, United States;US Naval Research Lab, Washington, DC, United States;Briartek Inc., Alexandria, VA, United States
Venue:
Neural Networks
Year:
2012

Citing 3
Cited 2

Unsupervised learning with stochastic gradient

Neurocomputing
Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information

IEEE Transactions on Information Theory
Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?

IEEE Transactions on Information Theory

Smartphone household wireless electroencephalogram hat

Applied Computational Intelligence and Soft Computing
Smartphone household wireless electroencephalogram hat

Applied Computational Intelligence and Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Smartphone video capture and transmission to the Web contributes to data pollution. In contrast, mammalian eyes sense all, capture only significant events, allowing us vividly recall the causalities. Likewise in our videos, we wish to skip redundancies and keep only significantly differences, as determined by real-time local medium filters. We construct a Picture Index (PI) of one's (center of gravity changes) among zeros (no changes) as Motion Organized Sparseness (MOS). Only non-overlapping time-ordered PI pair is admitted in the outer-product Associative Memory (AM). Another outer product between PI and its image builds Hetero-AM (HAM) for fault tolerant retrievals.