Large memory storage and retrieval neural network explained

A large memory storage and retrieval neural network (LAMSTAR)[1] is a fast deep learning neural network of many layers that can use many filters simultaneously. These filters may be nonlinear, stochastic, logic, non-stationary, or even non-analytical. They are biologically motivated and learn continuously.

A LAMSTAR neural network may serve as a dynamic neural network in spatial or time domains or both. Its speed is provided by Hebbian link-weights that integrate the various and usually different filters (preprocessing functions) into its many layers and to dynamically rank the significance of the various layers and functions relative to a given learning task. This vaguely imitates biological learning that integrates various preprocessors (cochlea, retina, etc.) and cortexes (auditory, visual, etc.) and their various regions. Its deep learning capability is further enhanced by using inhibition, correlation and by its ability to cope with incomplete data, or "lost" neurons or layers even amidst a task. It is fully transparent due to its link weights. The link-weights allow dynamic determination of innovation and redundancy, and facilitate the ranking of layers, of filters or of individual neurons relative to a task.

LAMSTAR has been applied to many domains, including medical[2] [3] [4] and financial predictions, adaptive filtering of noisy speech in unknown noise,[5] still-image recognition, video image recognition,[6] software security[7] and adaptive control of non-linear systems.[8] LAMSTAR had a much faster learning speed and somewhat lower error rate than a CNN based on ReLU-function filters and max pooling, in 20 comparative studies.[9]

These applications demonstrate delving into aspects of the data that are hidden from shallow learning networks and the human senses, such as in the cases of predicting onset of sleep apnea events, of an electrocardiogram of a fetus as recorded from skin-surface electrodes placed on the mother's abdomen early in pregnancy, of financial prediction or in blind filtering of noisy speech.

LAMSTAR was proposed in 1996 and was further developed Graupe and Kordylewski from 1997–2002.[10] [11] [12] A modified version, known as LAMSTAR 2, was developed by Schneider and Graupe in 2008.[13]

Notes and References

  1. Book: Graupe, Daniel . [{{google books |plainurl=y |id=W6W6CgAAQBAJ&pg=PP1}} Principles of Artificial Neural Networks ]. World Scientific. 2013. 978-981-4522-74-8.
  2. Nigam. Vivek Prakash. Graupe. Daniel. 2004-01-01. A neural-network-based detection of epilepsy . Neurological Research. 26. 1. 55–60. 10.1179/016164104773026534 . 0161-6412. 14977058. 10764633.
  3. Waxman. Jonathan A. . Graupe. Daniel. Carley . David W.. 2010-04-01. Automated Prediction of Apnea and Hypopnea, Using a LAMSTAR Artificial Neural Network. American Journal of Respiratory and Critical Care Medicine. 181. 7. 727–733 . 10.1164/rccm.200907-1146oc. 1073-449X . 20019342.
  4. Graupe. D.. Graupe. M. H. . Zhong. Y.. Jackson. R. K.. 2008. Blind adaptive filtering for non-invasive extraction of the fetal electrocardiogram and its non-stationarities. Proc. Inst. Mech. Eng. H . 222. 8. 1221–1234. 10.1243/09544119jeim417 . 19143416 . 40744228.
  5. Graupe. D.. Abon. J.. 2002. A Neural Network for Blind Adaptive Filtering of Unknown Noise from Speech . Intelligent Engineering Systems Through Artificial Neural Networks . 12. 683–688 . 2017-06-14.
  6. Girado. J. I. . Sandin. D. J. . DeFanti . T. A.. Nasser M. . Aggelos K. . Nasrabadi . Katsaggelos . 2003. Real-time camera-based face detection using a modified LAMSTAR neural network system. Proc. SPIE 5015, Applications of Artificial Neural Networks in Image Processing VIII . Applications of Artificial Neural Networks in Image Processing VIII. 5015 . 36–46 . 2003SPIE.5015...36G. 10.1117/12.477405. 15918252.
  7. Venkatachalam. V. . Selvan. S.. 2007 . Intrusion Detection using an Improved Competitive Learning Lamstar Network. International Journal of Computer Science and Network Security . 7. 2. 255–263.
  8. Web site: Control of unstable nonlinear and nonstationary systems using LAMSTAR neural networks. Graupe . D.. Smollack. M.. 2007 . ResearchGate . Proceedings of 10th IASTED on Intelligent Control, Sect.592. 141–144. 2017-06-14.
  9. Book: Graupe, Daniel. [{{google books |plainurl=y |id=e5hIDQAAQBAJ |page=57}} Deep Learning Neural Networks: Design and Case Studies]. 7 July 2016. World Scientific Publishing Co Inc. 978-981-314-647-1. 57–110.
  10. Book: Graupe. D. . Kordylewski. H.. Proceedings of the 39th Midwest Symposium on Circuits and Systems . Network based on SOM (Self-Organizing-Map) modules combined with statistical decision tools . August 1996. 978-0-7803-3636-0. 1. 471–474. 62437626 . 10.1109/mwscas.1996.594203.
  11. Graupe. D.. Kordylewski . H.. 1998-03-01. A Large Memory Storage and Retrieval Neural Network for Adaptive Retrieval and Diagnosis. International Journal of Software Engineering and Knowledge Engineering. 08 . 1. 115–138. 10.1142/s0218194098000091. 0218-1940.
  12. Kordylewski. H.. Graupe. D. Liu. K.. 2001 . A novel large-memory neural network as an aid in medical diagnosis applications. IEEE Transactions on Information Technology in Biomedicine. 5. 3. 202–209. 10.1109/4233.945291. 11550842 . 11783734.
  13. Schneider. N.C.. Graupe. 2008. A modified LAMSTAR neural network and its applications. International Journal of Neural Systems. 18 . 4. 331–337. 10.1142/s0129065708001634. 18763732.

This article is licensed under the GNU Free Documentation License. It uses material from the Wikipedia article "Large memory storage and retrieval neural network".

Except where otherwise indicated, Everything.Explained.Today is © Copyright 2009-2024, A B Cryer, All Rights Reserved. Cookie policy.