Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/115186
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Hierarchical Bayesian Reservoir Memory |
Author: | Nouri, A. Nikmehr, H. |
Citation: | Proceedings of the 14th International CSI Computer Conference (CSICC 2009), 2009, pp.582-587 |
Publisher: | IEEE |
Publisher Place: | Piscataway, NJ |
Issue Date: | 2009 |
ISBN: | 1424442613 9781424442614 |
Conference Name: | 14th International CSI Computer Conference (CSICC 2009) (20 Oct 2009 - 21 Oct 2009 : Tehran, Iran) |
Statement of Responsibility: | Ali Nouri and Hooman Nikmehr |
Abstract: | In a quest for modeling human brain, we are going to introduce a brain model based on a general framework for brain called Memory-Prediction Framework. The model is a hierarchical Bayesian structure that uses Reservoir Computing methods as the state-of-theart and the most biological plausible Temporal Sequence Processing method for online and unsupervised learning. So, the model is called Hierarchical Bayesian Reservoir Memory (HBRM). HBRM uses a simple stochastic gradient descent learning algorithm to learn and organize common multi-scale spatio-temporal patterns/features of the input signals in a hierarchical structure in an unsupervised manner to provide robust and real-time prediction of future inputs. We suggest HBRM as a real-time high-dimensional stream processing model for the basic brain computations. In this paper we will describe the model and assess its prediction accuracy in a simulated real-world environment. |
Keywords: | Brian theory; Bayesian networks, Memory- Prediction Framework; stochastic time-series prediction; Reservoir Computing |
Rights: | ©2009 IEEE |
DOI: | 10.1109/CSICC.2009.5349642 |
Published version: | https://ieeexplore-ieee-org.proxy.library.adelaide.edu.au/xpl/mostRecentIssue.jsp?punumber=5340903 |
Appears in Collections: | Aurora harvest 3 Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.