DocumentCode :
2629965
Title :
Hierarchical Bayesian reservoir memory
Author :
Nouri, Ali ; Nikmehr, Hooman
Author_Institution :
Comput. Eng. Dept., Bu-Ali Sina Univ., Hamedan, Iran
fYear :
2009
fDate :
20-21 Oct. 2009
Firstpage :
582
Lastpage :
587
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-the-art 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 :
belief networks; brain models; gradient methods; neural nets; stochastic processes; temporal reasoning; unsupervised learning; hierarchical Bayesian reservoir memory; hierarchical Bayesian structure; human brain modeling; memory-prediction framework; online learning; reservoir computing methods; stochastic gradient descent learning algorithm; temporal sequence processing method; unsupervised learning; Bayesian methods; Biological system modeling; Biology computing; Brain modeling; Humans; Predictive models; Reservoirs; Robustness; Stochastic processes; Unsupervised learning; Bayesian Networks; Brian Theory; Memory-Prediction Framework; Reservoir Computing; Stochastic Time-Series Prediction;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Conference, 2009. CSICC 2009. 14th International CSI
Conference_Location :
Tehran
Print_ISBN :
978-1-4244-4261-4
Electronic_ISBN :
978-1-4244-4262-1
Type :
conf
DOI :
10.1109/CSICC.2009.5349642
Filename :
5349642
Link To Document :
بازگشت