NDLI: An adaptive sequential Monte Carlo approach to neural network training

Content Provider	IEEE Xplore Digital Library
Author	Yiming Zhang Bo Hu
Copyright Year	2015
Description	Author affiliation: New York Univ. Shanghai, Shanghai, China (Yiming Zhang) \|\| Dept. of Electr. Eng., Fudan Univ., Shanghai, China (Bo Hu)
Abstract	Sequential Monte Carlo methods (Particle Filters) have been successfully applied to the online training of neural networks. However the generic Particle Filter requires the model noise to be known prior to training. Furthermore, the random walk assumption with which the network weights are modeled by may be problematic as a result of the insufficient knowledge of the model noise. In this paper, the evolution of the network weights are modeled using the Polynomial Prediction Model (PPM) which has been shown to have more predictive power than the random walk. The PPM can generate a whole class of models which can then be used in a modified multimodel version of the Particle Filter based on the Interacting Multiple Model (IMM) to train the neural network. The resulting algorithm generates an estimate of the noise terms which is closer to the true noise in the form of a weighted linear combination of the model noise given in the different models. This means that the algorithm can adapt to unknown model noise. Experiments show that the proposed algorithm offers better performance in training neural networks in the context where we are unable to determine the error terms.
Starting Page	1619
Ending Page	1623
File Size	389315
Page Count	5
File Format	PDF
ISBN	9781479978007
DOI	10.1109/ICIT.2015.7125328
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2015-03-17
Publisher Place	Spain
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Mathematical model Adaptation models Neural networks Training Particle filters Predictive models Computational modeling Polynomial Prediction Model (PPM) Neural Network Particle Filter Interacting Multiple Model (IMM)
Content Type	Text
Resource Type	Article

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Adaptive neural network prediction model for energy consumption

Interacting multiple model particle filters for side scan bathymetry

Sequential quasi-Monte Carlo filter for visual object tracking

Research of neural network model prediction strategy based on PSO-BP algorithm

Daily runoff time-series prediction based on the adaptive neural fuzzy inference system

Bayesian head state prediction: Computing the dynamic prior with spiking neurons

Adaptive stopping for fast particle smoothing

Robust auxiliary particle filters using multiple importance sampling

An adaptive imm estimator for aircraft tracking.

An adaptive sequential Monte Carlo approach to neural network training

Similar Documents

Adaptive neural network prediction model for energy consumption

Interacting multiple model particle filters for side scan bathymetry

Sequential quasi-Monte Carlo filter for visual object tracking

Research of neural network model prediction strategy based on PSO-BP algorithm

Daily runoff time-series prediction based on the adaptive neural fuzzy inference system

Bayesian head state prediction: Computing the dynamic prior with spiking neurons

Adaptive stopping for fast particle smoothing

Robust auxiliary particle filters using multiple importance sampling

An adaptive imm estimator for aircraft tracking.

An adaptive sequential Monte Carlo approach to neural network training