A Functional Dynamic Boltzmann Machine

Authors: Hiroshi Kajino

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We design numerical experiments to empirically confirm the effectiveness of our solutions. The experimental results demonstrate consistent error reductions as compared to baseline methods, from which we conclude the effectiveness of F-Dy BM for functional time series prediction. The effectiveness of F-Dy BM is empirically demonstrated using five real spatiotemporal data sets.
Researcher Affiliation Industry Hiroshi Kajino IBM Research Tokyo KAJINO@jp.ibm.com
Pseudocode Yes Algorithm 1 An online learning algorithm for F-Dy BM.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes NOAA Global Surface Temperature V4.01 We use a temperature data set provided by the NOAA/OAR/ESRL PSD, Boulder, Colorado, USA. It contains the global temperature anomalies from January 1880 to present, resulting in the length 1638.3 Retrieved from http://www.esrl.noaa.gov/psd/ data/gridded/data.noaaglobaltemp.html on Aug. 23, 2016. Air Data is maintained by the United States Environmental Protection Agency, and we retrieved it from Air Quality System Data Mart (http://aqsdr1.epa.gov/aqsweb/aqstmp/ airdata/download_files.html) on Dec. 28, 2016.
Dataset Splits Yes To do so, we first divide the time series into training, validation, and test sets in chronological order with ratio 3 : 3 : 4.
Hardware Specification No The paper does not provide specific hardware details used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers.
Experiment Setup Yes For all the models, we used the RBF kernel K(x, x ; γ) = exp( γ x x 2), and prepared the instances by all the combinations of the following hyperparameters: N = 25, d = 3, η[0] {2 n}23 n=19, σ2 {2 n}2 n=0, γ {2n}5 n=0 for all the models and L = 3, λ1 = 0.1, λ2 = 0.5, λ3 = 0.9 for G-Dy BM and F-Dy BM. All the models are trained by using SGD, and the learning rate is controlled by rmsprop [Tieleman and Hinton, 2012].