Computational Intelligence and Neuroscience / 2015 / Article / Tab 2

Research Article

Learning Document Semantic Representation with Hybrid Deep Belief Network

Table 2

Document classification accuracy and document retrieval precision of six categories on 20 Newsgroups.

DatasetModelL_rDocument classification Document retrieval
Output units number Output units number
501001285121000501001285121000

20 NewsgroupsRSM0.0176.1379.6080.6380.2480.6175.4079.8380.2478.6479.66
0.00174.1176.2081.8881.0381.3468.2370.4380.8981.0881.07
0.000157.8876.8976.9283.3482.9358.6671.9872.6480.4578.93
DBN0.0176.5279.7781.0382.9482.1177.3680.2180.0780.9979.01
DocNADE0.0178.8281.3782.7083.6783.7678.1381.0181.4681.8181.15
HDBN0.0185.9285.7786.8286.9486.1582.3282.4284.9784.8783.73

We are committed to sharing findings related to COVID-19 as quickly as possible. We will be providing unlimited waivers of publication charges for accepted research articles as well as case reports and case series related to COVID-19. Review articles are excluded from this waiver policy. Sign up here as a reviewer to help fast-track new submissions.