English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This work attempts to find the most optimal parameter setting of a deepartificial neural network (ANN) for Bengali digit dataset by pre-training itusing stacked denoising autoencoder (SDA). Although SDA based recognition ishugely popular in image, speech and language processing related tasks among theresearchers, it was never tried in Bengali dataset recognition. For this work,a dataset of 70000 handwritten samples were used from (Chowdhury and Rahman,2016) and was recognized using several settings of network architecture. Amongall these settings, the most optimal setting being found to be five or moredeeper hidden layers with sigmoid activation and one output layer with softmaxactivation. We proposed the optimal number of neurons that can be used in thehidden layer is 1500 or more. The minimum validation error found from this workis 2.34% which is the lowest error rate on handwritten Bengali dataset proposedtill date.

On Stacked Denoising Autoencoder based Pre-training of ANN for Isolated Handwritten Bengali Numerals Dataset Recognition