On Stacked Denoising Autoencoder based Pre-training of ANN for Isolated Handwritten Bengali Numerals Dataset Recognition
This work addresses digit recognition for Bengali script, an incremental improvement as it applies an existing method to a new dataset.
The authors tackled the problem of recognizing handwritten Bengali numerals by pre-training a deep artificial neural network with stacked denoising autoencoders, achieving a minimum validation error of 2.34%, which is the lowest error rate reported for this dataset to date.
This work attempts to find the most optimal parameter setting of a deep artificial neural network (ANN) for Bengali digit dataset by pre-training it using stacked denoising autoencoder (SDA). Although SDA based recognition is hugely popular in image, speech and language processing related tasks among the researchers, 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. Among all these settings, the most optimal setting being found to be five or more deeper hidden layers with sigmoid activation and one output layer with softmax activation. We proposed the optimal number of neurons that can be used in the hidden layer is 1500 or more. The minimum validation error found from this work is 2.34% which is the lowest error rate on handwritten Bengali dataset proposed till date.