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

Classifying hand-written digits and letters has taken a big leap with theintroduction of ConvNets. However, on very constrained hardware the timenecessary to train such models would be high. Our main contribution is twofold.First, we extensively test an end-to-end vanilla neural network (MLP) approachin pure numpy without any pre-processing or feature extraction done beforehand.Second, we show that basic data mining operations can significantly improve theperformance of the models in terms of computational time, without sacrificingmuch accuracy. We illustrate our claims on a simpler variant of the ExtendedMNIST dataset, called Balanced EMNIST dataset. Our experiments show that,without any data mining, we get increased generalization performance when usingmore hidden layers and regularization techniques, the best model achieving84.83% accuracy on a test dataset. Using dimensionality reduction done by PCAwe were able to increase that figure to 85.08% with only 10% of the originalfeature space, reducing the memory size needed by 64%. Finally, adding methodsto remove possibly harmful training samples like deviation from the mean helpedus to still achieve over 84% test accuracy but with only 32.8% of the originalmemory size for the training set. This compares favorably to the majority ofliterature results obtained through similar architectures. Although thisapproach gets outshined by state-of-the-art models, it does scale to some(AlexNet, VGGNet) trained on 50% of the same dataset.

A contextual analysis of multi-layer perceptron models in classifying hand-written digits and letters: limited resources