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

Deep learning models have been successfully used in computer vision and manyother fields. We propose an unorthodox algorithm for performing quantization ofthe model parameters. In contrast with popular quantization schemes based onthresholds, we use a novel technique based on periodic functions, such ascontinuous trigonometric sine or cosine as well as non-continuous hatfunctions. We apply these functions component-wise and add the sum over themodel parameters as a regularizer to the model loss during training. Thefrequency and amplitude hyper-parameters of these functions can be adjustedduring training. The regularization pushes the weights into discrete pointsthat can be encoded as integers. We show that using this technique theresulting quantized models exhibit the same accuracy as the original ones onCIFAR-10 and ImageNet datasets.

On Periodic Functions as Regularizers for Quantization of Neural Networks