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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Neural networks performance has been significantly improved in the last fewyears, at the cost of an increasing number of floating point operations persecond (FLOPs). However, more FLOPs can be an issue when computationalresources are limited. As an attempt to solve this problem, pruning filters isa common solution, but most existing pruning methods do not preserve the modelaccuracy efficiently and therefore require a large number of finetuning epochs.In this paper, we propose an automatic pruning method that learns which neuronsto preserve in order to maintain the model accuracy while reducing the FLOPs toa predefined target. To accomplish this task, we introduce a trainablebottleneck that only requires one single epoch with 25.6% (CIFAR-10) or 7.49%(ILSVRC2012) of the dataset to learn which filters to prune. Experiments onvarious architectures and datasets show that the proposed method can not onlypreserve the accuracy after pruning but also outperform existing methods afterfinetuning. We achieve a 52.00% FLOPs reduction on ResNet-50, with a Top-1accuracy of 47.51% after pruning and a state-of-the-art (SOTA) accuracy of76.63% after finetuning on ILSVRC2012. Code available athttps://github.com/nota-github/autobot_AAAI23.

Automatic Neural Network Pruning that Efficiently Preserves the Model Accuracy