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

On-device Deep Neural Network (DNN) inference consumes significant computingresources and development efforts. To alleviate that, we propose LUT-NN, thefirst system to empower inference by table lookup, to reduce inference cost.LUT-NN learns the typical features for each operator, named centroid, andprecompute the results for these centroids to save in lookup tables. Duringinference, the results of the closest centroids with the inputs can be readdirectly from the table, as the approximated outputs without computations.LUT-NN integrates two major novel techniques: (1) differentiable centroidlearning through backpropagation, which adapts three levels of approximation tominimize the accuracy impact by centroids; (2) table lookup inferenceexecution, which comprehensively considers different levels of parallelism,memory access reduction, and dedicated hardware units for optimal performance.LUT-NN is evaluated on multiple real tasks, covering image and speechrecognition, and nature language processing. Compared to related work, LUT-NNimproves accuracy by 66% to 92%, achieving similar level with the originalmodels. LUT-NN reduces the cost at all dimensions, including FLOPs ($\leq$16x), model size ($\leq$ 7x), latency ($\leq$ 6.8x), memory ($\leq$ 6.5x), andpower ($\leq$ 41.7%).

LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup