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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Although the quest for more accurate solutions is pushing deep learningresearch towards larger and more complex algorithms, edge devices demandefficient inference and therefore reduction in model size, latency and energyconsumption. One technique to limit model size is quantization, which impliesusing fewer bits to represent weights and biases. Such an approach usuallyresults in a decline in performance. Here, we introduce a method for designingoptimally heterogeneously quantized versions of deep neural network models forminimum-energy, high-accuracy, nanosecond inference and fully automateddeployment on chip. With a per-layer, per-parameter type automatic quantizationprocedure, sampling from a wide range of quantizers, model energy consumptionand size are minimized while high accuracy is maintained. This is crucial forthe event selection procedure in proton-proton collisions at the CERN LargeHadron Collider, where resources are strictly limited and a latency of${\mathcal O}(1)~\mu$s is required. Nanosecond inference and a resourceconsumption reduced by a factor of 50 when implemented on field-programmablegate array hardware are achieved.

Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors