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

With ever increasing depth and width in deep neural networks to achievestate-of-the-art performance, deep learning computation has significantlygrown, and dot-products remain dominant in overall computation time. Most priorworks are built on conventional dot-product where weighted input summation isused to represent the neuron operation. However, another implementation ofdot-product based on the notion of angles and magnitudes in the Euclidean spacehas attracted limited attention. This paper proposes DeepCAM, an inferenceaccelerator built on two critical innovations to alleviate the computation timebottleneck of convolutional neural networks. The first innovation is anapproximate dot-product built on computations in the Euclidean space that canreplace addition and multiplication with simple bit-wise operations. The secondinnovation is a dynamic size content addressable memory-based (CAM-based)accelerator to perform bit-wise operations and accelerate the CNNs with a lowercomputation time. Our experiments on benchmark image recognition datasetsdemonstrate that DeepCAM is up to 523x and 3498x faster than Eyeriss andtraditional CPUs like Intel Skylake, respectively. Furthermore, the energyconsumed by our DeepCAM approach is 2.16x to 109x less compared to Eyeriss.

DeepCAM: A Fully CAM-based Inference Accelerator with Variable Hash Lengths for Energy-efficient Deep Neural Networks