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

Deep Neural Networks (DNNs) are computationally and memory intensive, whichmakes their hardware implementation a challenging task especially for resourceconstrained devices such as IoT nodes. To address this challenge, this paperintroduces a new method to improve DNNs performance by fusing approximatecomputing with data reuse techniques to be used for image recognitionapplications. DNNs weights are approximated based on the linear and quadraticapproximation methods during the training phase, then, all of the weights arereplaced with the linear/quadratic coefficients to execute the inference in away where different weights could be computed using the same coefficients. Thisleads to a repetition of the weights across the processing element (PE) array,which in turn enables the reuse of the DNN sub-computations (computationalreuse) and leverage the same data (data reuse) to reduce DNNs computations,memory accesses, and improve energy efficiency albeit at the cost of increasedtraining time. Complete analysis for both MNIST and CIFAR 10 datasets ispresented for image recognition , where LeNet 5 revealed a reduction in thenumber of parameters by a factor of 1211.3x with a drop of less than 0.9% inaccuracy. When compared to the state of the art Row Stationary (RS) method, theproposed architecture saved 54% of the total number of adders and multipliersneeded. Overall, the proposed approach is suitable for IoT edge devices as itreduces the memory size requirement as well as the number of needed memoryaccesses.

Deep Neural Networks Based Weight Approximation and Computation Reuse for 2-D Image Classification