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

This paper presents BlendNet, a neural network architecture employing a novelbuilding block called Blend module, which relies on performing binary andfixed-point convolutions in its main and skip paths, respectively. There is ajudicious deployment of batch normalizations on both main and skip paths insidethe Blend module and in between consecutive Blend modules. This paper alsopresents a compiler for mapping various BlendNet models obtained by replacingsome blocks/modules in various vision neural network models with BlendNetmodules to FPGA devices with the goal of minimizing the end-to-end inferencelatency while achieving high output accuracy. BlendNet-20, derived fromResNet-20 trained on the CIFAR-10 dataset, achieves 88.0% classificationaccuracy (0.8% higher than the state-of-the-art binary neural network) while itonly takes 0.38ms to process each image (1.4x faster than state-of-the-art).Similarly, our BlendMixer model trained on the CIFAR-10 dataset achieves 90.6%accuracy (1.59% less than full precision MLPMixer) while achieving a 3.5xreduction in the model size. Moreover, The reconfigurability of DSP blocks forperforming 48-bit bitwise logic operations is utilized to achieve low-powerFPGA implementation. Our measurements show that the proposed implementationyields 2.5x lower power consumption.

BlendNet: Design and Optimization of a Neural Network-Based Inference Engine Blending Binary and Fixed-Point Convolutions