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/

Zendy Plus

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

Zendy Tools

Zendy Open

This paper introduces NeuroBlend, a novel neural network architecturefeaturing a unique building block known as the Blend module. This moduleincorporates binary and fixed-point convolutions in its main and skip paths,respectively. There is a judicious deployment of batch normalizations on bothmain and skip paths inside the Blend module and in between consecutive Blendmodules. Additionally, we present a compiler and hardware architecture designedto map NeuroBlend models onto FPGA devices, aiming to minimize inferencelatency while maintaining high accuracy. Our NeuroBlend-20 (NeuroBlend-18)model, derived from ResNet-20 (ResNet-18) trained on CIFAR-10 (CIFAR-100),achieves 88.0\% (73.73\%) classification accuracy, outperformingstate-of-the-art binary neural networks by 0.8\% (1.33\%), with an inferencetime of 0.38ms per image, 1.4x faster than previous FPGA implementation forBNNs. Similarly, our BlendMixer model for CIFAR-10 attains 90.6\%accuracy(1.59\% less than full precision MLPMixer), with a 3.5x reduction inmodel size compared to full precision MLPMixer. Furthermore, leveraging DSPblocks for 48-bit bitwise logic operations enables low-power FPGAimplementation, yielding a 2.5x reduction in power consumption.

NeuroBlend: Towards Low-Power yet Accurate Neural Network-Based Inference Engine Blending Binary and Fixed-Point Convolutions