Pith. sign in

REVIEW

ReBNet: Residual Binarized Neural Network

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1711.01243 v3 pith:4PRGQ5PN submitted 2017-11-03 cs.LG cs.CVcs.NE

ReBNet: Residual Binarized Neural Network

classification cs.LG cs.CVcs.NE
keywords accuracybinarynetworksbinarizationneuralareaclassificationcost
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

This paper proposes ReBNet, an end-to-end framework for training reconfigurable binary neural networks on software and developing efficient accelerators for execution on FPGA. Binary neural networks offer an intriguing opportunity for deploying large-scale deep learning models on resource-constrained devices. Binarization reduces the memory footprint and replaces the power-hungry matrix-multiplication with light-weight XnorPopcount operations. However, binary networks suffer from a degraded accuracy compared to their fixed-point counterparts. We show that the state-of-the-art methods for optimizing binary networks accuracy, significantly increase the implementation cost and complexity. To compensate for the degraded accuracy while adhering to the simplicity of binary networks, we devise the first reconfigurable scheme that can adjust the classification accuracy based on the application. Our proposition improves the classification accuracy by representing features with multiple levels of residual binarization. Unlike previous methods, our approach does not exacerbate the area cost of the hardware accelerator. Instead, it provides a tradeoff between throughput and accuracy while the area overhead of multi-level binarization is negligible.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.