Pith. sign in

REVIEW 1 cited by

Neural Precision Polarization: Simplifying Neural Network Inference with Dual-Level Precision

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 2411.05845 v1 pith:OU7GU65C submitted 2024-11-06 cs.LG

classification cs.LG
keywords precisionpathsaccuracynetworkneuralpolarizationactivationsedge
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We introduce a precision polarization scheme for DNN inference that utilizes only very low and very high precision levels, assigning low precision to the majority of network weights and activations while reserving high precision paths for targeted error compensation. This separation allows for distinct optimization of each precision level, thereby reducing memory and computation demands without compromising model accuracy. In the discussed approach, a floating-point model can be trained in the cloud and then downloaded to an edge device, where network weights and activations are directly quantized to meet the edge devices' desired level, such as NF4 or INT8. To address accuracy loss from quantization, surrogate paths are introduced, leveraging low-rank approximations on a layer-by-layer basis. These paths are trained with a sensitivity-based metric on minimal training data to recover accuracy loss under quantization as well as due to process variability, such as when the main prediction path is implemented using analog acceleration. Our simulation results show that neural precision polarization enables approximately 464 TOPS per Watt MAC efficiency and reliability by integrating rank-8 error recovery paths with highly efficient, though potentially unreliable, bit plane-wise compute-in-memory processing.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Intelligent Sensing-to-Action for Robust Autonomy at the Edge: Opportunities and Challenges

    cs.RO 2025-02 conditional novelty 3.0 of 10

    Bidirectional sensing-action loops, built from generative sensing, Koopman-based control, neuromorphic processing, and multi-agent coordination, can markedly reduce energy and latency for edge autonomy, according to t...

Pith tools