Pith. sign in

REVIEW 6 cited by

Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors

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 2006.10159 v3 pith:FBLKGCHP submitted 2020-06-15 physics.ins-det cs.LGeess.IVeess.SPhep-ex

classification physics.ins-detcs.LGeess.IVeess.SPhep-ex
keywords inferenceconsumptiondeepmodelquantizationsizeautomaticedge
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Although the quest for more accurate solutions is pushing deep learning research towards larger and more complex algorithms, edge devices demand efficient inference and therefore reduction in model size, latency and energy consumption. One technique to limit model size is quantization, which implies using fewer bits to represent weights and biases. Such an approach usually results in a decline in performance. Here, we introduce a method for designing optimally heterogeneously quantized versions of deep neural network models for minimum-energy, high-accuracy, nanosecond inference and fully automated deployment on chip. With a per-layer, per-parameter type automatic quantization procedure, sampling from a wide range of quantizers, model energy consumption and size are minimized while high accuracy is maintained. This is crucial for the event selection procedure in proton-proton collisions at the CERN Large Hadron Collider, where resources are strictly limited and a latency of ${\mathcal O}(1)~\mu$s is required. Nanosecond inference and a resource consumption reduced by a factor of 50 when implemented on field-programmable gate array hardware are achieved.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

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

  1. Real-time Surface-Code Error Correction Using an FPGA-based Neural-Network Decoder

    quant-ph 2026-05 unverdicted novelty 6.0 of 10

    An FPGA-based neural-network decoder achieves 550 ns deterministic closed-loop latency for real-time distance-3 surface code error correction on a superconducting processor, matching offline decoding performance.

  2. On-chip probabilistic inference for charged-particle tracking at the sensor edge

    physics.ins-det 2026-02 unverdicted novelty 6.0 of 10

    Neural networks integrated into silicon sensor front-end electronics can regress charged-particle hit positions and angles with calibrated uncertainties from single-layer data while satisfying hardware constraints on ...

  3. SparsePixels: Efficient Convolution for Sparse Data on FPGAs

    cs.AR 2025-12 conditional novelty 6.0 of 10

    A fixed-budget sparse-convolution FPGA framework runs CNNs on <=20 of ~4000 pixels, achieving 0.665 us inference for MicroBooNE with a 73x speedup and ~2% AUC loss.

  4. wa-hls4ml: A Benchmark and Surrogate Models for hls4ml Resource and Latency Estimation

    cs.LG 2025-11 conditional novelty 6.0 of 10

    A new open benchmark with 683,176 synthesized hls4ml designs plus GNN/transformer surrogates that predict FPGA resources/latency accurately in-distribution but poorly on out-of-distribution scientific models.

  5. Arbitrary Precision Printed Ternary Neural Networks with Holistic Evolutionary Approximation

    eess.SP 2025-08 conditional novelty 6.0 of 10

    A framework co-designs approximate printed ternary neural networks and their analog front-ends, claiming up to 17x smaller area and 59x lower power than prior printed classifiers at under 5% accuracy loss.

  6. APEIRON: composing smart TDAQ systems for high energy physics experiments

    physics.ins-det 2026-07 unverdicted novelty 4.0 of 10

    APEIRON is a distributed heterogeneous processing framework for multi-FPGA TDAQ systems in HEP that spans low-level drivers to HLS-based dataflow programming, demonstrated via a particle identification application for...

Pith tools