Pith. sign in

REVIEW 2 cited by

Probabilistic Binary Neural Networks

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 1809.03368 v1 pith:OVH2LWT2 submitted 2018-09-10 cs.LG stat.ML

classification cs.LGstat.ML
keywords neuralbinaryblrnetnetworkactivationsneednetworksprobabilistic
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Low bit-width weights and activations are an effective way of combating the increasing need for both memory and compute power of Deep Neural Networks. In this work, we present a probabilistic training method for Neural Network with both binary weights and activations, called BLRNet. By embracing stochasticity during training, we circumvent the need to approximate the gradient of non-differentiable functions such as sign(), while still obtaining a fully Binary Neural Network at test time. Moreover, it allows for anytime ensemble predictions for improved performance and uncertainty estimates by sampling from the weight distribution. Since all operations in a layer of the BLRNet operate on random variables, we introduce stochastic versions of Batch Normalization and max pooling, which transfer well to a deterministic network at test time. We evaluate the BLRNet on multiple standardized benchmarks.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Energy-Efficient Supervised Learning with a Binary Stochastic Forward-Forward Algorithm

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Binary stochastic forward-forward training reaches near-real-valued forward-forward accuracy on image benchmarks while estimating 10-100x energy savings in p-bit hardware.

  2. A Principled Bayesian Framework for Training Binary and Spiking Neural Networks

    cs.LG 2025-05 conditional novelty 5.0 of 10

    A variational Bayesian framework with importance-weighted straight-through estimators trains binary and spiking networks without normalization layers, matching surrogate-gradient baselines on CIFAR-10, DVS Gesture, and SHD.

Pith tools