AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Universal Approximation Property and Equivalence of Stochastic Computing-Based Neural Networks and Binary Neural Networks

Yanzhi Wang, Zheng Zhan, Liang Zhao, Jian Tang, Siyue Wang, Jiayu Li, Bo Yuan, Wujie Wen, Xue Lin

AAAI 2019 · Architectures and efficiency › Quantization · approach: Binary neural networks · 13 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Represent network parameters and inputs with stochastic bit-streamsIdeal SCNN · Continuous functions on I_nuniversal approximation probability: 1Improved
Use binary-valued inputs, weights, and biasesIdeal BNN · Continuous functions on I_nuniversal approximation probability: 1Improved
Use SCNNs rather than BNNs to reduce spatial input requirementsHardware implementations · Hardware deploymentI/O requirementImproved
Increase stochastic bit-stream length M to meet the stated approximation guaranteeSCNN · Continuous functions on I_napproximation error: M > \frac{(n+1)^2\cdot N^2}{\epsilon^2\delta}Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy