AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Nonparametric Bayesian Deep Networks with Local Competition

Konstantinos Panousis, Sotirios Chatzis, Sergios Theodoridis

ICML 2019 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Approximate inference in Bayesian neural networks · 3 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
use SB-LWTA with two competing units instead of ReLULeNet-300-100 · MNISTerror (%): 1.60 -> 1.31Improved
use SB-LWTA with four competing units instead of ReLULeNet-300-100 · MNISTerror (%): 1.60 -> 1.34Improved
reduce weight bit precision using inferred posterior varianceSB-LWTA/4 units · MNIST, LeNet-300-100error (%): 1.34 -> 1.5Hurt
replace LWTA blocks with ReLU units (ablation)SB-LWTA · MNIST, LeNet-300-100 with connections thresholdedError (%): 1.7 -> 1.75Mixed
increase competitors per LWTA block from two to four (ablation)SB-LWTA · MNIST, LeNet-300-100error (%): 1.31 -> 1.34Hurt
replace LWTA blocks with ReLU units (ablation)SB-LWTA · MNIST, LeNet-5-CaffeError (%): 0.9 -> 0.9No clear effect
use four competing feature maps instead of two (ablation)SB-LWTA · MNIST, LeNet-5-CaffeError (%): 0.9 -> 0.8Improved
infer and omit unnecessary connections using utility indicators (ablation)SB-LWTA (2 units) · MNIST, LeNet-300-100Error (%): 1.31 -> 1.7Mixed
infer and omit unnecessary convolutional componentsSB-LWTA-2 · MNIST, LeNet-5-CaffeError (%): 0.9No clear effect

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