AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Expected Gradients of Maxout Networks and Consequences to Parameter Initialization

Hanna Tseran, Guido Montufar

ICML 2023 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 0 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 maxout initialization (c = 0.55555) instead of ReLU He initializationFully-connected maxout network trained with SGD · MNIST testaccuracy: 53.22^{\pm 24.08} -> 97.8^{\pm 0.15}Improved
Use maxout initialization instead of ReLU He initializationFully-connected maxout network trained with SGD · Iris testaccuracy: 91.67^{\pm 3.73} -> 91.67^{\pm 3.73}No clear effect
Use maxout initialization instead of ReLU He initializationConvolutional maxout network trained with SGD · MNIST testaccuracy: 99.49^{\pm 0.04} -> 99.59^{\pm 0.04}No clear effect
Use maxout initialization instead of max-pooling initializationConvolutional maxout network trained with SGD · CIFAR-10 testaccuracy: 91.7^{\pm 0.17} -> 91.21^{\pm 0.13}Hurt
Use maxout initialization instead of max-pooling initializationConvolutional maxout network trained with SGD · CIFAR-100 testaccuracy: 65.33^{\pm 0.27} -> 65.39^{\pm 0.39}No clear effect
Use maxout initialization instead of max-pooling initializationConvolutional maxout network trained with SGD · Fashion MNIST testaccuracy: 93.55^{\pm 0.13} -> 93.49^{\pm 0.13}No clear effect
Use maxout initialization instead of ReLU He initializationConvolutional maxout network trained with SGD · SVHN testaccuracy: 96.74^{\pm 0.03} -> 97.78^{\pm 0.02}Improved
Use maxout initialization instead of naive initializationFully-connected maxout network trained with Adam · MNIST test, all epochsaccuracy: 98.13^{\pm 0.09} -> 98.12^{\pm 0.10}No clear effect
Use maxout initialization instead of max-pooling initializationConvolutional maxout network trained with Adam · MNIST test, all epochsaccuracy: 99.53^{\pm 0.04} -> 99.47^{\pm 0.07}No clear effect
Use maxout initialization instead of max-pooling initializationConvolutional maxout network trained with Adam · Fashion MNIST test, all epochsaccuracy: 93.57^{\pm 0.17} -> 93.45^{\pm 0.10}No clear effect
Use maxout initialization instead of max-pooling initializationConvolutional maxout network trained with Adam · CIFAR-10 test, all epochsaccuracy: 91.33^{\pm 0.31} -> 91.06^{\pm 0.22}No clear effect
Use maxout initialization instead of max-pooling initializationConvolutional maxout network trained with Adam · CIFAR-100 test, all epochsaccuracy: 65.33^{\pm 1.26} -> 61.96^{\pm 0.58}Hurt

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