AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Deep Complex Networks

Chiheb Trabelsi, Olexa Bilaniuk, Ying Zhang, Dmitriy Serdyuk, Sandeep Subramanian, Joao Felipe Santos, Soroush Mehri, Negar Rostamzadeh, Yoshua Bengio, Christopher J Pal

ICLR 2018 · Architectures and efficiency › RNNs and normalization · approach: Weight normalization and decay interplay · 167 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 a complex-valued network with CReLU instead of a real-valued networkwide-and-shallow residual network · CIFAR-100classification error: 27.22 -> 26.36Improved
use a complex-valued network with CReLU instead of a real-valued networkwide-and-shallow residual network · CIFAR-10classification error: 5.42 -> 6.17Hurt
use a complex-valued network with CReLU instead of a real-valued networkwide-and-shallow residual network · SVHN*classification error: 3.42 -> 3.70Hurt
use the deep complex model instead of the deep real modelMusicNet transcription · MusicNetaverage precision: 69.6 -> 72.9Improved
use a complex convolutional LSTM instead of a real convolutional LSTMspeech spectrum prediction · TIMIT testMSE: 12.18 -> 11.90Improved
replace CReLU with zReLU (ablation)complex residual networks · CIFAR-10classification error: 6.17 -> 11.71Hurt
replace CReLU with modReLU (ablation)complex residual networks · CIFAR-10classification error: 6.17 -> 23.42Hurt
replace CReLU with zReLU (ablation)complex residual networks · SVHN*classification error: 3.70 -> 80.41Hurt
replace complex batch normalization with naive complex batch normalization (ablation)complex residual networks · SVHN*classification errorHurt

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