Minimal Width for Universal Property of Deep RNN

v1v2 (latest)

Minimal Width for Universal Property of Deep RNN

25 November 2022

ArXiv (abs)PDF HTML

Papers citing "Minimal Width for Universal Property of Deep RNN"

8 / 8 papers shown

Title
CoAtNet: Marrying Convolution and Attention for All Data Sizes Zihang Dai Hanxiao Liu Quoc V. Le Mingxing Tan ViT 120 1,207 0 09 Jun 2021
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations Alexei Baevski Henry Zhou Abdel-rahman Mohamed Michael Auli SSL 282 5,801 0 20 Jun 2020
Are Transformers universal approximators of sequence-to-sequence functions? Chulhee Yun Srinadh Bhojanapalli A. S. Rawat Sashank J. Reddi Sanjiv Kumar 115 355 0 20 Dec 2019
ResNet with one-neuron hidden layers is a Universal Approximator Hongzhou Lin Stefanie Jegelka 105 228 0 28 Jun 2018
Universality of Deep Convolutional Neural Networks Ding-Xuan Zhou HAI PINN 412 516 0 28 May 2018
The Expressive Power of Neural Networks: A View from the Width Zhou Lu Hongming Pu Feicheng Wang Zhiqiang Hu Liwei Wang 99 894 0 08 Sep 2017
On the Properties of Neural Machine Translation: Encoder-Decoder Approaches Kyunghyun Cho B. V. Merrienboer Dzmitry Bahdanau Yoshua Bengio AI4CE AIMat 251 6,779 0 03 Sep 2014
Neural Machine Translation by Jointly Learning to Align and Translate Dzmitry Bahdanau Kyunghyun Cho Yoshua Bengio AIMat 558 27,311 0 01 Sep 2014