ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks

3 May 2015  ·  Francesco Visin, Kyle Kastner, Kyunghyun Cho, Matteo Matteucci, Aaron Courville, Yoshua Bengio ·

In this paper, we propose a deep neural network architecture for object recognition based on recurrent neural networks. The proposed network, called ReNet, replaces the ubiquitous convolution+pooling layer of the deep convolutional neural network with four recurrent neural networks that sweep horizontally and vertically in both directions across the image. We evaluate the proposed ReNet on three widely-used benchmark datasets; MNIST, CIFAR-10 and SVHN. The result suggests that ReNet is a viable alternative to the deep convolutional neural network, and that further investigation is needed.

PDF Abstract

Results from the Paper
Edit

Ranked #34 on Image Classification on MNIST

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data 		Result Benchmark
Image Classification CIFAR-10 ReNet Percentage correct 87.7 # 199
Compare
Image Classification MNIST ReNet Percentage error 0.5 # 34
Compare
Image Classification SVHN ReNet Percentage error 2.4 # 35
Compare

Methods
Add Remove

No methods listed for this paper. Add relevant methods here
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy