Residual neural networks

tags

Neural networks, Convolutional neural networks, Computer vision

resources

(He et al. 2016)

Residual neural networks are neural networks with skip-connections (or shortcuts, residual connections) that will bypass some of the networks operations in depth.

Highway networks

(Srivastava et al. 2015)

DenseNets

(<cite itemprop=“citation” itemscope=““Huang, Liu ,n.d.)

Bibliography

1. Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. June 2016. "Deep Residual Learning for Image Recognition". In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–78. Las Vegas, NV, USA: IEEE. DOI.
2. Rupesh Kumar Srivastava, Klaus Greff, Jürgen Schmidhuber. November 3, 2015. "Highway Networks". Arxiv:1505.00387 [cs]. http://arxiv.org/abs/1505.00387.
3. Gao Huang, Zhuang Liu. n.d.. "Densely Connected Convolutional Networks", 9.