• kiran singla
• Prakash Mohod

Deep convolutional neural networks have shown remarkable performance in image classification tasks in recent years. Due to the complexity and vanishing gradient problem, it normally takes a lot of time and more computational power to train deeper neural networks. Deep residual networks were introduced to tackle these problems, making the training process faster and attain more accuracy compared to their equivalent Deep neural networks. Since then more and more residual network variants and architectures have been proposed, and they form a residual networks family together. In this paper, we provide a comprehensive survey of the recent developments on deep residual networks. we summarize different residual network architectures and compare their performances on CIFAR-10 and CIFAR-100 dataset for image classification.

Image classification, Residual network, Highway Network, Residual Networks of Residual Networks; PyramidNet, Pyramidal RoR, stochastic depth, wide residual network.

"SURVEY ON DEEP RESIDUAL NETWORK FOR IMAGE RECOGNITION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.844-851, June-2019, Available :http://www.jetir.org/papers/JETIR1906265.pdf

"SURVEY ON DEEP RESIDUAL NETWORK FOR IMAGE RECOGNITION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp844-851, June-2019, Available at : http://www.jetir.org/papers/JETIR1906265.pdf