February 2018
Intermediate to advanced
378 pages
10h 14m
English
CondenseNet was proposed by Gao Huang, Shichen Liu, Laurens van der Maaten, and Kilian Q. Weinberger. It reaches unprecedented levels of efficiency by combining dense connectivity between layers with a mechanism to remove unused connections, and therefore enables reuse of features within the network. CondenseNet is believed to be much more efficient than the state-of-the-art compact convolutional networks, such as MobileNets and ShuffleNets.
Refer to this: CondenseNet: An Efficient DenseNet using Learned Group Convolutions, Gao Huang, Shichen Liu, Laurens van der Maaten, Kilian Q. Weinberger, November 25, 2017: https://arxiv.org/abs/1711.09224.
Read now
Unlock full access