1.5k citations · 2.5k across the 34 of their papers we have counts for
4 papers · 1 filter
Spectral-Spatial Classification of Hyperspectral Image Using Autoencoders
Zhouhan Lin, Yushi Chen, Xing Zhao +1
Hyperspectral image (HSI) classification is a hot topic in the remote sensing community. This paper proposes a new framework of spectral-spatial feature extraction for HSI classifi…
How far can we go without convolution: Improving fully-connected networks
Zhouhan Lin, Roland Memisevic, Kishore Konda
We propose ways to improve the performance of fully connected networks. We found that two approaches in particular have a strong effect on performance: linear bottleneck layers and…
Neural Networks with Few Multiplications
Zhouhan Lin, Matthieu Courbariaux, Roland Memisevic +1
For most deep learning algorithms training is notoriously time consuming. Since most of the computation in training neural networks is typically spent on floating point multiplicat…
Towards Biologically Plausible Deep Learning
Yoshua Bengio, Dong-Hyun Lee, Jorg Bornschein +2
Neuroscientists have long criticised deep learning algorithms as incompatible with current knowledge of neurobiology. We explore more biologically plausible versions of deep repres…