Exploring generative perspective of convolutional neural networks by learning random field models
STATISTICS AND ITS INTERFACE, pp. 515-529, 2018.
This paper studies the convolutional neural network (ConvNet or CNN) from a statistical modeling perspective. The ConvNet has proven to be a very successful discriminative learning machine. In this paper, we explore the generative perspective of the ConvNet. We propose to learn Markov random field models called FRAME (Filters, Random fiel...More
Full Text (Upload PDF)
PPT (Upload PPT)