Revisit Multinomial Logistic Regression in Deep Learning: Data Dependent Model Initialization for Image Recognition
arXiv: Computer Vision and Pattern Recognition, Volume abs/1809.06131, 2018.
We study in this paper how to initialize the parameters of multinomial logistic regression (a fully connected layer followed with softmax and cross entropy loss), which is widely used in deep neural network (DNN) models for classification problems. As logistic regression is widely known not having a closed-form solution, it is usually ran...More
Full Text (Upload PDF)
PPT (Upload PPT)