Improving Deep Neural Networks with Probabilistic Maxout Units

20 Dec 2013Jost Tobias SpringenbergMartin Riedmiller

We present a probabilistic variant of the recently introduced maxout unit. The success of deep neural networks utilizing maxout can partly be attributed to favorable performance under dropout, when compared to rectified linear units... (read more)

PDF Abstract

Code


No code implementations yet. Submit your code now

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Image Classification CIFAR-10 DNN+Probabilistic Maxout Percentage correct 90.6 # 66
Image Classification CIFAR-100 DNN+Probabilistic Maxout Percentage correct 61.9 # 67