Top network posts

• 81 Stratified Train/Test-split in scikit-learn
• 44 Importance of local response normalization in CNN
• 40 NaN loss when training regression network
• 39 Are pooling layers added before or after dropout layers?
• 36 Finding gradient of a Caffe conv-filter with regards to input
• 32 Choosing between CPU and GPU for training a neural network
• 32 Using explicit (predefined) validation set for grid search with sklearn
• View more network posts →