data_mining:neural_network:model_combination

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
data_mining:neural_network:model_combination [2017/08/19 20:11] – phreazerdata_mining:neural_network:model_combination [2017/08/19 20:12] (current) – [Approximating full Bayesian learning in a NN] phreazer
Line 86: Line 86:
  
 If we compute gradient of cost function on a **random mini-batch**, we will get an unbiased estimate with sampling noise. If we compute gradient of cost function on a **random mini-batch**, we will get an unbiased estimate with sampling noise.
 +
 +====== Dropout ======
 +See [[data_mining:neural_network:regularization|Regularization]]
 +
  • data_mining/neural_network/model_combination.1503173499.txt.gz
  • Last modified: 2017/08/19 20:11
  • by phreazer