Next steps

Next up is dropout layers. remember that it can be used to see uncerstaty in multiply output, which is not in the book

include/modules/neural_networks/layers/Dense_Layer.h

@@ -66,7 +66,7 @@ namespace neural_networks{
         	dbiases = numerics::sum_rowwise(dvalues);
 
 
-        	// Gradients on regularization
+        	// Gradients on regularization 
         	// L1 on weights
         	if(weight_regularizer_l1){
         		utils::Matrix<T> dL1(weights.rows(), weights.cols(), T{1});