Surprising properties of dropout in deep networks (Q4558527): Difference between revisions

@@ Property / arXiv ID @@
+.04484
@@ Property / arXiv ID: 1602.04484 / rank @@
+Normal rank
@@ Property / cites work @@
+The dropout learning algorithm
@@ Property / cites work: The dropout learning algorithm / rank @@
+Normal rank
@@ Property / cites work @@
+Convexity, Classification, and Risk Bounds
@@ Property / cites work: Convexity, Classification, and Risk Bounds / rank @@
+Normal rank
@@ Property / cites work @@
+Population theory for boosting ensembles.
@@ Property / cites work: Population theory for boosting ensembles. / rank @@
+Normal rank
@@ Property / cites work @@
+On the Inductive Bias of Dropout
@@ Property / cites work: On the Inductive Bias of Dropout / rank @@
+Normal rank
@@ Property / cites work @@
+Q2934059
@@ Property / cites work: Q2934059 / rank @@
+Normal rank
@@ Property / cites work @@
+Random classification noise defeats all convex potential boosters
+Normal rank
@@ Property / cites work @@
+Statistical behavior and consistency of classification methods based on convex risk minimization.
+Normal rank