Landscape analysis for shallow neural networks: complete classification of critical points for affine target functions (Q2156337): Difference between revisions

@@ Property / cites work @@
+A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions
+Normal rank
@@ Property / cites work @@
+Q4969246
@@ Property / cites work: Q4969246 / rank @@
+Normal rank
@@ Property / cites work @@
+First-order methods almost always avoid strict saddle points
+Normal rank
@@ Property / cites work @@
+Gradient Descent Only Converges to Minimizers: Non-Isolated Critical Points and Invariant Regions
+Normal rank
@@ Property / cites work @@
+Topological properties of the set of functions generated by neural networks of fixed size
+Normal rank
@@ Property / cites work @@
+Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural Networks
+Normal rank
@@ Property / cites work @@
+Spurious Valleys in Two-layer Neural Network Optimization Landscapes
+Normal rank