We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 297612b commit 3c250e2Copy full SHA for 3c250e2
LeNet5/readme.txt
@@ -0,0 +1,10 @@
1
+Benchmarking the performance of the following methods on the MNIST dataset:
2
+
3
+Momentum
4
+Adam
5
+KFAC
6
+Fisher type preconditioner (square root version)
7
+Newton type preconditioner
8
9
+For each method, we train it with ten epochs, anneal its learning rate from lr to 0.01*lr,
10
+and tune its hyperparameters to optimize its test classification error rate.
0 commit comments