Differences

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

--- projects:localnn:start [2015/02/11 16:07] – hj
+++ projects:localnn:start [2015/05/11 20:12] (current) – hj
@@ Line 3: / Line 3: @@
 ===== Locally Connected Neural Networks =====
-{{ :projects:localnn:screen_shot_2015-02-11_at_11.03.36_am.png?0x200 |LCNN}}
+{{ :projects:localnn:screen_shot_2015-02-11_at_11.03.36_am.png?0x250 |LCNN}}
 \\
 \\
@@ Line 10: / Line 10: @@
 network (LCNN), which imposes local connections within the neighboring neurons
 in the same layer in order to imitate the lateral inhibition.
+  * Our maxout neuron based LCNN can achieve a 0.79% classfication error rate on the MNIST task without using pretraining and data augmentation.
+  * Our ReLU based LCNN can achieve a 15.0% word error rate in speech recognition on the Switchboard database.
+ To our knowledge, both results set the new state of the art performance on these tasks under similar training conditions.
+**Reference:**\\
+[1] //Shiliang Zhang, Hui Jiang, Li-Rong Dai and Si Wei//, ``Locally Connected Deep Neural Networks,'' submitted to //Neural Networks//, 2015.